journalArticle
104
AMERICAN JOURNAL OF PUBLIC HEALTH
DOI 10.2105/AJPH.2013.301726
5
Hohl
Sarah D.
Gonzalez
Claire
Carosso
Elizabeth
Ibarra
Genoveva
Thompson
Beti
"I Did It for Us and I Would Do It Again": Perspectives of Rural Latinos on Providing Biospecimens for Research
Objectives. We elicited perspectives of rural Latino farmworkers and non-farmworkers about their participation in a community-based participatory pesticides exposure study in which they provided multiple biospecimens.Methods. Between March and April 2012, we conducted semistructured, one-on-one interviews with 39 rural Latino farmworkers and non-farmworkers in Washington State (n = 39). Nineteen open-ended interview questions aimed to elicit participants' attitudes toward, expectations and experiences of biospecimen collection for research, and willingness to participate in future biomedical research studies. We reviewed and coded transcriptions using qualitative principles of grounded theory in which concepts were identified and themes derived from interview data.Results. We grouped themes into 3 major categories: (1) motivation to participate, (2) challenges of participation, and (3) perceived rewards of participation. Many participants were motivated by the perceived importance of the study topic and a desire to acquire and contribute to new knowledge. Respondents said that the benefits of participation outweighed the challenges, and many expressed satisfaction to be able to contribute to research that would benefit future generations.Conclusions. Our findings supported the use of community-based participatory research to engage minorities as participants and invested parties in such studies.
2014 MAY
WOS:000341790600035
QID: Q28384057
911-916
journalArticle
137
JOURNAL OF ENVIRONMENTAL MANAGEMENT
DOI 10.1016/j.jenvman.2013.11.057
Dyer
J.
Stringer
L. C.
Dougill
A. J.
Leventon
J.
Nshimbi
M.
Chama
F.
Kafwifwi
A.
Muledi
J. I.
Kaumbu
J. -M. K.
Falcao
M.
Muhorro
S.
Munyemba
F.
Kalaba
G. M.
Syampungani
S.
Assessing participatory practices in community-based natural resource management: Experiences in community engagement from southern Africa
The emphasis on participatory environmental management within international development has started to overcome critiques of traditional exclusionary environmental policy, aligning with shifts towards decentralisation and community empowerment. However, questions are raised regarding the extent to which participation in project design and implementation is meaningful and really engages communities in the process. Calls have been made for further local-level (project and community-scale) research to identify practices that can increase the likelihood of meaningful community engagement within externally initiated projects. This paper presents data from three community-based natural resource management (CBNRM) project case studies from southern Africa, which promote Joint Forest Management (JFM), tree planting for carbon and conservation agriculture. Data collection was carried out through semi-structured interviews with key stakeholders, community-level meetings, focus groups and interviews. We find that an important first step for a meaningful community engagement process is to define 'community' in an open and participatory manner. Two-way communication at all stages of the community engagement process is shown to be critical, and charismatic leadership based on mutual respect and clarity of roles and responsibilities is vital to improve the likelihood of participants developing understanding of project aims and philosophy. This can lead to successful project outcomes through community ownership of the project goals and empowerment in project implementation. Specific engagement methods are found to be less important than the contextual and environmental factors associated with each project, but consideration should be given to identifying appropriate methods to ensure community representation. Our findings extend current thinking on the evaluation of participation by making explicit links between the community engagement process and project outcomes, and by identifying further criteria that can be considered in process and outcome-based evaluations. We highlight good practices for future CBNRM projects which can be used by project designers and initiators to further the likelihood of successful project outcomes. (C) 2014 Published by Elsevier Ltd.
2014 MAY 1
WOS:000336359100017
QID: Q30360238
137-145
journalArticle
9
PLOS ONE
DOI 10.1371/journal.pone.0096817
5
Reddy
Sheila M. W.
Groves
Theodore
Nagavarapu
Sriniketh
Consequences of a Government-Controlled Agricultural Price Increase on Fishing and the Coral Reef Ecosystem in the Republic of Kiribati
Background: Economic development policies may have important economic and ecological consequences beyond the sector they target. Understanding these consequences is important to improving these policies and finding opportunities to align economic development with natural resource conservation. These issues are of particular interest to governments and non-governmental organizations that have new mandates to pursue multiple benefits. In this case study, we examined the direct and indirect economic and ecological effects of an increase in the government-controlled price for the primary agricultural product in the Republic of Kiribati, Central Pacific.Methods/Principal Findings: We conducted household surveys and underwater visual surveys of the coral reef to examine how the government increase in the price of copra directly affected copra labor and indirectly affected fishing and the coral reef ecosystem. The islands of Kiribati are coral reef atolls and the majority of households participate in copra agriculture and fishing on the coral reefs. Our household survey data suggest that the 30% increase in the price of copra resulted in a 32% increase in copra labor and a 38% increase in fishing labor. Households with the largest amount of land in coconut production increased copra labor the most and households with the smallest amount of land in coconut production increased fishing the most. Our ecological data suggests that increased fishing labor may result in a 20% decrease in fish stocks and 4% decrease in coral reef-builders.Conclusions/Significance: We provide empirical evidence to suggest that the government increase in the copra price in Kiribati had unexpected and indirect economic and ecological consequences. In this case, the economic development policy was not in alignment with conservation. These results emphasize the importance of accounting for differences in household capital and taking a systems approach to policy design and evaluation, as advocated by sustainable livelihood and ecosystem-based management frameworks.
2014 MAY 12
WOS:000336653300034
QID: Q33599839
journalArticle
481
SCIENCE OF THE TOTAL ENVIRONMENT
DOI 10.1016/j.scitotenv.2014.02.052
Khoshnevisan
Benyamin
Rajaeifar
Mohammad Ali
Clark
Sean
Shamahirband
Shahaboddin
Anuar
Nor Badrul
Shuib
Nor Liyana Mohd
Gani
Abdullah
Evaluation of traditional and consolidated rice farms in Guilan Province, Iran, using life cycle assessment and fuzzy modeling
In this study the environmental impact of consolidated rice farms (CF) - farms which have been integrated to increase the mechanization index - and traditional farms (TF) - small farms with lower mechanization index - in Guilan Province, Iran, were evaluated and compared using Life cycle assessment (LCA) methodology and adaptive neuro-fuzzy inference system (ANFIS). Foreground data were collected from farmers using face-to-face questionnaires and background information about production process and inventory data was taken from the EcoInvent (R) 2.0 database. The system boundary was confined to within the farm gate (cradle to farm gate) and two functional units (land and mass based) were chosen. The study also included a comparison of the input-output energy flows of the farms. The results revealed that the average amount of energy consumed by the CFs was 57 GJ compared to 74.2 GJ for the TFs. The energy ratios for CFs and TFs were 1.6 and 0.9, respectively. The LCA results indicated that CFs produced fewer environmental burdens per ton of produced rice. When compared according to the land-based FU the same results were obtained. This indicates that the differences between the two types of farms were not caused by a difference in their production level, but rather by improved management on the CFs. The analysis also showed that electricity accounted for the greatest share of the impact for both types of farms, followed by P-based and N-based chemical fertilizers. These findings suggest that the CFs had superior overall environmental performance compared to the TFs in the study area. The performance metrics of the model based on ANFIS show that it can be used to predict the environmental burdens of rice production with high accuracy and minimal error. (C) 2014 Elsevier B.V. All rights reserved.
2014 MAY 15
WOS:000335096400027
QID: Q44819749
242-251
journalArticle
178
INTERNATIONAL JOURNAL OF FOOD MICROBIOLOGY
DOI 10.1016/j.ijfoodmicro.2014.02.023
Copetti
Marina V.
Iamanaka
Beatriz T.
Pitt
John I.
Taniwaki
Marta H.
Fungi and mycotoxins in cocoa: From farm to chocolate
Cocoa is an important crop, as it is the raw material from which chocolate is manufactured. It is grown mainly in West Africa although significant quantities also come from Asia and Central and South America. Primary processing is carried out on the farm, and the flavour of chocolate starts to develop at that time. Freshly harvested pods are opened, the beans, piled in heaps or wooden boxes, are fermented naturally by yeasts and bacteria, then dried in the sun on wooden platforms or sometimes on cement or on the ground, where a gradual reduction in moisture content inhibits microbial growth. Beans are then bagged and marketed. In processing plants, the dried fermented beans are roasted, shelled and ground, then two distinct processes are used, to produce powdered cocoa or chocolate. Filamentous fungi may contaminate many stages in cocoa processing, and poor practices may have a strong influence on the quality of the beans. Apart from causing spoilage, filamentous fungi may also produce aflatoxins and ochratoxin A. This review deals with the growth of fungal species and formation of mycotoxins during the various steps in cocoa processing, as well as reduction of these contaminants by good processing practices. Methodologies for fungal and mycotoxin detection and quantification are discussed while current data about dietary exposure and regulation are also presented. (c) 2014 Elsevier B.V. All rights reserved.
2014 MAY 16
WOS:000335708100003
QID: Q38199297
13-20
journalArticle
9
PLOS ONE
DOI 10.1371/journal.pone.0097288
5
Shekoofa
Avat
Emam
Yahya
Shekoufa
Navid
Ebrahimi
Mansour
Ebrahimie
Esmaeil
Determining the Most Important Physiological and Agronomic Traits Contributing to Maize Grain Yield through Machine Learning Algorithms: A New Avenue in Intelligent Agriculture
Prediction is an attempt to accurately forecast the outcome of a specific situation while using input information obtained from a set of variables that potentially describe the situation. They can be used to project physiological and agronomic processes; regarding this fact, agronomic traits such as yield can be affected by a large number of variables. In this study, we analyzed a large number of physiological and agronomic traits by screening, clustering, and decision tree models to select the most relevant factors for the prospect of accurately increasing maize grain yield. Decision tree models (with nearly the same performance evaluation) were the most useful tools in understanding the underlying relationships in physiological and agronomic features for selecting the most important and relevant traits (sowing date-location, kernel number per ear, maximum water content, kernel weight, and season duration) corresponding to the maize grain yield. In particular, decision tree generated by C&RT algorithm was the best model for yield prediction based on physiological and agronomical traits which can be extensively employed in future breeding programs. No significant differences in the decision tree models were found when feature selection filtering on data were used, but positive feature selection effect observed in clustering models. Finally, the results showed that the proposed model techniques are useful tools for crop physiologists to search through large datasets seeking patterns for the physiological and agronomic factors, and may assist the selection of the most important traits for the individual site and field. In particular, decision tree models are method of choice with the capability of illustrating different pathways of yield increase in breeding programs, governed by their hierarchy structure of feature ranking as well as pattern discovery via various combinations of features.
2014 MAY 15
WOS:000336789500046
QID: Q35168917
journalArticle
9
PLOS ONE
DOI 10.1371/journal.pone.0097814
5
Wu
Xinliang
Zhou
Bin
Yin
Chao
Guo
Yong
Lin
Ying
Pan
Li
Wang
Bin
Characterization of Natural Antisense Transcript, Sclerotia Development and Secondary Metabolism by Strand-Specific RNA Sequencing of Aspergillus flavus
Aspergillus flavus has received much attention owing to its severe impact on agriculture and fermented products induced by aflatoxin. Sclerotia morphogenesis is an important process related to A. flavus reproduction and aflatoxin biosynthesis. In order to obtain an extensive transcriptome profile of A. flavus and provide a comprehensive understanding of these physiological processes, the isolated mRNA of A. flavus CA43 cultures was subjected to high-throughput strand-specific RNA sequencing (ssRNA-seq). Our ssRNA-seq data profiled widespread transcription across the A. flavus genome, quantified vast transcripts (73% of total genes) and annotated precise transcript structures, including untranslated regions, upstream open reading frames (ORFs), alternative splicing variants and novel transcripts. We propose natural antisense transcripts in A. flavus might regulate gene expression mainly on the post-transcriptional level. This regulation might be relevant to tune biological processes such as aflatoxin biosynthesis and sclerotia development. Gene Ontology annotation of differentially expressed genes between the mycelia and sclerotia cultures indicated sclerotia development was related closely to A. flavus reproduction. Additionally, we have established the transcriptional profile of aflatoxin biosynthesis and its regulation model. We identified potential genes linking sclerotia development and aflatoxin biosynthesis. These genes could be used as targets for controlled regulation of aflatoxigenic strains of A. flavus.
2014 MAY 21
WOS:000336730600062
QID: Q33645502
journalArticle
509
NATURE
DOI 10.1038/nature13377
7502
Forsberg
Kevin J.
Patel
Sanket
Gibson
Molly K.
Lauber
Christian L.
Knight
Rob
Fierer
Noah
Dantas
Gautam
Bacterial phylogeny structures soil resistomes across habitats
Ancient and diverse antibiotic resistance genes (ARGs) have previously been identified from soil(1-3), including genes identical to those in human pathogens(4). Despite the apparent overlap between soil and clinical resistomes(4-6), factors influencing ARG composition in soil and their movement between genomes and habitats remain largely unknown(3). General metagenome functions often correlate with the underlying structure of bacterial communities(7-12). However, ARGs are proposed to be highly mobile(4,5,13), prompting speculation that resistomes may not correlate with phylogenetic signatures or ecological divisions(13,14). To investigate these relationships, we performed functional metagenomic selections for resistance to 18 antibiotics from 18 agricultural and grassland soils. The 2,895 ARGs we discovered were mostly new, and represent all major resistance mechanisms(15). We demonstrate that distinct soil types harbour distinct resistomes, and that the addition of nitrogen fertilizer strongly influenced soil ARG content. Resistome composition also correlated with microbial phylogenetic and taxonomic structure, both across and within soil types. Consistent with this strong correlation, mobility elements (genes responsible for horizontal gene transfer between bacteria such as transposases and integrases) syntenic with ARGs were rare in soil by comparison with sequenced pathogens, suggesting that ARGs may not transfer between soil bacteria as readily as is observed between human pathogens. Together, our results indicate that bacterial community composition is the primary determinant of soil ARG content, challenging previous hypotheses that horizontal gene transfer effectively decouples resistomes from phylogeny(13,14).
2014 MAY 29
WOS:000336457100047
QID: Q33837847
612-+
journalArticle
10
PLOS GENETICS
DOI 10.1371/journal.pgen.1004401
6
Fernandez
Eva
Perez-Perez
Alejandro
Gamba
Cristina
Prats
Eva
Cuesta
Pedro
Anfruns
Josep
Molist
Miquel
Arroyo-Pardo
Eduardo
Turbon
Daniel
Ancient DNA Analysis of 8000 B.C. Near Eastern Farmers Supports an Early Neolithic Pioneer Maritime Colonization of Mainland Europe through Cyprus and the Aegean Islands
The genetic impact associated to the Neolithic spread in Europe has been widely debated over the last 20 years. Within this context, ancient DNA studies have provided a more reliable picture by directly analyzing the protagonist populations at different regions in Europe. However, the lack of available data from the original Near Eastern farmers has limited the achieved conclusions, preventing the formulation of continental models of Neolithic expansion. Here we address this issue by presenting mitochondrial DNA data of the original Near-Eastern Neolithic communities with the aim of providing the adequate background for the interpretation of Neolithic genetic data from European samples. Sixty-three skeletons from the Pre Pottery Neolithic B (PPNB) sites of Tell Halula, Tell Ramad and Dja'de El Mughara dating between 8,700-6,600 cal. B. C. were analyzed, and 15 validated mitochondrial DNA profiles were recovered. In order to estimate the demographic contribution of the first farmers to both Central European and Western Mediterranean Neolithic cultures, haplotype and haplogroup diversities in the PPNB sample were compared using phylogeographic and population genetic analyses to available ancient DNA data from human remains belonging to the Linearbandkeramik-Alfoldi Vonaldiszes Keramia and Cardial/Epicardial cultures. We also searched for possible signatures of the original Neolithic expansion over the modern Near Eastern and South European genetic pools, and tried to infer possible routes of expansion by comparing the obtained results to a database of 60 modern populations from both regions. Comparisons performed among the 3 ancient datasets allowed us to identify K and N-derived mitochondrial DNA haplogroups as potential markers of the Neolithic expansion, whose genetic signature would have reached both the Iberian coasts and the Central European plain. Moreover, the observed genetic affinities between the PPNB samples and the modern populations of Cyprus and Crete seem to suggest that the Neolithic was first introduced into Europe through pioneer seafaring colonization.
2014 JUN
WOS:000338847700021
QID: Q21144871
journalArticle
58
MICROBIOLOGY AND IMMUNOLOGY
DOI 10.1111/1348-0421.12159
7
Saekhow
Prayuth
Mawatari
Takahiro
Ikeda
Hidetoshi
Coexistence of multiple strains of porcine parvovirus 2 in pig farms
The porcine parvovirus 2 (PPV2) genome was first identified in 2001 in Myanmar. Recently, the PPV2 genome has been found in several other countries. In this study, the prevalence of PPV2 in Japanese domestic pigs was investigated and found to be 58% (69/120) in healthy domestic pigs and 100% (69/69) in sick domestic pigs. Sequencing and phylogenetic analysis of the PCR products of the VP1 gene and an almost full length PPV2 clone indicated that diverged PPV2 strains exist in Japan. Clearly distinct strains of PPV2 were detected in 7 of the 10 pig farms.
2014 JUL
WOS:000339478400003
QID: Q42217550
382-387
journalArticle
21
INTERNATIONAL JOURNAL OF INJURY CONTROL AND SAFETY PROMOTION
DOI 10.1080/17457300.2013.792286
2
Kitching
Fiona
Jones
Christopher B.
Ibrahim
Joseph E.
Ozanne-Smith
Joan
Pedestrian worker fatalities in workplace locations, Australia, 2000-2010
Pedestrian deaths of workers in Australian workplaces (1 July 2000-31 December 2010) are described using coronial and safety authority fatality databases. One hundred and fifteen deaths were identified, with the majority male (93%) and aged over 50 years (59%). Four industries predominated (85% of deaths): Agriculture, Forestry and Fishing (31%), Construction (29%), Transport, Postal and Warehousing (16%) and Manufacturing (10%). Similarly, three occupations dominated: Farmers (28%), Labourers (27%) and Machinery Operators and Drivers (25%). Common circumstantial factors (reversing machines or vehicles, driver also the pedestrian, driver's vision impeded and working accompanied) occurred in the Construction, Transport and Manufacturing industries, providing collaborative opportunities for prevention. Deaths occurring in the Agriculture industry showed different circumstantial factors, likely needing different solutions. While some effective countermeasures are known, workplace pedestrian fatalities continue to occur. Prevention strategies are needed to share known information across industries and to produce data enhancements and new knowledge.
2014 JUN
WOS:000338030700009
QID: Q86745332
163-169
journalArticle
482
SCIENCE OF THE TOTAL ENVIRONMENT
DOI 10.1016/j.scitotenv.2014.02.103
Fernandez
Jose M.
Nieto
M. Aurora
Lopez-de-Sa
Esther G.
Gasco
Gabriel
Mendez
Ana
Plaza
Cesar
Carbon dioxide emissions from semi-arid soils amended with biochar alone or combined with mineral and organic fertilizers
Semi-arid soils cover a significant area of Earth's land surface and typically contain large amounts of inorganic C. Determining the effects of biochar additions on CO2 emissions from semi-arid soils is therefore essential for evaluating the potential of biochar as a climate change mitigation strategy. Here, we measured the CO2 that evolved from semi-arid calcareous soils amended with biochar at rates of 0 and 20 t ha(-1) in a full factorial combination with three different fertilizers (mineral fertilizer, municipal solid waste compost, and sewage sludge) applied at four rates (equivalent to 0, 75, 150, and 225 kg potentially available N ha(-1)) during 182 days of aerobic incubation. A double exponential model, which describes cumulative CO2 emissions from two active soil C compartments with different turnover rates (one relatively stable and the other more labile), was found to fit very well all the experimental datasets. In general, the organic fertilizers increased the size and decomposition rate of the stable and labile soil C pools. In contrast, biochar addition had no effects on any of the double exponential model parameters and did not interact with the effects ascribed to the type and rate of fertilizer. After 182 days of incubation, soil organic and microbial biomass C contents tended to increase with increasing the application rates of organic fertilizer, especially of compost, whereas increasing the rate of mineral fertilizer tended to suppress microbial biomass. Biochar was found to increase both organic and inorganic C contents in soil and not to interact with the effects of type and rate of fertilizer on C fractions. As a whole, our results suggest that the use of biochar as enhancer of semi-arid soils, either alone or combined with mineral and organic fertilizers, is unlikely to increase abiotic and biotic soil CO2 emissions. (C) 2014 Elsevier B.V. All rights reserved.
2014 JUN 1
WOS:000335625100001
QID: Q30778584
1-7
journalArticle
281
PROCEEDINGS OF THE ROYAL SOCIETY B-BIOLOGICAL SCIENCES
DOI 10.1098/rspb.2014.0649
1786
Paquette
Sebastien Rioux
Pelletier
Fanie
Garant
Dany
Belisle
Marc
Severe recent decrease of adult body mass in a declining insectivorous bird population
Migratory bird species that feed on air-borne insects are experiencing widespread regional declines, but these remain poorly understood. Agricultural intensification in the breeding range is often regarded as one of the main drivers of these declines. Here, we tested the hypothesis that body mass in breeding individuals should reflect habitat quality in an aerial insectivore, the tree swallow (Tachycineta bicolor), along a gradient of agricultural intensity. Our dataset was collected over 7 years (2005-2011) and included 2918 swallow captures and 1483 broods. Analyses revealed a substantial decline of the population over the course of the study (-19% occupancy rate), mirrored by decreasing body mass. This trend was especially severe in females, representing a total loss of 8% of their mass. Reproductive success was negatively influenced by intensive agriculture, but did not decrease over time. Interestingly, variation in body mass was independent of breeding habitat quality, leading us to suggest that this decline in body mass may result from carry-over effects from non-breeding areas and affect population dynamics through reduced survival. This work contributes to the growing body of evidence suggesting that declines in migratory aerial insectivores are driven by multiple, complex factors requiring better knowledge of year-round habitat use.
2014 JUL 7
WOS:000336784500027
QID: Q52772232
journalArticle
20
GLOBAL CHANGE BIOLOGY
DOI 10.1111/gcb.12482
7
Gilroy
James J.
Woodcock
Paul
Edwards
Felicity A.
Wheeler
Charlotte
Medina Uribe
Claudia A.
Haugaasen
Torbjorn
Edwards
David P.
Optimizing carbon storage and biodiversity protection in tropical agricultural landscapes
With the rapidly expanding ecological footprint of agriculture, the design of farmed landscapes will play an increasingly important role for both carbon storage and biodiversity protection. Carbon and biodiversity can be enhanced by integrating natural habitats into agricultural lands, but a key question is whether benefits are maximized by including many small features throughout the landscape ('land-sharing' agriculture) or a few large contiguous blocks alongside intensive farmland ('land-sparing' agriculture). In this study, we are the first to integrate carbon storage alongside multi-taxa biodiversity assessments to compare land-sparing and land-sharing frameworks. We do so by sampling carbon stocks and biodiversity (birds and dung beetles) in landscapes containing agriculture and forest within the Colombian Choco-Andes, a zone of high global conservation priority. We show that woodland fragments embedded within a matrix of cattle pasture hold less carbon per unit area than contiguous primary or advanced secondary forests (>15 years). Farmland sites also support less diverse bird and dung beetle communities than contiguous forests, even when farmland retains high levels of woodland habitat cover. Landscape simulations based on these data suggest that land-sparing strategies would be more beneficial for both carbon storage and biodiversity than land-sharing strategies across a range of production levels. Biodiversity benefits of land-sparing are predicted to be similar whether spared lands protect primary or advanced secondary forests, owing to the close similarity of bird and dung beetle communities between the two forest classes. Land-sparing schemes that encourage the protection and regeneration of natural forest blocks thus provide a synergy between carbon and biodiversity conservation, and represent a promising strategy for reducing the negative impacts of agriculture on tropical ecosystems. However, further studies examining a wider range of ecosystem services will be necessary to fully understand the links between land-allocation strategies and long-term ecosystem service provision.
2014 JUL
WOS:000337680700013
QID: Q35157310
2162-2172
journalArticle
488
SCIENCE OF THE TOTAL ENVIRONMENT
DOI 10.1016/j.scitotenv.2014.03.126
Melkonyan
Ani
Environmental and socio-economic vulnerability of agricultural sector in Armenia
Being a mountainous country, Armenia has undergone different kinds of natural disasters, such as droughts, floods, and storms, which have a direct influence on economy and are expected to occur more frequently in terms of climate change, raising the need to estimate economic vulnerability especially in agricultural sector. Agriculture plays a great role in national economy of Armenia, with 21% share in Gross Domestic Production (GDP). For this reason, the estimation of agricultural resources of the country, their vulnerability towards current and future climate, and assessment of economical loss of the agricultural crop production due to climate change are the main goals of the given study. Crop productivity in dependence on climatic elements temperature, radiation, precipitation, wind field, etc. has been estimated, further on interpolating these relations for future climate conditions using climate projections in the region for the time period of 2011-2040.Data on air temperature, precipitation, relative humidity, wind speed and direction for the period of 1966-2011 have been taken from 30 stations from the measuring network of Armenian State Hydrometeorological Service. Other climatic parameters like potential and actual evapotranspiration, soil temperature and humidity, field capacity, and wilting point have been calculated with the help of an AMBAV/AMBETTI (agroclimatic) model (German Weather Service).The results showed that temperature increase accompanied with evapotranspiration increase and water availability decrease especially in low and mid-low altitudes (where the main national crop production is centralized) caused a significant shift in the phenological phases of crops, which is very important information for effective farming dates, giving an opportunity to raise efficiency of agricultural production through minimizing the yield loss due to unfavorable climatic conditions. With the help of macroeconomical analysis of the crop market, it was estimated that the economical loss of the wheat production due to even drier conditions in the future climate (2011-2040) will be more than doubled, causing essential problems in irrigation systems with sparse water resources. (C) 2014 Published by Elsevier B.V.
2014 AUG 1
WOS:000338600800035
QID: Q30823081
333-342
journalArticle
13
JOURNAL OF PROTEOME RESEARCH
DOI 10.1021/pr500153m
8
Huerta-Ocampo
Jose A.
Barrera-Pacheco
Alberto
Mendoza-Hernandez
Christian S.
Espitia-Rangel
Eduardo
Mock
Hans-Peter
Barba de la Rosa
Ana P.
Salt Stress-Induced Alterations in the Root Proteome of Amaranthus cruentus L.
Salt stress is one of the major factors limiting crop productivity worldwide. Amaranth is a highly nutritious pseudocereal with remarkable nutraceutical properties; it is also a stress-tolerant plant, making it an alternative crop for sustainable food production in semiarid conditions. A two-dimensional electrophoresis gel coupled with a liquid chromatography-mass spectrometry/mass spectrometry (LC-MS/MS) approach was applied in order to analyze the changes in amaranth root protein accumulation in plants subjected to salt stress under hydroponic conditions during the osmotic phase (1 h), after recovery (24 h), and during the ionic phase of salt stress (168 h). A total of 101 protein spots were differentially accumulated in response to stress, in which 77 were successfully identified by LC-MS/MS and a database search against public and amaranth transcriptome databases. The resulting proteins were grouped into different categories of biological processes according to Gene Ontology. The identification of several protein isoforms with a change in pI and/or molecular weight reveals the importance of the salt-stress-induced posttranslational modifications in stress tolerance. Interestingly stress-responsive proteins unique to amaranth, for example, Ah24, were identified. Amaranth is a stress-tolerant alternative crop for sustainable food production, and the understanding of amaranth's stress tolerance mechanisms will provide valuable input to improve stress tolerance of other crop plants.
2014 AUG
WOS:000339983600011
QID: Q38475864
3607-3627
journalArticle
23
MOLECULAR ECOLOGY
DOI 10.1111/mec.12701
15
Derocles
Stephane A. P.
Le Ralec
Anne
Besson
Mathilde M.
Maret
Marion
Walton
Alan
Evans
Darren M.
Plantegenest
Manuel
Molecular analysis reveals high compartmentalization in aphid-primary parasitoid networks and low parasitoid sharing between crop and noncrop habitats
The ecosystem service of insect pest regulation by natural enemies, such as primary parasitoids, may be enhanced by the presence of uncultivated, semi-natural habitats within agro-ecosystems, although quantifying such host-parasitoid interactions is difficult. Here, we use rRNA 16S gene sequencing to assess both the level of parasitism by Aphidiinae primary parasitoids and parasitoid identity on a large sample of aphids collected in cultivated and uncultivated agricultural habitats in Western France. We used these data to construct ecological networks to assess the level of compartmentalization between aphid and parasitoid food webs of cultivated and uncultivated habitats. We evaluated the extent to which uncultivated margins provided a resource for parasitoids shared between pest and nonpest aphids. We compared the observed quantitative ecological network described by our molecular approach to an empirical qualitative network based on aphid-parasitoid interactions from traditional rearing data found in the literature. We found that the molecular network was highly compartmentalized and that parasitoid sharing is relatively rare between aphids, especially between crop and noncrop compartments. Moreover, the few cases of putative shared generalist parasitoids were questionable and could be due to the lack of discrimination of cryptic species or from intraspecific host specialization. Our results suggest that apparent competition mediated by Aphidiinae parasitoids is probably rare in agricultural areas and that the contribution of field margins as a source of these biocontrol agents is much more limited than expected. Further large-scale (spatial and temporal) studies on other crops and noncrop habitats are needed to confirm this.
2014 AUG
WOS:000339487300026
QID: Q42647551
3900-3911
journalArticle
80
APPLIED AND ENVIRONMENTAL MICROBIOLOGY
DOI 10.1128/AEM.00720-14
15
Denes
Thomas
Vongkamjan
Kitiya
Ackermann
Hans-Wolfgang
Switt
Andrea I. Moreno
Wiedmann
Martin
den Bakker
Henk C.
Comparative Genomic and Morphological Analyses of Listeria Phages Isolated from Farm Environments
The genus Listeria is ubiquitous in the environment and includes the globally important food-borne pathogen Listeria monocytogenes. While the genomic diversity of Listeria has been well studied, considerably less is known about the genomic and morphological diversity of Listeria bacteriophages. In this study, we sequenced and analyzed the genomes of 14 Listeria phages isolated mostly from New York dairy farm environments as well as one related Enterococcus faecalis phage to obtain information on genome characteristics and diversity. We also examined 12 of the phages by electron microscopy to characterize their morphology. These Listeria phages, based on gene orthology and morphology, together with previously sequenced Listeria phages could be classified into five orthoclusters, including one novel orthocluster. One orthocluster (orthocluster I) consists of large-genome (similar to 135-kb) myoviruses belonging to the genus "Twort-like viruses," three orthoclusters (orthoclusters II to IV) contain small-genome (36- to 43-kb) siphoviruses with icosahedral heads, and the novel orthocluster V contains medium-sized-genome (similar to 66-kb) siphoviruses with elongated heads. A novel orthocluster (orthocluster VI) of E. faecalis phages, with medium-sized genomes (similar to 56 kb), was identified, which grouped together and shares morphological features with the novel Listeria phage orthocluster V. This new group of phages (i.e., orthoclusters V and VI) is composed of putative lytic phages that may prove to be useful in phage-based applications for biocontrol, detection, and therapeutic purposes.
2014 AUG
WOS:000338707800016
QID: Q34106967
4616-4625
journalArticle
90
PHOTOCHEMISTRY AND PHOTOBIOLOGY
DOI 10.1111/php.12280
5
Larsen
Mette Bodekaer
Petersen
Bibi
Philipsen
Peter Alshede
Young
Antony
Thieden
Elisabeth
Wulf
Hans Christian
Sun exposure and Protection Behavior of Danish Farm Children: Parental Influence on Their Children
Healthy sun habits acquired in childhood could reduce skin cancer incidence. We examined the sun exposure and protection behavior of an expected high-exposure group of children, and the association to their parents. Open, prospective cohort study. One hundred and thirty nine participants (40 families) kept daily sun behavior diaries (sun exposure, sunscreen use, sunburns) over a 4-month summer period (15985 diary days). The Pigment Protection Factor (PPF), an objective measure of sun exposure, was measured at two body sites, before and after summer. All participants presented data from the same 115days. Risk behavior (sun exposure of upper body) took place on 9.5days (boys) and 15.6days (girls). Sunburn and sunscreen use were infrequent. Boys' sun exposure resulted in an increased photo protection over the study period of 1.7SED (upper arm) and 0.8SED (shoulder) to elicit erythema. Corresponding values for girls were as follows: 0.9SED (upper arm) and 0.5SED (shoulder). Boys' sunscreen use correlated to their mothers' (r=0.523, P=0.02). Girls' number of risk days (r=0.552, P=0.005) and sun exposure (upper arm: r=0.621, P<0.001) correlated to their mothers'. The children's sun exposure was substantial. Only mothers influenced children's sun behavior and exposure. This may be of relevance in future sun protection campaigns.
2014 SEP-OCT
WOS:000341873400029
QID: Q39206671
1193-1198
journalArticle
111
PROCEEDINGS OF THE NATIONAL ACADEMY OF SCIENCES OF THE UNITED STATES OF AMERICA
DOI 10.1073/pnas.1409516111
34
Riehl
Simone
Pustovoytov
Konstantin E.
Weippert
Heike
Klett
Stefan
Hole
Frank
Drought stress variability in ancient Near Eastern agricultural systems evidenced by delta C-13 in barley grain
The collapse and resilience of political systems in the ancient Near East and their relationship with agricultural development have been of wide interest in archaeology and anthropology. Despite attempts to link the archaeological evidence to local paleoclimate data, the precise role of environmental conditions in ancient agricultural production remains poorly understood. Recently, stable isotope analysis has been used for reconstructing site-specific ancient growing conditions for crop species in semiarid and arid landscapes. To open the discussion of the role of regional diversity in past agricultural production as a factor in societal development, we present 1.037 new stable carbon isotope measurements from 33 archaeological sites and modern fields in the geographic area of the Fertile Crescent, spanning the Aceramic Neolithic [10,000 calibrated years (cal) B.C.] to the later Iron Age (500 cal B.C.), alongside modern data from 13 locations. Our data show that drought stress was an issue in many agricultural settlements in the ancient Near East, particularly in correlation with the major Holocene climatic fluctuations, but its regional impact was diverse and influenced by geographic factors. Although cereals growing in the coastal areas of the northern Levant were relatively unaffected by Holocene climatic fluctuations, farmers of regions further inland had to apply irrigation to cope with increased water stress. However, inland agricultural strategies showed a high degree of variability. Our findings suggest that regional differences in climatic effects led to diversified strategies in ancient subsistence and economy even within spatially limited cultural units.
2014 AUG 26
WOS:000340780300029
QID: Q30842146
12348-12353
journalArticle
21
ENVIRONMENTAL SCIENCE AND POLLUTION RESEARCH
DOI 10.1007/s11356-014-3046-x
18
Liu
Mei
Lu
Jun
Support vector machine-an alternative to artificial neuron network for water quality forecasting in an agricultural nonpoint source polluted river?
Water quality forecasting in agricultural drainage river basins is difficult because of the complicated nonpoint source (NPS) pollution transport processes and river self-purification processes involved in highly nonlinear problems. Artificial neural network (ANN) and support vector model (SVM) were developed to predict total nitrogen (TN) and total phosphorus (TP) concentrations for any location of the river polluted by agricultural NPS pollution in eastern China. River flow, water temperature, flow travel time, rainfall, dissolved oxygen, and upstream TN or TP concentrations were selected as initial inputs of the two models. Monthly, bimonthly, and trimonthly datasets were selected to train the two models, respectively, and the same monthly dataset which had not been used for training was chosen to test the models in order to compare their generalization performance. Trial and error analysis and genetic algorisms (GA) were employed to optimize the parameters of ANN and SVM models, respectively. The results indicated that the proposed SVM models performed better generalization ability due to avoiding the occurrence of overtraining and optimizing fewer parameters based on structural risk minimization (SRM) principle. Furthermore, both TN and TP SVM models trained by trimonthly datasets achieved greater forecasting accuracy than corresponding ANN models. Thus, SVM models will be a powerful alternative method because it is an efficient and economic tool to accurately predict water quality with low risk. The sensitivity analyses of two models indicated that decreasing upstream input concentrations during the dry season and NPS emission along the reach during average or flood season should be an effective way to improve Changle River water quality. If the necessary water quality and hydrology data and even trimonthly data are available, the SVM methodology developed here can easily be applied to other NPS-polluted rivers.
2014 SEP
WOS:000342132500045
QID: Q39181091
11036-11053
journalArticle
114
ANNALS OF BOTANY
DOI 10.1093/aob/mcu101
4
Garin
Guillaume
Fournier
Christian
Andrieu
Bruno
Houles
Vianney
Robert
Corinne
Pradal
Christophe
A modelling framework to simulate foliar fungal epidemics using functional-structural plant models
Background and Aims Sustainable agriculture requires the identification of new, environmentally responsible strategies of crop protection. Modelling of pathosystems can allow a better understanding of the major interactions inside these dynamic systems and may lead to innovative protection strategies. In particular, functional-structural plant models (FSPMs) have been identified as a means to optimize the use of architecture-related traits. A current limitation lies in the inherent complexity of this type of modelling, and thus the purpose of this paper is to provide a framework to both extend and simplify the modelling of pathosystems using FSPMs.Methods Different entities and interactions occurring in pathosystems were formalized in a conceptual model. A framework based on these concepts was then implemented within the open-source OpenAlea modelling platform, using the platform's general strategy of modelling plant-environment interactions and extending it to handle plant interactions with pathogens. New developments include a generic data structure for representing lesions and dispersal units, and a series of generic protocols to communicate with objects representing the canopy and its micro-environment in the OpenAlea platform. Another development is the addition of a library of elementary models involved in pathosystem modelling. Several plant and physical models are already available in OpenAlea and can be combined in models of pathosystems using this framework approach.Key Results Two contrasting pathosystems are implemented using the framework and illustrate its generic utility. Simulations demonstrate the framework's ability to simulate multiscaled interactions within pathosystems, and also show that models are modular components within the framework and can be extended. This is illustrated by testing the impact of canopy architectural traits on fungal dispersal.Conclusions This study provides a framework for modelling a large number of pathosystems using FSPMs. This structure can accommodate both previously developed models for individual aspects of pathosystems and new ones. Complex models are deconstructed into separate 'knowledge sources' originating from different specialist areas of expertise and these can be shared and reassembled into multidisciplinary models. The framework thus provides a beneficial tool for a potential diverse and dynamic research community.
2014 SEP
WOS:000343039600017
QID: Q35187365
795-812
journalArticle
14
SENSORS
DOI 10.3390/s140917753
9
Casanova
Joaquin J.
O'Shaughnessy
Susan A.
Evett
Steven R.
Rush
Charles M.
Development of a Wireless Computer Vision Instrument to Detect Biotic Stress in Wheat
Knowledge of crop abiotic and biotic stress is important for optimal irrigation management. While spectral reflectance and infrared thermometry provide a means to quantify crop stress remotely, these measurements can be cumbersome. Computer vision offers an inexpensive way to remotely detect crop stress independent of vegetation cover. This paper presents a technique using computer vision to detect disease stress in wheat. Digital images of differentially stressed wheat were segmented into soil and vegetation pixels using expectation maximization (EM). In the first season, the algorithm to segment vegetation from soil and distinguish between healthy and stressed wheat was developed and tested using digital images taken in the field and later processed on a desktop computer. In the second season, a wireless camera with near real-time computer vision capabilities was tested in conjunction with the conventional camera and desktop computer. For wheat irrigated at different levels and inoculated with wheat streak mosaic virus (WSMV), vegetation hue determined by the EM algorithm showed significant effects from irrigation level and infection. Unstressed wheat had a higher hue (118.32) than stressed wheat (111.34). In the second season, the hue and cover measured by the wireless computer vision sensor showed significant effects from infection (p = 0.0014), as did the conventional camera (p < 0.0001). Vegetation hue obtained through a wireless computer vision system in this study is a viable option for determining biotic crop stress in irrigation scheduling. Such a low-cost system could be suitable for use in the field in automated irrigation scheduling applications.
2014 SEP
WOS:000343106600111
QID: Q34398184
17753-17769
journalArticle
24
ECOLOGICAL APPLICATIONS
DOI 10.1890/13-0872.1
6
Cunningham
Ross
Lindenmayer
David
Barton
Philip
Ikin
Karen
Crane
Mason
Michael
Damian
Okada
Sachiko
Gibbons
Philip
Stein
John
Cross-sectional and temporal relationships between bird occupancy and vegetation cover at multiple spatial scales
Scale is a key concept in ecology, but the statistically based quantification of scale effects has often proved difficult. This is exemplified by the challenges of quantifying relationships between biodiversity and vegetation cover at different spatial scales to guide restoration and conservation efforts in agricultural environments. We used data from 2002 to 2010 on 184 sites (viz., site scale) nested within 46 farms (the farm scale), nested within 23 landscapes (the landscape scale). We found cross-sectional relationships with the amount of vegetation cover that were typically positive for woodland birds and negative for open-country birds. However, for some species, relationships differed between spatial scales, suggesting differences in nesting and foraging requirements. There was a 3.5% increase in the amount of native vegetation cover in our study region between 2002 and 2010, and our analyses revealed that some open country species responded negatively to these temporal changes, typically at the farm and/or site scale, but not the landscape scale. Species generally exhibited stronger cross-sectional relationships with the amount of vegetation cover than relationships between changes in occupancy and temporal changes in vegetation cover. This unexpected result can be attributed to differences in habitat use by birds of existing vegetation cover (typically old-growth woodland) vs. plantings and natural regeneration, which are the main contributors to temporal increases in vegetation cover. By taking a multi-scaled empirical approach, we have identified species-specific, scale-dependent responses to vegetation cover. These findings are of considerable practical importance for understanding which species will respond to different scales of protection of existing areas of native vegetation, efforts to increase the amount of native vegetation over time, and both approaches together.
2014 SEP
WOS:000341715800003
QID: Q46954100
1275-1288
journalArticle
143
JOURNAL OF ENVIRONMENTAL MANAGEMENT
DOI 10.1016/j.jenvman.2014.04.029
Lomba
Angela
Guerra
Carlos
Alonso
Joaquim
Honrado
Joao Pradinho
Jongman
Rob
McCracken
David
Mapping and monitoring High Nature Value farmlands: Challenges in European landscapes
The importance of low intensity farming for the conservation of biodiversity throughout Europe was acknowledged early in the 1990s when the concept of 'High Nature Value farmlands' (HNVf) was devised. HNVf has subsequently been given high priority within the EU Rural Development Programme. This puts a requirement on each EU Member State not only to identify the extent and condition of HNVf within their borders but also to track trends in HNVf over time. However, the diversity of rural landscapes across the EU, the scarcity of (adequate) datasets on biodiversity, land cover and land use, and the lack of a common methodology for HNVf mapping currently represent obstacles to the implementation of the HNVf concept across Europe. This manuscript provides an overview of the characteristics of HNVf across Europe together with a description of the development of the HNVf concept. Current methodological approaches for the identification and mapping of HNVf across EU-27 and Switzerland are then reviewed, the main limitations of these approaches highlighted and recommendations made as to how the identification, mapping and reporting of HNVf state and trends across Europe can potentially be improved and harmonised. In particular, we propose a new framework that is built on the need for strategic HNVf monitoring based on a hierarchical, bottom-up structure of assessment units, coincident with the EU levels of political decision and devised indicators, and which is linked strongly to a collaborative European network that can provide the integration and exchange of data from different sources and scales under common standards. Such an approach is essential if the scale of the issues facing HNVf landscapes are to be identified and monitored properly at the European level. This would then allow relevant agri-environmental measures to be developed, implemented and evaluated at the scale(s) required to maintain the habitats and species of high nature conservation value that are intimately associated with those landscapes. (C) 2014 Elsevier Ltd. All rights reserved.
2014 OCT 1
WOS:000338810200017
QID: Q38218223
140-150
journalArticle
32
NATURE BIOTECHNOLOGY
DOI 10.1038/nbt.2979
10
Li
Ying-hui
Zhou
Guangyu
Ma
Jianxin
Jiang
Wenkai
Jin
Long-guo
Zhang
Zhouhao
Guo
Yong
Zhang
Jinbo
Sui
Yi
Zheng
Liangtao
Zhang
Shan-shan
Zuo
Qiyang
Shi
Xue-hui
Li
Yan-fei
Zhang
Wan-ke
Hu
Yiyao
Kong
Guanyi
Hong
Hui-long
Tan
Bing
Song
Jian
Liu
Zhang-xiong
Wang
Yaoshen
Ruan
Hang
Yeung
Carol K. L.
Liu
Jian
Wang
Hailong
Zhang
Li-juan
Guan
Rong-xia
Wang
Ke-jing
Li
Wen-bin
Chen
Shou-yi
Chang
Ru-zhen
Jiang
Zhi
Jackson
Scott A.
Li
Ruiqiang
Qiu
Li-juan
De novo assembly of soybean wild relatives for pan-genome analysis of diversity and agronomic traits
Wild relatives of crops are an important source of genetic diversity for agriculture, but their gene repertoire remains largely unexplored. We report the establishment and analysis of a pan-genome of Glycine soja, the wild relative of cultivated soybean Glycine max, by sequencing and de novo assembly of seven phylogenetically and geographically representative accessions. Intergenomic comparisons identified lineage-specific genes and genes with copy number variation or large-effect mutations, some of which show evidence of positive selection and may contribute to variation of agronomic traits such as biotic resistance, seed composition, flowering and maturity time, organ size and final biomass. Approximately 80% of the pan-genome was present in all seven accessions (core), whereas the rest was dispensable and exhibited greater variation than the core genome, perhaps reflecting a role in adaptation to diverse environments. This work will facilitate the harnessing of untapped genetic diversity from wild soybean for enhancement of elite cultivars.
2014 OCT
WOS:000343763800022
QID: Q46124159
1045-+
journalArticle
16
ENVIRONMENTAL MICROBIOLOGY
DOI 10.1111/1462-2920.12423
10
Collavino
Monica M.
Tripp
H. James
Frank
Ildiko E.
Vidoz
Maria L.
Calderoli
Priscila A.
Donato
Mariano
Zehr
Jonathan P.
Mario Aguilar
O.
nifH pyrosequencing reveals the potential for location-specific soil chemistry to influence N-2-fixing community dynamics
A dataset of 87020 nifH reads and 16782 unique nifH protein sequences obtained over 2 years from four locations across a gradient of agricultural soil types in Argentina were analysed to provide a detailed and comprehensive picture of the diversity, abundance and responses of the N-2-fixing community in relation to differences in soil chemistry and agricultural practices. Phylogenetic analysis revealed an expected high proportion of Alphaproteobacteria, Betaproteobacteria and Deltaproteobacteria, mainly relatives to Bradyrhizobium and Methylosinus/Methylocystis, but a surprising paucity of Gammaproteobacteria. Analysis of variance and stepwise regression modelling suggested location and treatment-specific influences of soil type on diazotrophic community composition and organic carbon concentrations on nifH diversity. nifH gene abundance, determined by quantitative real-time polymerase chain reaction, was higher in agricultural soils than in non-agricultural soils, and was influenced by soil chemistry under intensive crop rotation but not under monoculture. At some locations, sustainable increased crop yields might be possible through the management of soil chemistry to improve the abundance and diversity of N-2-fixing bacteria.
2014 OCT
WOS:000343867700016
QID: Q57241047
3211-3223
journalArticle
13
INTERNATIONAL JOURNAL FOR EQUITY IN HEALTH
DOI 10.1186/s12939-014-0065-7
Narushima
Miya
Sanchez
Ana Lourdes
Employers' paradoxical views about temporary foreign migrant workers' health: a qualitative study in rural farms in Southern Ontario
Background: The province of Ontario hosts nearly a half of Canada's temporary foreign migrant farm workers (MFWs). Despite the essential role played by MFWs in the economic prosperity of the region, a growing body of research suggests that the workers' occupational safety and health are substandard, and often neglected by employers. This study thus explores farm owners' perceptions about MFWs occupational safety and general health, and their attitudes towards health promotion for their employees.Methods: Using modified grounded theory approach, we collected data through in-depth individual interviews with farm owners employing MFWs in southern Ontario, Canada. Data were analyzed following three steps (open, axial, and selective coding) to identify thematic patterns and relationships. Nine employers or their representatives were interviewed.Results: Four major overarching categories were identified: employers' dependence on MFWs; their fragmented view of occupational safety and health; their blurring of the boundaries between the work and personal lives of the MFWs on their farms; and their reluctance to implement health promotion programs. The interaction of these categories suggests the complex social processes through which employers come to hold these paradoxical attitudes towards workers' safety and health. There is a fundamental contradiction between what employers considered public versus personal. Despite employers' preference to separate MFWs' workplace safety from personal health issues, due to the fact that workers live within their employers' property, workers' private life becomes public making their personal health a business-related concern. Farmers' conflicting views, combined with a lack of support from governing bodies, hold back timely implementation of health promotion activities in the workplace.Conclusions: In order to address the needs of MFWs in a more integrated manner, an ecological view of health, which includes the social and psychological determinants of health, by employers is necessary. Employers and other stakeholders should work collaboratively to find a common ground, harnessing expertise and resources to develop more community-based approaches. Further research and continuous dialogue are needed.
2014 SEP 10
WOS:000344630600001
QID: Q34157215
journalArticle
14
SENSORS
DOI 10.3390/s141019639
10
Bitella
Giovanni
Rossi
Roberta
Bochicchio
Rocco
Perniola
Michele
Amato
Mariana
A Novel Low-Cost Open-Hardware Platform for Monitoring Soil Water Content and Multiple Soil-Air-Vegetation Parameters
Monitoring soil water content at high spatio-temporal resolution and coupled to other sensor data is crucial for applications oriented towards water sustainability in agriculture, such as precision irrigation or phenotyping root traits for drought tolerance. The cost of instrumentation, however, limits measurement frequency and number of sensors. The objective of this work was to design a low cost. open hardware. platform for multi-sensor measurements including water content at different depths, air and soil temperatures. The system is based on an open-source ARDUINO microcontroller-board, programmed in a simple integrated development environment (IDE). Low cost high-frequency dielectric probes were used in the platform and lab tested on three non-saline soils (ECe1: 2.5 < 0.1 mS/cm). Empirical calibration curves were subjected to cross-validation (leave-one-out method), and normalized root mean square error (NRMSE) were respectively 0.09 for the overall model, 0.09 for the sandy soil, 0.07 for the clay loam and 0.08 for the sandy loam. The overall model (pooled soil data) fitted the data very well (R-2 = 0.89) showing a high stability, being able to generate very similar RMSEs during training and validation (RMSEtraining = 2.63; RMSEvalidation = 2.61). Data recorded on the card were automatically sent to a remote server allowing repeated field-data quality checks. This work provides a framework for the replication and upgrading of a customized low cost platform, consistent with the open source approach whereby sharing information on equipment design and software facilitates the adoption and continuous improvement of existing technologies.
2014 OCT
WOS:000344455700092
QID: Q34554020
19639-19659
journalArticle
9
PLOS ONE
DOI 10.1371/journal.pone.0107783
10
Stockinger
Herbert
Peyret-Guzzon
Marine
Koegel
Sally
Bouffaud
Marie-Lara
Redecker
Dirk
The Largest Subunit of RNA Polymerase II as a New Marker Gene to Study Assemblages of Arbuscular Mycorrhizal Fungi in the Field
Due to the potential of arbuscular mycorrhizal fungi (AMF, Glomeromycota) to improve plant growth and soil quality, the influence of agricultural practice on their diversity continues to be an important research question. Up to now studies of community diversity in AMF have exclusively been based on nuclear ribosomal gene regions, which in AMF show high intra-organism polymorphism, seriously complicating interpretation of these data. We designed specific PCR primers for 454 sequencing of a region of the largest subunit of RNA polymerase II gene, and established a new reference dataset comprising all major AMF lineages. This gene is known to be monomorphic within fungal isolates but shows an excellent barcode gap between species. We designed a primer set to amplify all known lineages of AMF and demonstrated its applicability in combination with high-throughput sequencing in a long-term tillage experiment. The PCR primers showed a specificity of 99.94% for glomeromycotan sequences. We found evidence of significant shifts of the AMF communities caused by soil management and showed that tillage effects on different AMF taxa are clearly more complex than previously thought. The high resolving power of high-throughput sequencing highlights the need for quantitative measurements to efficiently detect these effects.
2014 OCT 2
WOS:000342591500008
QID: Q35294245
journalArticle
9
PLOS ONE
DOI 10.1371/journal.pone.0108517
10
Linseele
Veerle
Van Neer
Wim
Thys
Sofie
Phillipps
Rebecca
Cappers
Rene
Wendrich
Willeke
Holdaway
Simon
New Archaeozoological Data from the Fayum "Neolithic'' with a Critical Assessment of the Evidence for Early Stock Keeping in Egypt
Faunal evidence from the Fayum Neolithic is often cited in the framework of early stock keeping in Egypt. However, the data suffer from a number of problems. In the present paper, large faunal datasets from new excavations at Kom K and Kom W (4850-4250 BC) are presented. They clearly show that, despite the presence of domesticates, fish predominate in the animal bone assemblages. In this sense, there is continuity with the earlier Holocene occupation from the Fayum, starting ca. 7350 BC. Domesticated plants and animals appear first from approximately 5400 BC. The earliest possible evidence for domesticates in Egypt are the very controversial domesticated cattle from the 9th/8th millennium BC in the Nabta Playa-Bir Kiseiba area. The earliest domesticates found elsewhere in Egypt date to the 6th millennium BC. The numbers of bones are generally extremely low at this point in time and only caprines are present. From the 5th millennium BC, the numbers of sites with domesticates dramatically increase, more species are also involved and they are usually represented by significant quantities of bones. The data from the Fayum reflect this two phase development, with very limited evidence for domesticates in the 6th millennium BC and more abundant and clearer indications in the 5th millennium BC. Any modelling of early food production in Egypt suffers from poor amounts of data, bias due to differential preservation and visibility of sites and archaeological remains, and a lack of direct dates for domesticates. In general, however, the evidence for early stock keeping and accompanying archaeological features shows large regional variation and seems to be mainly dependent on local environmental conditions. The large numbers of fish at Kom K and Kom W reflect the proximity of Lake Qarun.
2014 OCT 13
WOS:000343210300020
QID: Q28654738
journalArticle
10
JOURNAL OF ETHNOBIOLOGY AND ETHNOMEDICINE
DOI 10.1186/1746-4269-10-73
Schulz
Francine
Printes
Rodrigo C.
Oliveira
Larissa R.
Depredation of domestic herds by pumas based on farmer's information in Southern Brazil
Background: Large carnivores such as pumas are frequently killed due to conflicts with human populations involving predation on domestic herds. In Southern Brazil, traditional pasture systems, where animals feed without specific husbandry practices is typical, becoming the herds vulnerable to puma attacks. The aim of this study was to examine the conflict between local people and pumas in a Protected Areas mosaic in southern Brazil.Methods: Forty-five face-to-face interviews with local people were performed during the year of 2011, using a structured questionnaire with open and closed questions about puma attack episodes in some farms. Based on responses, the conflict and puma attacks were described, and the characteristics of attacked farms and estimated financial losses were evaluated. The first respondents were indicated by the Local Environmental Agency, and the others were indicated by the first one and so on, which is known as "snow-ball" method.Results: Our data suggested that pumas used to attack in unfavorable conditions of visibility (foggy days) and on easier prey (e.g. sheep). Most of the attacks reported were close to forested areas and were focused on free herds during feeding activities. Some farmers said they gave up their sheep breeding activity due to losses caused by puma attacks. However, some farmers could over estimate their losses. Moreover, pumas were considered a threat to domestic herds and respondents mentioned cases of illegal puma hunting in the area. The results of questionnaires suggested that puma attack episodes were related to fragmentation of their habitat associated to incorrect management of herds in the farms studied. The diagnosis of this type of conflict and the characterization of most attacked sites are extremely important to create strategies to prevent and control attacks by wild carnivores.Conclusions: Deep changes in husbandry practices added to educational programs should be implemented, in order to maintain the sustainability of rural activities as well as the survival of pumas in southern Brazil.
2014 OCT 15
WOS:000345874900002
QID: Q34740200
journalArticle
144
JOURNAL OF ENVIRONMENTAL MANAGEMENT
DOI 10.1016/j.jenvman.2014.06.004
Yan
Hongliang
Xie
Liyong
Guo
Liping
Fan
Jingwei
Diao
Tiantian
Lin
Miao
Zhang
He
Lin
Erda
Characteristics of nitrous oxide emissions and the affecting factors from vegetable fields on the North China Plain
Nitrous oxide (N2O) is one of the most important greenhouse gases emitted from fertilized agricultural soils. Vegetable fields, mostly managed under intensive mode with higher rate nitrogen application, frequent irrigation, and multiple planting-harvest cycles, does contribute to national GHG inventory greatly due to the increasing planting area in China. N2O emissions from four different fields a maize field (maize), a newly established open-ground vegetable field converted from a maize field four years earlier (OV4), an established open-ground vegetable field converted from a maize field more than 20 years ago (OV20), and an established sunlight heated greenhouse vegetable field converted from a maize field more than 20 years ago (GV20) with four different fertilization treatments for the OV4 field were measured using the closed chamber method between March 15th, 2012 and March 14th, 2013 in suburban area of Beijing, North China Plain. Results showed that the annual N2O emissions from vegetable fields were 3.1-4.6 times higher than the typical maize field. All the N2O emission peaks were occurred after fertilization and the fertilization associated emissions accounted for 81.1% (ranging from 77.0% to 87.2%) of the annual N2O emission with 22.2% time duration in the whole year for vegetable fields. Both the occurrence data and duration of N2O emission peaks were associated with N input type (chemical or manure) and the application rate. The N2O emission peaks appeared earlier (on the 3rd day after application) and lasted shorter when only chemical N was applied; while they appeared later (on the 7th to 10th day after application) and lasted longer when the combination of manure and chemical N were applied. The magnitudes of N2O emission peaks increased when the N application rate was higher. Dicyandiamide (DCD) decreased N2O emissions by 30.1% and 21.1% in the spring cucumber and autumn cabbage seasons respectively (averaged of 24.7% over the whole year). Calculations showed that it is critical to estimate the emission factor (EF) by N type in order to decrease the uncertainty of regional N2O emissions when using EF as calculation method. EFs were 0.20% and 0.42% for manure N in the cucumber and cabbage seasons respectively; and were 0.55-1.30% and 0.8-1.59% for chemical N in the cucumber and cabbage seasons respectively. (C) 2014 Elsevier Ltd. All rights reserved.
2014 NOV 1
WOS:000340011800036
QID: Q42670145
316-321
journalArticle
31
PUBLIC HEALTH NURSING
DOI 10.1111/phn.12112
6
Postma
Julie
Peterson
Jeff
Vega
Mary Jo Ybarra
Ramon
Cristian
Cortes
Guadalupe
Latina Youths' Perceptions of Children's Environmental Health Risks in an Agricultural Community
ObjectivesThe objective of this study was to identify Latina youths' perceptions of local assets and concerns related to children's environmental health (EH) in an agricultural community.Design and SampleFour photovoice sessions were used to elicit 6 promotores' and 5 middle school students' perspectives on problems and strengths related to children; environment; and health.MeasuresData collection was diverse and included a demographic and evaluation questionnaire, photographs, audio recordings of group photo-sharing sessions, and field notes.ResultsParticipants identified three themes that reflected group discussion during two photo-sharing sessions: a lack of structured youth activities; poverty and stress; and benefits and detriments of agricultural work. Community assets related to creating a healthy environment for youth were identified and included the clinic, churches, and youth programs.ConclusionsFindings from this study reinforce that social background and position affect how EH issues are defined and may be addressed. Participant perspectives are valuable to nurses because they offer a lens through which to see the complexities of EH from the viewpoint of those most directly affected. Leadership training and opportunities to serve on coalitions and neighborhood councils are recommended approaches to meaningfully involving youth in environmental justice initiatives.
2014 NOV-DEC
WOS:000345510000005
QID: Q42643932
508-516
journalArticle
25
INTERNATIONAL JOURNAL OF DRUG POLICY
DOI 10.1016/j.drugpo.2014.01.016
6
Botoeva
Gulzat
Hashish as cash in a post-Soviet Kyrgyz village
Background: This paper discusses how hashish produced by the local population of Tyup, Kyrgyzstan became an important source of cash in an agricultural semi-subsistence economy.Methods: The paper is based on a research study conducted between 2009 and 2010 that adopted a mixed-method approach to data collection. I gathered 64 semi-structured interviews, 147 structured interviews and made ethnographic observations of the livelihoods of the people of Toolu village in Tyup region.Results: The local population of the region became involved in hashish production due to a cash deficit in both the agricultural economy and wider society from the beginning of the 1990s. Privatization of land as a consequence of the neoliberalization of the economy left many families with small share lands which are insufficient to provide market surplus. Agricultural products, therefore, are mainly consumed by the majority of farmers, turning the economy of the region into a semi-subsistence agricultural economy. In the context of such a cash deficit economy, wild-growing cannabis plants are used not only as a cash crop but are symbolically turned into a form of cash and a source of informal credit. People can pay for goods with hashish as well as obtain advance payments and credits for it. I argue that hashish making assists the agricultural rural economy by allowing people to obtain goods, advance payments and credits to use for the cultivation of land, their everyday needs and maintaining social relationships. I also argue that many local farmers, who do not consider themselves as criminals, were able to become involved in this activity by shifting the meaning of hashish and hashish making from an illegal activity to a culturally valued and justifiable form of economic activity.Conclusion: This allows me to show that the local drug economy in Tyup serves as a lens through which to examine the strategies through which illegal and illicit drug production becomes culturally acceptable. Understanding of hashish production in this local context of the semi-subsistence agricultural economy operating in a constant deficit of cash provides rich data for effective evidence-based policy. (C) 2014 Elsevier B.V. All rights reserved.
2014 NOV
WOS:000347499400031
QID: Q43925958
1227-1234
journalArticle
117
PREVENTIVE VETERINARY MEDICINE
DOI 10.1016/j.prevetmed.2014.07.011
2
Santman-Berends
I. M. G. A.
Buddiger
M.
Smolenaars
A. J. G.
Steuten
C. D. M.
Roos
C. A. J.
Van Erp
A. J. M.
Van Schaik
G.
A multidisciplinary approach to determine factors associated with calf rearing practices and calf mortality in dairy herds
In the Netherlands, an increase in ear-tagged calf mortality (3 days to 1 year of age) in dairy farms was observed. The aim was to determine why calf mortality increased and how to reduce calf mortality in herds with structural high rates.A multi-disciplinary approach was chosen to study this phenomenon. First analysis of census data revealed that the majority of the calves died in the first month of life. In addition, a panel of 236 farmers indicated that the increase in calf mortality might be related to priority, time management and the mind-set of farmers. For that reason a questionnaire was carried out to detect risk factors for mortality among young calves (<1 month) in 100 dairy farms with increased calf mortality compared to 100 dairy farms with stable and below average calf mortality. The results showed that, besides management factors such as IBR and BVDV control, and purchase of cattle, also the answers to statements giving an indication on the farmers' mind-set, were associated with calf mortality. Therefore, a qualitative sociological study on the farmers' identity was conducted by performing in-depth interviews among 30 farmers with structurally high calf mortality rates. Afterwards, the results were communicated with a veterinary advisor who visited the farmers and gave tailored advice. Most of the interviewed farmers believed to have sufficient knowledge and skills regarding calf rearing. The farmers did not share their calf rearing problems with colleagues and advisors but they mentioned to be open to receive advice if not communicated in a reproaching or pedantic way. The sociologist distinguished three different phases of awareness concerning calf mortality among the farmers: (1) farmers who were only partly, or not at all, aware of high calf mortality; (2) farmers who felt powerless because of their inability to find a solution to their problems; and (3) farmers who knew they can be inaccurate when it comes to rearing calves, but were reluctant to change this. With the background information of the farmers' identity it was easier for the veterinary advisor to provide tailored advice resulting in a higher probability of following up. A first evaluation in which calf mortality rates in the six months after providing the advice were monitored, indicated that the advice resulted in reduced mortality. The combination of census data, epidemiological and qualitative sociological research revealed that advisors should be aware of the attitude and mind-set of the farmer and adapt their approach and advice accordingly. (C) 2014 Elsevier B.V. All rights reserved.
2014 NOV 15
WOS:000346215700007
QID: Q42678125
375-387
journalArticle
9
PLOS ONE
DOI 10.1371/journal.pone.0111642
11
Dong
Yingying
Luo
Ruisen
Feng
Haikuan
Wang
Jihua
Zhao
Jinling
Zhu
Yining
Yang
Guijun
Analysing and Correcting the Differences between Multi-Source and Multi-Scale Spatial Remote Sensing
Differences exist among analysis results of agriculture monitoring and crop production based on remote sensing observations, which are obtained at different spatial scales from multiple remote sensors in same time period, and processed by same algorithms, models or methods. These differences can be mainly quantitatively described from three aspects, i.e. multiple remote sensing observations, crop parameters estimation models, and spatial scale effects of surface parameters. Our research proposed a new method to analyse and correct the differences between multi-source and multi-scale spatial remote sensing surface reflectance datasets, aiming to provide references for further studies in agricultural application with multiple remotely sensed observations from different sources. The new method was constructed on the basis of physical and mathematical properties of multi-source and multi-scale reflectance datasets. Theories of statistics were involved to extract statistical characteristics of multiple surface reflectance datasets, and further quantitatively analyse spatial variations of these characteristics at multiple spatial scales. Then, taking the surface reflectance at small spatial scale as the baseline data, theories of Gaussian distribution were selected for multiple surface reflectance datasets correction based on the above obtained physical characteristics and mathematical distribution properties, and their spatial variations. This proposed method was verified by two sets of multiple satellite images, which were obtained in two experimental fields located in Inner Mongolia and Beijing, China with different degrees of homogeneity of underlying surfaces. Experimental results indicate that differences of surface reflectance datasets at multiple spatial scales could be effectively corrected over non-homogeneous underlying surfaces, which provide database for further multi-source and multi-scale crop growth monitoring and yield prediction, and their corresponding consistency analysis evaluation.
2014 NOV 18
WOS:000347121300013
QID: Q35432331
journalArticle
20
GLOBAL CHANGE BIOLOGY
DOI 10.1111/gcb.12684
12
Tao
Fulu
Zhang
Shuai
Zhang
Zhao
Rotter
Reimund P.
Maize growing duration was prolonged across China in the past three decades under the combined effects of temperature, agronomic management, and cultivar shift
Maize phenology observations at 112 national agro-meteorological experiment stations across China spanning the years 1981-2009 were used to investigate the spatiotemporal changes of maize phenology, as well as the relations to temperature change and cultivar shift. The greater scope of the dataset allows us to estimate the effects of temperature change and cultivar shift on maize phenology more precisely. We found that maize sowing date advanced significantly at 26.0% of stations mainly for spring maize in northwestern, southwestern and northeastern China, although delayed significantly at 8.0% of stations mainly in northeastern China and the North China Plain (NCP). Maize maturity date delayed significantly at 36.6% of stations mainly in the northeastern China and the NCP. As a result, duration of maize whole growing period (GPw) was prolonged significantly at 41.1% of stations, although mean temperature (Tmean) during GPw increased at 72.3% of stations, significantly at 19.6% of stations, and Tmean was negatively correlated with the duration of GPw at 92.9% of stations and significantly at 42.9% of stations. Once disentangling the effects of temperature change and cultivar shift with an approach based on accumulated thermal development unit, we found that increase in temperature advanced heading date and maturity date and reduced the duration of GPw at 81.3%, 82.1% and 83.9% of stations on average by 3.2, 6.0 and 3.5days/decade, respectively. By contrast, cultivar shift delayed heading date and maturity date and prolonged the duration of GPw at 75.0%, 94.6% and 92.9% of stations on average by 1.5, 6.5 and 6.5days/decade, respectively. Our results suggest that maize production is adapting to ongoing climate change by shift of sowing date and adoption of cultivars with longer growing period. The spatiotemporal changes of maize phenology presented here can further guide the development of adaptation options for maize production in near future.
2014 DEC
WOS:000344375700012
QID: Q30837584
3686-3699
journalArticle
186
ENVIRONMENTAL MONITORING AND ASSESSMENT
DOI 10.1007/s10661-014-4059-0
12
Rozemeijer
J. C.
Klein
J.
Broers
H. P.
van Tol-Leenders
T. P.
van der Grift
B.
Water quality status and trends in agriculture-dominated headwaters; a national monitoring network for assessing the effectiveness of national and European manure legislation in The Netherlands
Large nutrient losses to groundwater and surface waters are a major drawback of the highly productive agricultural sector in The Netherlands. The resulting high nutrient concentrations in water resources threaten their ecological, industrial, and recreational functions. To mitigate eutrophication problems, legislation on nutrient application in agriculture was enforced in 1986 in The Netherlands. The objective of this study was to evaluate this manure policy by assessing the water quality status and trends in agriculture-dominated headwaters. We used datasets from 5 agricultural test catchments and from 167 existing monitoring locations in agricultural headwaters. Trend analysis for these locations showed a fast reduction of nutrient concentrations after the enforcement of the manure legislation (median slopes of -0.55 mg/l per decade for total nitrogen (N-tot) and -0.020 mg/l per decade for total phosphorus (P-tot)). Still, up to 76 % of the selected locations currently do not comply with either the environmental quality standards (EQSs) for nitrogen (N-tot) or phosphorus (P-tot). This indicates that further improvement of agricultural water quality is needed. We observed that weather-related variations in nutrient concentrations strongly influence the compliance testing results, both for individual locations and for the aggregated results at the national scale. Another important finding is that testing compliance for nutrients based on summer average concentrations may underestimate the agricultural impact on ecosystem health. The focus on summer concentrations does not account for the environmental impact of high winter loads from agricultural headwaters towards downstream water bodies.
2014 DEC
WOS:000344349200068
QID: Q46836623
8981-8995
journalArticle
90
FEMS MICROBIOLOGY ECOLOGY
DOI 10.1111/1574-6941.12420
3
Moora
Mari
Davison
John
Oepik
Maarja
Metsis
Madis
Saks
Uelle
Jairus
Teele
Vasar
Martti
Zobel
Martin
Anthropogenic land use shapes the composition and phylogenetic structure of soil arbuscular mycorrhizal fungal communities
Arbuscular mycorrhizal (AM) fungi play an important role in ecosystems, but little is known about how soil AM fungal community composition varies in relation to habitat type and land-use intensity. We molecularly characterized AM fungal communities in soil samples (n = 88) from structurally open (permanent grassland, intensive and sustainable agriculture) and forested habitats (primeval forest and spruce plantation). The habitats harboured significantly different AM fungal communities, and there was a broad difference in fungal community composition between forested and open habitats, the latter being characterized by higher average AM fungal richness. Within both open and forest habitats, intensive land use significantly influenced community composition. There was a broad difference in the phylogenetic structure of AM fungal communities between mechanically disturbed and nondisturbed habitats. Taxa from Glomeraceae served as indicator species for the nondisturbed habitats, while taxa from Archaeosporaceae, Claroideoglomeraceae and Diversisporaceae were indicators for the disturbed habitats. The distribution of these indicator taxa among habitat types in the MaarjAM global database of AM fungal diversity was in accordance with their local indicator status.
2014 DEC
WOS:000346057900007
QID: Q35238011
609-621
journalArticle
14
SENSORS
DOI 10.3390/s141224212
12
Haemmerle
Martin
Hoefle
Bernhard
Effects of Reduced Terrestrial LiDAR Point Density on High-Resolution Grain Crop Surface Models in Precision Agriculture
3D geodata play an increasingly important role in precision agriculture, e.g., for modeling in-field variations of grain crop features such as height or biomass. A common data capturing method is LiDAR, which often requires expensive equipment and produces large datasets. This study contributes to the improvement of 3D geodata capturing efficiency by assessing the effect of reduced scanning resolution on crop surface models (CSMs). The analysis is based on high-end LiDAR point clouds of grain crop fields of different varieties (rye and wheat) and nitrogen fertilization stages (100%, 50%, 10%). Lower scanning resolutions are simulated by keeping every n-th laser beam with increasing step widths n. For each iteration step, high-resolution CSMs (0.01 m(2) cells) are derived and assessed regarding their coverage relative to a seamless CSM derived from the original point cloud, standard deviation of elevation and mean elevation. Reducing the resolution to, e.g., 25% still leads to a coverage of > 90% and a mean CSM elevation of > 96% of measured crop height. CSM types (maximum elevation or 90th-percentile elevation) react differently to reduced scanning resolutions in different crops (variety, density). The results can help to assess the trade-off between CSM quality and minimum requirements regarding equipment and capturing set-up.
2014 DEC
WOS:000346794300101
QID: Q35529383
24212-24230
journalArticle
21
ENVIRONMENTAL SCIENCE AND POLLUTION RESEARCH
DOI 10.1007/s11356-013-2384-4
23
Dambruoso
P.
de Gennaro
G.
Di Gilio
A.
Palmisani
J.
Tutino
M.
The impact of infield biomass burning on PM levels and its chemical composition
In the South of Italy, it is common for farmers to burn pruning waste from olive trees in spring. In order to evaluate the impact of the biomass burning source on the physical and chemical characteristics of the particulate matter (PM) emitted by these fires, a PM monitoring campaign was carried out in an olive grove. Daily PM10 samples were collected for 1 week, when there were no open fires, and when biomass was being burned, and at two different distances from the fires. Moreover, an optical particle counter and a polycyclic aromatic hydrocarbon (PAH) analyzer were used to measure the high time-resolved dimensional distribution of particles emitted and total PAHs concentrations, respectively. Chemical analysis of PM10 samples identified organic and inorganic components such as PAHs, ions, elements, and carbonaceous fractions (OC, EC). Analysis of the collected data showed the usefulness of organic and inorganic tracer species and of PAH diagnostic ratios for interpreting the impact of biomass fires on PM levels and on its chemical composition. Finally, high time-resolved monitoring of particle numbers and PAH concentrations was performed before, during, and after biomass burning, and these concentrations were seen to be very dependent on factors such as weather conditions, combustion efficiency, and temperature (smoldering versus flaming conditions), and moisture content of the wood burned.
2014 DEC
WOS:000345280200005
QID: Q42631796
13175-13185
journalArticle
146
JOURNAL OF ENVIRONMENTAL MANAGEMENT
DOI 10.1016/j.jenvman.2014.08.012
Massei
Gianluca
Rocchi
Lucia
Paolotti
Luisa
Greco
Salvatore
Boggia
Antonio
Decision Support Systems for environmental management: A case study on wastewater from agriculture
Dealing with spatial decision problems means combining and transforming geographical data (input) into a resultant decision (output), interfacing a Geographical Information System (GIS) with Multi-Criteria Decision Analysis (MCDA) methods. The conventional MCDA approach assumes the spatial homogeneity of alternatives within the case study area, although it is often unrealistic. On the other side, GIS provides excellent data acquisition, storage, manipulation and analysis capabilities, but in the case of a value structure analysis this capability is lower. For these reasons, several studies in the last twenty years have given attention to MCDA-GIS integration and to the development of Spatial Decision Support Systems (SDSS). Hitherto, most of these applications are based only on a formal integration between the two approaches. In this paper, we propose a complete MCDA-GIS integration with a plurality of MCDA methodologies, grouped in a suite. More precisely, we considered an open-source GIS (GRASS GIS 6.4) and a modular package including five MCDA modules based on five different methodologies. The methods included are: ELECTRE I, Fuzzy set, REGIME analysis, Analytic Hierarchy Process and Dominance-based Rough Set Approach. Thanks to the modular nature of the package, it is possible to add new methods without modifying the existing structure. To present the suite, we applied each module to the same case study, making comparisons. The strong points of the MCDA-GIS integration we developed are its open-source setting and the user friendly interface, both thanks to GRASS GIS, and the use of raster data. Moreover, our suite is a genuine case of perfect integration, where the spatial nature of criteria is always present. (C) 2014 Elsevier Ltd. All rights reserved.
2014 DEC 15
WOS:000343614400051
QID: Q42681779
491-504
journalArticle
146
JOURNAL OF ENVIRONMENTAL MANAGEMENT
DOI 10.1016/j.jenvman.2014.07.020
Jennings
Aaron A.
Li
Zijian
Scope of the worldwide effort to regulate pesticide contamination in surface soils
Regulating surface soil contamination is a worldwide problem. Many jurisdictions address this problem with regulatory guidance values (RGVs) that specify the maximum allowable soil concentration of contaminants. Pesticides are a particularly important class of soil contaminants because of their intentional toxicity and widespread application to home, garden, and agricultural soils. Pesticides are also difficult to regulate because they are marketed in thousands of products made from hundreds of potentially toxic chemicals. Worldwide, at least 174 jurisdictions from 54 United Nations member states have promulgated more than 19,400 pesticide RGVs. Values may be found for at least 739 pesticides, identified by unique Chemical Abstract Service numbers (CAS No.). Using CAS numbers helps to avoid confusion that may result from alternative product names, chemical nomenclature conventions, or flawed translations. Assembling the set of pesticide RGVs required translating guidance documents authored in 30 different languages. Results indicate that more than 100 RGVs have been promulgated for each of the 22 most frequently regulated pesticides including over 300 values for DDT. Data are presented on the number of pesticides typically addressed by a regulatory jurisdiction and on the size and variability of the RGV datasets for the 200 most frequently regulated pesticides. (C) 2014 Elsevier Ltd. All rights reserved.
2014 DEC 15
WOS:000343614400045
QID: Q43905717
420-443
journalArticle
2
SCIENTIFIC DATA
DOI 10.1038/sdata.2015.69
Sheffield
Kathryn
Morse-McNabb
Elizabeth
Clark
Rob
Robson
Susan
Lewis
Hayden
Mapping dominant annual land cover from 2009 to 2013 across Victoria, Australia using satellite imagery
There is a demand for regularly updated, broad-scale, accurate land cover information in Victoria from multiple stakeholders. This paper documents the methods used to generate an annual dominant land cover (DLC) map for Victoria, Australia from 2009 to 2013. Vegetation phenology parameters derived from an annual time series of the Moderate Resolution Imaging Spectroradiometer Vegetation Indices 16-day 250 m (MOD13Q1) product were used to generate annual DLC maps, using a three-tiered hierarchical classification scheme. Classification accuracy at the broadest (primary) class level was over 91% for all years, while it ranged from 72 to 81% at the secondary class level. The most detailed class level (tertiary) had accuracy levels ranging from 61 to 68%. The approach used was able to accommodate variable climatic conditions, which had substantial impacts on vegetation growth patterns and agricultural production across the state between both regions and years. The production of an annual dataset with complete spatial coverage for Victoria provides a reliable base data set with an accuracy that is fit-for-purpose for many applications.
2015
WOS:000209844100070
QID: Q36316748
journalArticle
59
INTERNATIONAL JOURNAL OF BIOMETEOROLOGY
DOI 10.1007/s00484-014-0825-5
1
Subash
N.
Gangwar
B.
Singh
Rajbir
Sikka
A. K.
Identification of climate-resilient integrated nutrient management practices for rice-rice cropping system-an empirical approach to uphold food security
Yield datasets of long-term experiments on integrated nutrient management in rice-rice cropping systems were used to investigate the relationship of variability in rainfall, temperature, and integrated nutrient management (INM) practices in rice-rice cropping system in three different agroecological regions of India. Twelve treatments with different combinations of inorganic (chemical fertilizer) and organic (farmyard manure, green manure, and paddy straw) were compared with farmer's conventional practice. The intraseasonal variations in rice yields are largely driven by rainfall during kharif rice and by temperature during rabi rice. Half of the standard deviation from the average monthly as well as seasonal rainfall during kharif rice and 1 A degrees C increase or decrease from the average maximum and minimum temperature during rabi rice has been taken as the classification of yield groups. The trends in the date of effective onset of monsoon indicate a 36-day delay during the 30-year period at Rajendranagar, which is statistically significant at 95 % confidence level. The mean annual maximum temperature shows an increasing trend in all the study sites. The length of monsoon also showed a shrinking trend in the rate of 40 days during the 30-year study period at Rajendranagar representing a semiarid region. At Bhubaneshwar, the application of 50 % recommended NPK through chemical fertilizers and 50 % N through green manure resulted in an overall average higher increase of 5.1 % in system productivity under both excess and deficit rainfall years and also during the years having seasonal mean maximum temperature a parts per thousand yen35 A degrees C. However, at Jorhat, the application of 50 % recommended NPK through chemical fertilizers and 50 % N through straw resulted in an overall average higher increase of 7.4 % in system productivity, while at Rajendranagar, the application of 75 % NPK through chemical fertilizers and 25 % N through green manusre resulted in an overall average higher increase of 8.8 % in system productivity. This study highlights the adaptive capacity of different integrated nutrient management practices to rainfall and temperature variability under a rice-rice cropping system in humid, subhumid, and semiarid ecosystems.
2015 JAN
WOS:000346637800007
QID: Q50456507
65-78
journalArticle
12
INTERNATIONAL JOURNAL OF ENVIRONMENTAL RESEARCH AND PUBLIC HEALTH
DOI 10.3390/ijerph120100032
1
Holvoet
Kevin
Sampers
Imca
Seynnaeve
Marleen
Jacxsens
Liesbeth
Uyttendaele
Mieke
Agricultural and Management Practices and Bacterial Contamination in Greenhouse versus Open Field Lettuce Production
The aim of this study was to gain insight into potential differences in risk factors for microbial contamination in greenhouse versus open field lettuce production. Information was collected on sources, testing, and monitoring and if applicable, treatment of irrigation and harvest rinsing water. These data were combined with results of analysis on the levels of Escherichia coli as a fecal indicator organism and the presence of enteric bacterial pathogens on both lettuce crops and environmental samples. Enterohemorragic Escherichia coli (EHEC) PCR signals (vt1 or vt2 positive and eae positive), Campylobacter spp., and Salmonella spp. isolates were more often obtained from irrigation water sampled from open field farms (21/45, 46.7%) versus from greenhouse production (9/75, 12.0%). The open field production was shown to be more prone to fecal contamination as the number of lettuce samples and irrigation water with elevated E. coli was significantly higher. Farmers comply with generic guidelines on good agricultural practices available at the national level, but monitoring of microbial quality, and if applicable appropriateness of water treatment, or water used for irrigation or at harvest is restricted. These results indicate the need for further elaboration of specific guidelines and control measures for leafy greens with regard to microbial hazards.
2015 JAN
WOS:000348403300003
QID: Q35014989
32-63
journalArticle
118
PREVENTIVE VETERINARY MEDICINE
DOI 10.1016/j.prevetmed.2014.10.015
1
De Clercq
E. M.
Leta
S.
Estrada-Pena
A.
Madder
M.
Adehan
S.
Vanwambeke
S. O.
Species distribution modelling for Rhipicephalus microplus (Acari: Ixodidae) in Benin, West Africa: Comparing datasets and modelling algorithms
Rhipicephalus microplus is one of the most widely distributed and economically important ticks, transmitting Babesia bigemina, B. bovis and Anaplasma marginale. It was recently introduced to West Africa on live animals originating from Brazil. Knowing the precise environmental suitability for the tick would allow veterinary health officials to draft vector control strategies for different regions of the country. To test the performance of modelling algorithms and different sets of environmental explanatory variables, species distribution models for this tick species in Benin were developed using generalized linear models, linear discriminant analysis and random forests. The training data for these models were a dataset containing reported absence or presence in 104 farms, randomly selected across Benin. These farms were sampled at the end of the rainy season, which corresponds with an annual peak in tick abundance. Two environmental datasets for the country of Benin were compared: one based on interpolated climate data (WorldClim) and one based on remotely sensed images (MODIS). The pixel size for both environmental datasets was 1 km. Highly suitable areas occurred mainly along the warmer and humid coast extending northwards to central Benin. The northern hot and drier areas were found to be unsuitable. The models developed and tested on data from the entire country were generally found to perform well, having an AUC value greater than 0.92. Although statistically significant, only small differences in accuracy measures were found between the modelling algorithms, or between the environmental datasets. The resulting risk maps differed nonetheless. Models based on interpolated climate suggested gradual variations in habitat suitability, while those based on remotely sensed data indicated a sharper contrast between suitable and unsuitable areas, and a patchy distribution of the suitable areas. Remotely sensed data yielded more spatial detail in the predictions. When computing accuracy measures on a subset of data along the invasion front, the modelling technique Random Forest outperformed the other modelling approaches, and results with MODIS-derived variables were better than those using WorldClim data. The high environmental suitability for R. microplus in the southern half of Benin raises concern at the regional level for animal health, including its potential to substantially alter transmission risk of Babesia bovis. The northern part of Benin appeared overall of low environmental suitability. Continuous surveillance in the transition zone however remains relevant, in relation to important cattle movements in the region, and to the invasive character of R. microplus. (C) 2014 The Authors. Published by Elsevier B.V.
2015 JAN 1
WOS:000348958300002
QID: Q38965091
8-21
journalArticle
34
ENVIRONMENTAL TOXICOLOGY AND CHEMISTRY
DOI 10.1002/etc.2772
1
de Santiago-Martin
Ana
van Oort
Folkert
Gonzalez
Concepcion
Quintana
Jose R.
Lafuente
Antonio L.
Lamy
Isabelle
IMPROVING THE RELATIONSHIP BETWEEN SOIL CHARACTERISTICS AND METAL BIOAVAILABILITY BY USING REACTIVE FRACTIONS OF SOIL PARAMETERS IN CALCAREOUS SOILS
The contribution of the nature instead of the total content of soil parameters relevant to metal bioavailability in lettuce was tested using a series of low-polluted Mediterranean agricultural calcareous soils offering natural gradients in the content and composition of carbonate, organic, and oxide fractions. Two datasets were compared by canonical ordination based on redundancy analysis: total concentrations (TC dataset) of main soil parameters (constituents, phases, or elements) involved in metal retention and bioavailability; and chemically defined reactive fractions of these parameters (RF dataset). The metal bioavailability patterns were satisfactorily explained only when the RF dataset was used, and the results showed that the proportion of crystalline Fe oxides, dissolved organic C, diethylene-triamine-pentaacetic acid (DTPA)-extractable Cu and Zn, and a labile organic pool accounted for 76% of the variance. In addition, 2 multipollution scenarios by metal spiking were tested that showed better relationships with the RF dataset than with the TC dataset (up to 17% more) and new reactive fractions involved. For Mediterranean calcareous soils, the use of reactive pools of soil parameters rather than their total contents improved the relationships between soil constituents and metal bioavailability. Such pool determinations should be systematically included in studies dealing with bioavailability or risk assessment. Environ Toxicol Chem 2015;34:37-44. (c) 2014 SETAC
2015 JAN
WOS:000346789800006
QID: Q57216463
37-44
journalArticle
148
JOURNAL OF ENVIRONMENTAL MANAGEMENT
DOI 10.1016/j.jenvman.2013.12.026
Vadrevu
Krishna
Lasko
Kristofer
Fire regimes and potential bioenergy loss from agricultural lands in the Indo-Gangetic Plains
Agricultural fires in the Indo-Gangetic Plains (IGP) are a major cause of air pollution. In this study, we evaluate fire regimes and quantify the potential of agricultural residues in generating bioenergy that otherwise are subject to burning by local farmers in the region. For characterizing the fire regimes, we used MODIS satellite datasets in conjunction with IRS-AWiFS classified data. We collected crop statistical data for area, production, and yield for 31 different crops and mapped the bioenergy potential of agricultural residues. We also tested the MODIS net primary production (NPP) dataset potential for crop yield estimation and thereby bioenergy calculations. Results from land use-fire analysis suggested that 88.13% of fires occurred in agricultural areas. Relatively more fires and burnt areas were recorded during the winter rice residue burning season than the summer wheat residue burning season. Monte Carlo analysis suggested that nearly 16.5 Tg of crop residues are burned at 60% probability. MODIS NPP data could explain 62% of variation in field-level crop yield estimates. Our analysis revealed that in the IGP nearly 73.28 Tg of crop residue biomass is available for recycling. The energy equivalent from these residues is estimated to be 1110.77 PJ. From the residues, the biogas potential production is estimated to be 1165.1098 million m(3), the electric power potential at 20% efficiency is estimated at 61698.9 kWh, and the total bioethanol production potential at 21.0 billion liters. Results also highlight geographic locations of bioenergy resources in the IGP useful for energy planning. Controlling agricultural residue burning and promoting the bioenergy sector is an attractive "win-win" strategy in the IGP. (C) 2014 Elsevier Ltd. All rights reserved.
2015 JAN 15
WOS:000348016400003
QID: Q43785216
10-20
journalArticle
17
ENVIRONMENTAL SCIENCE-PROCESSES & IMPACTS
DOI 10.1039/c5em00196j
10
Corwin
Dennis L.
Ahmad
Hamaad Raza
Spatio-temporal impacts of dairy lagoon water reuse on soil: heavy metals and salinity
Diminishing freshwater resources have brought attention to the reuse of degraded water as a water resource rather than a disposal problem. The spatial impact and sustainability of dairy lagoon water reuse from concentrated animal feeding operations (CAFOs) has not been evaluated at field scale. The objective of this study is to monitor the impact of dairy lagoon water blended with recycled water on a 32 ha field near San Jacinto, CA from 2007 to 2011. Spatial monitoring was based on soil samples collected at locations identified from apparent soil electrical conductivity (ECa) directed sampling. Soil samples were taken at depth increments of 0-0.15, 0.15-0.3, 0.3-0.6, 0.6-0.9, 0.9-1.2, 1.2-1.5, and 1.5-1.8 m at 28 sample sites on 7-11 May 2007 and again on 31 May -2 June 2011 after 4 years of irrigation with the blended waters. Chemical analyses included salinity (electrical conductivity of the saturation extract, ECe), pH(e) (pH of the saturation extract), SAR (sodium adsorption ratio), trace elements (As, B, Mo, Se), and heavy metals (Cd, Cu, Mn, Ni, Zn). Results indicate a decrease in mean values of pH(e) at all depth increments; a decrease in ECe and SAR above a depth of 0.15 m, but an increase below 0.15 m; a decrease in all trace elements except B, which increased throughout the 1.8 m profile; and the accumulation of Cd, Mn, and Ni at all depth increments, while Cu was readily leached from the 1.8 m profile. Zinc showed little change. The results focused concern on the potential long-term agronomic effect of salinity, SAR, and B, and the long-term environmental threat of salinity and Cu to detrimentally impact groundwater. The accumulation of Cd, Mn, and Ni in the soil profile raised concern since it provided a potential future source of metals for leaching. The long-term sustainability of dairy lagoon water reuse hinges on regular monitoring to provide spatial feedback for site-specific management.
2015
WOS:000362429000004
QID: Q38972251
1731-1748
journalArticle
119
CHEMOSPHERE
DOI 10.1016/j.chemosphere.2014.10.066
Allen
Gina
Halsall
Crispin J.
Ukpebor
Justina
Paul
Nigel D.
Ridall
Gareth
Wargent
Jason J.
Increased occurrence of pesticide residues on crops grown in protected environments compared to crops grown in open field conditions
Crops grown under plastic-clad structures or in greenhouses may be prone to an increased frequency of pesticide residue detections and higher concentrations of pesticides relative to equivalent crops grown in the open field. To test this we examined pesticide data for crops selected from the quarterly reports (2004-2009) of the UK's Pesticide Residue Committee. Five comparison crop pairs were identified whereby one crop of each pair was assumed to have been grown primarily under some form of physical protection ('protected') and the other grown primarily in open field conditions ('open'). For each pair, the number of detectable. pesticide residues and the proportion of crop samples containing pesticides were statistically compared (n = 100 s samples for each crop). The mean concentrations of selected photolabile pesticides were also compared. For the crop pairings of cabbage ('open') vs. lettuce ('protected') and 'berries' ('open') vs. strawberries ('protected') there was a significantly higher number of pesticides and proportion of samples with multiple residues for the protected crops. Statistically higher concentrations of pesticides, including cypermethrin, cyprodinil, fenhexamid, boscalid and iprodione were also found in the protected crops compared to the open crops. The evidence here demonstrates that, in general, the protected crops possess a higher number of detectable pesticides compared to analogous crops grown in the open. This may be due to different pesticide-use regimes, but also due to slower rates of pesticide removal in protected systems. The findings of this study raise implications for pesticide management in protected-crop systems. (C) 2014 Elsevier Ltd. All rights reserved.
2015 JAN
WOS:000347739600195
QID: Q41736551
1428-1435
journalArticle
370
PHILOSOPHICAL TRANSACTIONS OF THE ROYAL SOCIETY B-BIOLOGICAL SCIENCES
DOI 10.1098/rstb.2013.0373
1660
Malmstrom
Helena
Linderholm
Anna
Skoglund
Pontus
Stora
Jan
Sjodin
Per
Gilbert
M. Thomas P.
Holmlund
Gunilla
Willerslev
Eske
Jakobsson
Mattias
Liden
Kerstin
Gotherstrom
Anders
Ancient mitochondrial DNA from the northern fringe of the Neolithic farming expansion in Europe sheds light on the dispersion process
The European Neolithization process started around 12 000 years ago in the Near East. The introduction of agriculture spread north and west throughout Europe and a key question has been if this was brought about by migrating individuals, by an exchange of ideas or a by a mixture of these. The earliest farming evidence in Scandinavia is found within the Funnel Beaker Culture complex (Trichterbecherkultur, TRB) which represents the northernmost extension of Neolithic farmers in Europe. The TRB coexisted for almost a millennium with hunter-gatherers of the Pitted Ware Cultural complex (PWC). If migration was a substantial part of the Neolithization, even the northerly TRB community would display a closer genetic affinity to other farmer populations than to hunter-gatherer populations. We deep-sequenced the mitochondrial hypervariable region 1 from seven farmers (six TRB and one Battle Axe complex, BAC) and 13 hunter-gatherers (PWC) and authenticated the sequences using postmortem DNA damage patterns. A comparison with 124 previously published sequences from prehistoric Europe shows that the TRB individuals share a close affinity to Central European farmer populations, and that they are distinct from hunter-gatherer groups, including the geographically close and partially contemporary PWC that show a close affinity to the European Mesolithic hunter-gatherers.
2015 JAN 19
WOS:000346147700002
QID: Q34768723
journalArticle
505
SCIENCE OF THE TOTAL ENVIRONMENT
DOI 10.1016/j.scitotenv.2014.11.023
Zhang
Anping
Luo
Wenxiu
Sun
Jianqiang
Xiao
Hang
Liu
Weiping
Distribution and uptake pathways of organochlorine pesticides in greenhouse and conventional vegetables
The application of greenhouse vegetable cultivation has dramatically expanded worldwide during the last several decades. However, little information is available on the distribution and uptake of pesticides in greenhouse vegetables. To bridge this knowledge gap, the present study was initiated to investigate the distribution and uptake of organochlorine pesticides (OCPs) in vegetables from plastic greenhouse and conventional cultivation methods. The uptake pathways of OCPs were not significantly different between these two cultivation methods. The arithmetic means of OCP concentrations in greenhouse vegetables were higher than those in conventional vegetables, although there was no significant difference. This small difference raised the concern of whether the tiny difference could be magnified to a significant difference by bioaccumulation in the food chain. The issue should be addressed by a well-designed scheme in future studies. (C) 2014 Elsevier B.V. All rights reserved.
2015 FEB 1
WOS:000347654900112
QID: Q39085444
1142-1147
journalArticle
505
SCIENCE OF THE TOTAL ENVIRONMENT
DOI 10.1016/j.scitotenv.2014.09.101
Whittaker
Gerald
Barnhart
Bradley L.
Srinivasan
Raghavan
Arnold
Jeffrey G.
Cost of areal reduction of gulf hypoxia through agricultural practice
A major share of the area of hypoxic growth in the Northern Gulf of Mexico has been attributed to nutrient runoff from agricultural fields, but no estimate is available for the cost of reducing Gulf hypoxic area using agricultural conservation practices. We apply the Soil and Water Assessment Tool using observed daily weather to simulate the reduction in nitrogen loading in the Upper Mississippi River Basin (UMRB) that would result from enrolling all row crop acreage in the Conservation Reserve Program (CRP). Nitrogen loadings at the outlet of the UMRB are used to predict Gulf hypoxic area, and net cash farm rent is used as the price for participation in the CRP. Over the course of the 42 year simulation, direct CRP costs total more than $388 billion, and the Inter-Governmental Task Force goal of hypoxic area less than 5000 square kilometers is met in only two years. Published by Elsevier B.V.
2015 FEB 1
WOS:000347654900014
QID: Q41742009
149-153
journalArticle
37
ENVIRONMENTAL GEOCHEMISTRY AND HEALTH
DOI 10.1007/s10653-014-9638-z
1
Singh
Sudhir Kumar
Srivastava
Prashant K.
Singh
Dharmveer
Han
Dawei
Gautam
Sandeep Kumar
Pandey
A. C.
Modeling groundwater quality over a humid subtropical region using numerical indices, earth observation datasets, and X-ray diffraction technique: a case study of Allahabad district, India
Water is undoubtedly the vital commodity for all living creatures and required for well-being of the human society. The present work is based on the surveys and chemical analyses performed on the collected groundwater samples in a part of the Ganga basin in order to understand the sources and evolution of the water quality in the region. The two standard indices such as water quality index and synthetic pollution index for the classification of water in the region are computed. The soil and sediment analysis are carried out with the help of X-ray diffractometer (XRD) for the identification of possible source of ions in water from rock and soil weathering. The dominant minerals which include quartz, muscovite, plagioclase, and orthoclase are reported in the area. The study further utilizes the multivariate statistical techniques for handling large and complex datasets in order to get better information about the groundwater quality. The following statistical methods such as cluster analysis (CA), factor analysis (FA), and principal component analysis (PCA) are applied to handle the large datasets and to understand the latent structure of the data. Through FA/PCAs, we have identified a total of 3 factors in pre-monsoon and 4 factors in post-monsoon season, which are responsible for the whole data structure. These factors explain 77.62 and 82.39 % of the total variance of the pre- and post-monsoon datasets. On the other hand, CA depicted the regions that have similar pollutants origin. The average value of synthetic pollution index of groundwater during pre-monsoon is 9.27, while during post-monsoon, it has been recorded as 8.74. On the other hand, the average values of water quality index of groundwater during pre-monsoon and post-monsoon seasons are found as 217.59 and 233.02, respectively. The study indicates that there occurs an extensive urbanization with gradual vast development of various small-and large-scale industries, which is responsible for degradation in water quality. The overall analysis reveals that the agricultural runoff, waste disposal, leaching, and irrigation with waste-water are the main causes of groundwater pollution followed by some degree of pollution from geogenic sources such as rock and soil weathering, confirmed through XRD analysis.
2015 FEB
WOS:000351751600012
QID: Q45135051
157-180
journalArticle
58
AMERICAN JOURNAL OF INDUSTRIAL MEDICINE
DOI 10.1002/ajim.22380
2
Thierry
Amy Danielle
Snipes
Shedra Amy
Why do Farmworkers Delay Treatment After Debilitating Injuries? Thematic Analysis Explains If, When, and Why Farmworkers Were Treated for Injuries
BackgroundFarmworkers who delay treatment after workplace injuries may increase injury severity and experience longer recovery times. To understand why farmworkers delay treatment we employed a mixed-methods analysis of 393 farmworker injury narratives from the National Agricultural Workers Survey (NAWS).MethodsFirst, open-ended injury narratives were coded for attitudes related to injury timing and delay. Next, narratives were compared against demographic survey attributes to assess contextual information and patterns linked to treatment timing.ResultsFour treatment timings were identified: immediate medical treatment (57.9%), delayed medical treatment (18.2%) self- administered treatment (14.9%), and no treatment at all (8.9%). Delay was primarily attributed to attitudes prioritizing work over pain, and when workers were able to work despite injury. However, immediate treatment was sought when workers were completely debilitated and unable to work, when a supervisor was notified, or when exposed to pesticides during injury. Timing choices varied by education, gender and migrant status.ConclusionsTraining on timely treatment, including notification of supervisors, may help reduce treatment delay for farmworkers. Am. J. Ind. Med. 58:178-192, 2015. (c) 2015 Wiley Periodicals, Inc.
2015 FEB
WOS:000348563100006
QID: Q41555734
178-192
journalArticle
505
SCIENCE OF THE TOTAL ENVIRONMENT
DOI 10.1016/j.scitotenv.2014.10.088
Liu
Jing
Sun
Shikun
Wu
Pute
Wang
Yubao
Zhao
Xining
Evaluation of crop production, trade, and consumption from the perspective of water resources: A case study of the Hetao irrigation district, China, for 1960-2010
The integration of water footprints and virtual water flows allows the mapping of the links between production, trade, and consumption and could potentially help to alleviate water scarcity and improve water management. We evaluated the water footprints and virtual water flows of crop production, consumption, and trade and their influencing factors in the Hetao irrigation district in China for 1960-2010. The water footprint of crop production and the export of virtual water fluctuated but tended to increase during this period and were influenced mainly by agricultural factors such as crop yield, irrigation efficiency, and area sown. The water footprint of crop consumption and the import of virtual water increased during 1960-1979 and decreased during 1980-2010 and were influenced by socio-economic factors such as total population, the retail-price index, and the proportion of the population in urban areas. Most of the water footprint of production was exported to other areas, which added to the pressure on local water systems. The import of virtual water led to a saving of water for the Hetao irrigation district, while its share of the water footprint of consumption has decreased significantly since 1977. An increase in irrigation efficiency can alleviate water scarcity, and its application should be coupled with measures that constrain the continued expansion of agriculture. Full-cost pricing of irrigation water was an effective policy tool for its management. Re-shaping regional water-production and water-trade nexuses by changing crop structures could provide alternative opportunities for addressing the problems of local water scarcity, but the trade-offs involved should first be assessed. (C) 2014 Elsevier B.V. All rights reserved.
2015 FEB 1
WOS:000347654900116
QID: Q40240209
1174-1181
journalArticle
12
Foodborne Pathogens and Disease
DOI 10.1089/fpd.2014.1817
2
Hamilton
Karin E.
Umber
Jamie
Hultberg
Annalisa
Tong
Cindy
Schermann
Michele
Diez-Gonzalez
Francisco
Bender
Jeff B.
Validation of Good Agricultural Practices (GAP) on Minnesota Vegetable Farms
The United States Food and Drug Administration and the Department of Agriculture jointly published the "Guide to Minimize Microbial Food Safety Hazards for Fresh Fruits and Vegetables," which is used as a basis for Good Agricultural Practices (GAP) audits. To understand barriers to incorporation of GAP by Minnesota vegetable farmers, a mail survey completed in 2008 was validated with visits to a subset of the farms. This was done to determine the extent to which actual practices matched perceived practices. Two hundred forty-six producers completed the mail survey, and 27 participated in the on-farm survey. Over 75% of the on-farm survey respondents produced vegetables on 10 acres or less and had 10 or fewer employees. Of 14 questions, excellent agreement between on-farm interviews and mail survey responses was observed on two questions, four questions had poor or slight agreement, and eight questions had no agreement. Ninety-two percent of respondents by mail said "they took measures to keep animals and pests out of packing and storage buildings." However, with the on-site visit only 45% met this requirement. Similarly, 81% of respondents by mail said "measures were taken to reduce the risk of wild and/or domestic animals entering into fruit and vegetable growing areas." With direct observation, 70% of farms actually had taken measures to keep animals out of the growing areas. Additional, on-farm assessments were done regarding employee hygiene, training, presence of animals, water sources, and composting practices. This validation study demonstrated the challenge of creating nonleading and concise questions that are not open to broad interpretation from the respondents. If mail surveys are used to assess GAP, they should include open-ended questions and ranking systems to better assess farm practices. To provide the most accurate survey data for educational purposes or GAP audits, on-farm visits are recommended.
2015 FEB 1
WOS:000349008100008
QID: Q41615457
145-150
journalArticle
71
PEST MANAGEMENT SCIENCE
DOI 10.1002/ps.3781
2
Grimmer
Michael K.
van den Bosch
Frank
Powers
Stephen J.
Paveley
Neil D.
Fungicide resistance risk assessment based on traits associated with the rate of pathogen evolution
BACKGROUNDA new fungicide resistance risk assessment method is described, based on traits (of pathogens, fungicides and agronomic systems) that are associated with rapid or slow occurrence of resistance. Candidate traits tested for their predictive value were those for which there was a mechanistic rationale that they could be determinants of the rate of resistance evolution.RESULTSA dataset of 61 European cases of resistance against single-site-acting fungicides was assembled. For each case, the number of years from product introduction to first detection of resistance (the FDR time) was quantified-varying from 2 to 24 years. Short and long predicted FDR times represent high and low resistance risk respectively. Regression analysis identified traits that were statistically associated with FDR time. A model combining these traits explained 61% of the variation in FDR time. Validation showed that this predictive power was highly unlikely to have occurred by chance.CONCLUSIONUnlike previous methods, trait-based risk assessment can be used to assess resistance risk for fungicides with new modes of action, when there is no prior knowledge of resistance behaviour. Risk predictions using the new method provide a more reliable basis for resistance management decisions. (c) 2014 Society of Chemical Industry
2015 FEB
WOS:000347234400007
QID: Q87512482
207-215
journalArticle
114
HEREDITY
DOI 10.1038/hdy.2014.83
2
Forsberg
N. E. G.
Russell
J.
Macaulay
M.
Leino
M. W.
Hagenblad
J.
Farmers without borders-genetic structuring in century old barley (Hordeum vulgare)
The geographic distribution of genetic diversity can reveal the evolutionary history of a species. For crop plants, phylogeographic patterns also indicate how seed has been exchanged and spread in agrarian communities. Such patterns are, however, easily blurred by the intense seed trade, plant improvement and even genebank conservation during the twentieth century, and discerning fine-scale phylogeographic patterns is thus particularly challenging. Using historical crop specimens, these problems are circumvented and we show here how high-throughput genotyping of historical nineteenth century crop specimens can reveal detailed geographic population structure. Thirty-one historical and nine extant accessions of North European landrace barley (Hordeum vulgare L.), in total 231 individuals, were genotyped on a 384 single nucleotide polymorphism assay. The historical material shows constant high levels of within-accession diversity, whereas the extant accessions show more varying levels of diversity and a higher degree of total genotype sharing. Structure, discriminant analysis of principal components and principal component analysis cluster the accessions in latitudinal groups across country borders in Finland, Norway and Sweden. F-ST statistics indicate strong differentiation between accessions from southern Fennoscandia and accessions from central or northern Fennoscandia, and less differentiation between central and northern accessions. These findings are discussed in the context of contrasting historical records on intense within-country south to north seed movement. Our results suggest that although seeds were traded long distances, long-term cultivation has instead been of locally available, possibly better adapted, genotypes.
2015 FEB
WOS:000348071600008
QID: Q35256584
195-206
journalArticle
187
ENVIRONMENTAL MONITORING AND ASSESSMENT
DOI 10.1007/s10661-015-4307-y
2
Cuoco
E.
Darrah
T. H.
Buono
G.
Verrengia
G.
De Francesco
S.
Eymold
W. K.
Tedesco
D.
Inorganic contaminants from diffuse pollution in shallow groundwater of the Campanian Plain (Southern Italy). Implications for geochemical survey
The Campanian Plain (CP) shallow aquifer (Southern Italy) represents a natural laboratory to validate geochemical methods for differentiating diffuse anthropogenic pollution from natural water-rock interaction processes. The CP is an appropriate study area because of numerous potential anthropogenic pollution vectors including agriculture, animal husbandry, septic/drainage sewage systems, and industry. In order to evaluate the potential for geochemical methods to differentiate various contamination vectors, 538 groundwater wells from the shallow aquifer in Campanian Plain (CP) were sampled. The dataset includes both major and trace elements. Natural water-rock interactions, which primarily depend on local lithology, control the majority of geochemical parameters, including most of the major and trace elements. Using prospective statistical methods in combination with the traditional geochemical techniques, we determined the chemical variables that are enriched by anthropogenic contamination (i.e. NO3, SO4 and U) by using NO3 as the diagnostic variable for detecting polluted groundwater. Synthetic agricultural fertilizers are responsible for the majority of SO4 and U pollution throughout the CP area. Both SO4 and U are present in the groundmass of synthetic fertilizers; the uranium concentration is specifically applicable as a tracer for non-point source agricultural fertilizer contamination. The recognition of non-geological (anthropogenic) inputs of these elements has to be considered in the geochemical investigations of contaminated aquifers.
2015 FEB
WOS:000349012200046
QID: Q86632089
journalArticle
10
PLOS ONE
DOI 10.1371/journal.pone.0116846
2
Boerner
Jan
Marinho
Eduardo
Wunder
Sven
Mixing Carrots and Sticks to Conserve Forests in the Brazilian Amazon: A Spatial Probabilistic Modeling Approach
Annual forest loss in the Brazilian Amazon had in 2012 declined to less than 5,000 sqkm, from over 27,000 in 2004. Mounting empirical evidence suggests that changes in Brazilian law enforcement strategy and the related governance system may account for a large share of the overall success in curbing deforestation rates. At the same time, Brazil is experimenting with alternative approaches to compensate farmers for conservation actions through economic incentives, such as payments for environmental services, at various administrative levels. We develop a spatially explicit simulation model for deforestation decisions in response to policy incentives and disincentives. The model builds on elements of optimal enforcement theory and introduces the notion of imperfect payment contract enforcement in the context of avoided deforestation. We implement the simulations using official deforestation statistics and data collected from field-based forest law enforcement operations in the Amazon region. We show that a large-scale integration of payments with the existing regulatory enforcement strategy involves a tradeoff between the cost-effectiveness of forest conservation and landholder incomes. Introducing payments as a complementary policy measure increases policy implementation cost, reduces income losses for those hit hardest by law enforcement, and can provide additional income to some land users. The magnitude of the tradeoff varies in space, depending on deforestation patterns, conservation opportunity and enforcement costs. Enforcement effectiveness becomes a key determinant of efficiency in the overall policy mix.
2015 FEB 4
WOS:000349250700007
QID: Q35049432
journalArticle
506
SCIENCE OF THE TOTAL ENVIRONMENT
DOI 10.1016/j.scitotenv.2014.11.010
Peng
Shuang
Wang
Yiming
Zhou
Beibei
Lin
Xiangui
Long-term application of fresh and composted manure increase tetracycline resistance in the arable soil of eastern China
The aim of this study was to compare the occurrence, abundance, and diversity of tetracycline resistance genes (tet) in agricultural soils after 6 years' application of fresh or composted swine manure. Soil samples were collected from fresh or composted manure-treated farmland at three depths (0-5 cm, 5-10 cm, and 10-20 cm). Nine classes of tet genes RetW, tetB(P), tet0, tetS, tetC, tetG, tetZ, tetL, and tetX] were detected; tetG, tetZ, tetL, and tetB(P) were predominant in the manure-treated soil. The abundances of tetB(P), tetW, tetC, and tet0 were reduced, while tetG and tetL were increased by fertilizing with composted versus fresh manure; thus, the total abundance of tet genes was not significantly reduced by compost manuring. tetG was the most abundant gene in manure-treated soil; the predominant tetG genotypes shared high homology with pathogenic bacteria. The tetC isolates were more diverse in soils treated with fresh versus composted manure, although the residual tet genes in composted manure remain a pollutant and produce a different influence on the tet gene resistome in field soil. (C) 2014 Elsevier B.V. All rights reserved.
2015 FEB 15
WOS:000347576800029
QID: Q53674992
279-286
journalArticle
30
HEALTH POLICY AND PLANNING
DOI 10.1093/heapol/czt106
2
Wendland
Kelly J.
Pattanayak
Subhrendu K.
Sills
Erin O.
National-level differences in the adoption of environmental health technologies: a cross-border comparison from Benin and Togo
Environmental health problems such as malaria, respiratory infections, diarrhoea and malnutrition pose very high burdens on the poor rural people in much of the tropics. Recent research on key interventions-the adoption and use of relatively cheap and effective environmental health technologies-has focused primarily on the influence of demand-side household-level drivers. Relatively few studies of the promotion and use of these technologies have considered the role of contextual factors such as governance, the enabling environment and national policies because of the challenges of cross-country comparisons. We exploit a natural experimental setting by comparing household adoption across the Benin-Togo national border that splits the Tamberma Valley in West Africa. Households across the border share the same culture, ethnicity, weather, physiographic features, livelihoods and infrastructure; however, they are located in countries at virtually opposite ends of the institutional spectrum of democratic elections, voice and accountability, effective governance and corruption. Binary choice models and rigorous non-parametric matching estimators confirm that households in Benin are more likely than households in Togo to plant soybeans, build improved cookstoves and purchase mosquito nets, ceteris paribus. Although we cannot identify the exact mechanism for the large and significant national-level differences in technology adoption, our findings suggest that contextual institutional factors can be more important than household characteristics for technology adoption.
2015 MAR
WOS:000352229700001
QID: Q38401031
145-154
journalArticle
508
SCIENCE OF THE TOTAL ENVIRONMENT
DOI 10.1016/j.scitotenv.2014.11.055
Wang
Fei
Mu
Xingmin
Li
Rui
Fleskens
Luuk
Stringer
Lindsay C.
Ritsema
Coen J.
Co-evolution of soil and water conservation policy and human-environment linkages in the Yellow River Basin since 1949
Policy plays a very important role in natural resource management as it lays out a government framework for guiding long-term decisions, and evolves in light of the interactions between human and environment. This paper focuses on soil and water conservation (SWC) policy in the Yellow River Basin (YRB), China. The problems, rural poverty, severe soil erosion, great sediment loads and high flood risks, are analyzed over the period of 1949-present using the Driving force-Pressure-State-Impact-Response (DPSIR) framework as a way to organize analysis of the evolution of SWC policy. Three stages are identified in which SWC policy interacts differently with institutional, financial and technology support. In Stage 1(1949-1979), SWC policy focused on rural development in eroded areas and on reducing sediment loads. Local farmers were mainly responsible for SWC The aim of Stage 2(1980-1990) was the overall development of rural industry and SWC. A more integrated management perspective was implemented taking a small watershed as a geographic interactional unit. This approach greatly improved the efficiency of SWC activities. In Stage 3 (1991 till now), SWC has been treated as the main measure for natural resource conservation, environmental protection, disaster mitigation and agriculture development. Prevention of new degradation became a priority. The government began to be responsible for SWC, using administrative, legal and financial approaches and various technologies that made large-scale SWC engineering possible. Over the historical period considered, with the implementation of the various SWC policies, the rural economic and ecological system improved continuously while the sediment load and flood risk decreased dramatically. The findings assist in providing a historical perspective that could inform more rational, scientific and effective natural resource management going forward. (C) 2014 The Authors. Published by Elsevier B.V. This is an open access article under the CC BY license
2015 MAR 1
WOS:000349195100020
QID: Q41723940
166-177
journalArticle
55
WOMEN & HEALTH
DOI 10.1080/03630242.2014.979968
2
Woldu
Dawit Okubatsion
Haile
Zelalem Teka
Gender Roles and Perceptions of Malaria Risk in Agricultural Communities of Mwea Division in Central Kenya
We examined gender differences in the perception of high malaria risk in women and factors associated with a high number of malaria episodes in the Mwea Division of Central Kenya. Ethnographic and successive free listing interviews (an open-ended data collection technique used to show the relation of items in a given domain) with 53 key informants and structured interviews conducted from June to October 2010 with 250 respondents who represented the socioeconomic and geographical diversity of the area were analyzed. Qualitative text analysis and inferential statistics were employed. While a greater proportion of men (51.6%) attributed women's high malaria risk to their "biological weakness," most women believed that their high malaria risk was related to their role in the agricultural fields (43.6%) and to their household responsibilities (23.1%). Compared to men, women were more likely to work in wet aspects of agricultural activities (chi(2) (2, N = 153) = 13.47, p < .01). Women were nearly twice as likely as men to report high episodes of malaria (adjusted odds ratio: 2.54; 95% confidence interval: 1.05-6.15). Culturally prescribed gender roles in agricultural communities in Mwea may play an important role in explaining disparity in reported malaria incidence. While identification of ecological and economic determinants of malaria is important, gender-based research can make a significant contribution to the development of effective and sustainable malaria reduction strategies.
2015 FEB 17
WOS:000351763100007
QID: Q41213432
227-243
journalArticle
21
GLOBAL CHANGE BIOLOGY
DOI 10.1111/gcb.12776
3
Fyfe
Ralph M.
Woodbridge
Jessie
Roberts
Neil
From forest to farmland: pollen-inferred land cover change across Europe using the pseudobiomization approach
Maps of continental-scale land cover are utilized by a range of diverse users but whilst a range of products exist that describe present and recent land cover in Europe, there are currently no datasets that describe past variations over long time-scales. User groups with an interest in past land cover include the climate modelling community, socio-ecological historians and earth system scientists. Europe is one of the continents with the longest histories of land conversion from forest to farmland, thus understanding land cover change in this area is globally significant. This study applies the pseudobiomization method (PBM) to 982 pollen records from across Europe, taken from the European Pollen Database (EPD) to produce a first synthesis of pan-European land cover change for the period 9000 bp to present, in contiguous 200year time intervals. The PBM transforms pollen proportions from each site to one of eight land cover classes (LCCs) that are directly comparable to the CORINE land cover classification. The proportion of LCCs represented in each time window provides a spatially aggregated record of land cover change for temperate and northern Europe, and for a series of case study regions (western France, the western Alps, and the Czech Republic and Slovakia). At the European scale, the impact of Neolithic food producing economies appear to be detectable from 6000 bp through reduction in broad-leaf forests resulting from human land use activities such as forest clearance. Total forest cover at a pan-European scale moved outside the range of previous background variability from 4000 bp onwards. From 2200 bp land cover change intensified, and the broad pattern of land cover for preindustrial Europe was established by 1000 bp. Recognizing the timing of anthropogenic land cover change in Europe will further the understanding of land cover-climate interactions, and the origins of the modern cultural landscape.
2015 MAR
WOS:000349896400016
QID: Q46821518
1197-1212
journalArticle
80
JOURNAL OF HUMAN EVOLUTION
DOI 10.1016/j.jhevol.2014.11.005
Noback
Marlijn L.
Harvati
Katerina
The contribution of subsistence to global human cranial variation
Diet-related cranial variation in modern humans is well documented on a regional scale, with ample examples of cranial changes related to the agricultural transition. However, the influence of subsistence strategy on global cranial variation is less clear, having been confirmed only for the mandible, and dietary effects beyond agriculture are often neglected. Here we identify global patterns of subsistence-related human cranial shape variation. We analysed a worldwide sample of 15 populations (n = 255) with known subsistence strategies using 3-D landmark datasets designed to capture the shape of different units of the cranium. Results show significant correlations between global cranial shape and diet, especially for temporalis muscle shape and general cranial shape. Importantly, the differences between populations with either a plant- or an animal-based diet are more pronounced than those between agriculturalists and hunter-gatherers, suggesting that the influence of diet as driver of cranial variation is not limited to Holocene transitions to agricultural subsistence. Dental arch shape did not correlate with subsistence pattern, possibly indicating the high plasticity of this region of the face in relation to age, disease and individual use of the dentition. Our results highlight the importance of subsistence strategy as one of the factors underlying the evolution of human geographic cranial variation. (C) 2014 Elsevier Ltd. All rights reserved.
2015 MAR
WOS:000352750800003
QID: Q51010344
34-50
journalArticle
55
ENVIRONMENTAL MANAGEMENT
DOI 10.1007/s00267-014-0431-7
3
Norgrove
Lindsey
Hauser
Stefan
Estimating the Consequences of Fire Exclusion for Food Crop Production, Soil Fertility, and Fallow Recovery in Shifting Cultivation Landscapes in the Humid Tropics
In the Congo Basin, smallholder farmers practice slash-and-burn shifting cultivation. Yet, deliberate burning might no longer be sustainable under reduced fallow scenarios. We synthesized data from the Forest Margins Benchmark Area (FMBA), comprising 1.54 million hectares (ha), in southern Cameroon and assessed the impact of fire exclusion on yield, labor inputs, soil fertility, ecosystem carbon stocks, and fallow recovery indicators in two common field types (plantain and maize) under both current and reduced fallow scenarios. While we could not distinguish between impacts of standard farmer burning practice and fire exclusion treatments for the current fallow scenario, we concluded that fire exclusion would lead to higher yields, higher ecosystem carbon stocks as well as potentially faster fallow recovery under the reduced fallow scenario. While its implementation would increase labor requirements, we estimated increased revenues of 421 and 388 US$ ha(-1) for plantain and maize, respectively. Applied to the FMBA, and assuming a 6-year reduced fallow scenario, fire exclusion in plantain fields would potentially retain 240,464 Mg more ecosystem carbon, comprising topsoil carbon plus tree biomass carbon, than standard farmer practice. Results demonstrate a potential "win-win scenario" where yield benefits, albeit modest, and conservation benefits can be obtained simultaneously. This could be considered as a transitional phase towards higher input use and thus higher yielding systems.
2015 MAR
WOS:000350368300002
QID: Q35126794
536-549
journalArticle
10
PLOS ONE
DOI 10.1371/journal.pone.0121689
3
Calenge
Clement
Chadoeuf
Joel
Giraud
Christophe
Huet
Sylvie
Julliard
Romain
Monestiez
Pascal
Piffady
Jeremy
Pinaud
David
Ruette
Sandrine
The Spatial Distribution of Mustelidae in France
We estimated the spatial distribution of 6 Mustelidae species in France using the data collected by the French national hunting and wildlife agency under the "small carnivorous species logbooks" program. The 1500 national wildlife protection officers working for this agency spend 80% of their working time traveling in the spatial area in which they have authority. During their travels, they occasionally detect dead or living small and medium size carnivorous animals. Between 2002 and 2005, each car operated by this agency was equipped with a logbook in which officers recorded information about the detected animals (species, location, dead or alive, date). Thus, more than 30000 dead or living animals were detected during the study period. Because a large number of detected animals in a region could have been the result of a high sampling pressure there, we modeled the number of detected animals as a function of the sampling effort to allow for unbiased estimation of the species density. For dead animals - mostly roadkill - we supposed that the effort in a given region was proportional to the distance traveled by the officers. For living animals, we had no way to measure the sampling effort. We demonstrated that it was possible to use the whole dataset (dead and living animals) to estimate the following: (i) the relative density i.e., the density multiplied by an unknown constant - of each species of interest across the different French agricultural regions, (ii) the sampling effort for living animals for each region, and (iii) the relative detection probability for various species of interest.
2015 MAR 26
WOS:000356353700128
QID: Q35220240
journalArticle
10
PLOS ONE
DOI 10.1371/journal.pone.0122492
3
Melis
Claudia
Herfindal
Ivar
Dahl
Fredrik
Ahlen
Per-Arne
Individual and Temporal Variation in Habitat Association of an Alien Carnivore at Its Invasion Front
Gathering information on how invasive species utilize the habitat is important, in order to better aim actions to reduce their negative impact. We studied habitat use and selection of 55 GPS-marked raccoon dogs (30 males, 25 females) at their invasion front in Northern Sweden, with particular focus on differences between males and females, between movement states, and between seasons and times of the day. Daily movement pattern was used to classify GPS-locations into dispersing and settled. We focused on both anthropogenic and natural landscape characteristics. Since we did not have any a priori knowledge about the spatial scale of raccoon dog habitat selection, we first assessed how landscape characteristics of random points changed with distance from the GPS-location they were paired to. Because changes in habitat use became less pronounced at approximately 5 km for all variables, we focused on habitat use at two spatial scales: fine (500 m) and coarse (5 km). Habitat selection was strongest at the coarse scale, and reflected the results found for habitat use. Raccoon dogs selected agricultural areas and wetlands, lower altitudes, and shallow slopes, and avoided forests, open natural areas, and areas close to water and roads. There were no differences in habitat selection between males and females, or between movement states. This lack of sexual segregation increases the probability of encountering potential mates during dispersal, and therefore the likelihood for reproduction in new areas. The seasonal and diurnal pattern of habitat use may provide guidance for where and when to aim management efforts.
2015 MAR 27
WOS:000352133600184
QID: Q35224699
journalArticle
29
CONSERVATION BIOLOGY
DOI 10.1111/cobi.12411
2
Milder
Jeffrey C.
Arbuthnot
Margaret
Blackman
Allen
Brooks
Sharon E.
Giovannucci
Daniele
Gross
Lee
Kennedy
Elizabeth T.
Komives
Kristin
Lambin
Eric F.
Lee
Audrey
Meyer
Daniel
Newton
Peter
Phalan
Ben
Schroth
Goetz
Semroc
Bambi
Van Rikxoort
Henk
Zrust
Michal
An agenda for assessing and improving conservation impacts of sustainability standards in tropical agriculture
Sustainability standards and certification serve to differentiate and provide market recognition to goods produced in accordance with social and environmental good practices, typically including practices to protect biodiversity. Such standards have seen rapid growth, including in tropical agricultural commodities such as cocoa, coffee, palm oil, soybeans, and tea. Given the role of sustainability standards in influencing land use in hotspots of biodiversity, deforestation, and agricultural intensification, much could be gained from efforts to evaluate and increase the conservation payoff of these schemes. To this end, we devised a systematic approach for monitoring and evaluating the conservation impacts of agricultural sustainability standards and for using the resulting evidence to improve the effectiveness of such standards over time. The approach is oriented around a set of hypotheses and corresponding research questions about how sustainability standards are predicted to deliver conservation benefits. These questions are addressed through data from multiple sources, including basic common information from certification audits; field monitoring of environmental outcomes at a sample of certified sites; and rigorous impact assessment research based on experimental or quasi-experimental methods. Integration of these sources can generate time-series data that are comparable across sites and regions and provide detailed portraits of the effects of sustainability standards. To implement this approach, we propose new collaborations between the conservation research community and the sustainability standards community to develop common indicators and monitoring protocols, foster data sharing and synthesis, and link research and practice more effectively. As the role of sustainability standards in tropical land-use governance continues to evolve, robust evidence on the factors contributing to effectiveness can help to ensure that such standards are designed and implemented to maximize benefits for biodiversity conservation.
2015 APR
WOS:000351353400002
QID: Q35386566
309-320
journalArticle
29
CONSERVATION BIOLOGY
DOI 10.1111/cobi.12422
2
Gilroy
James J.
Medina Uribe
Claudia A.
Haugaasen
Torbjorn
Edwards
David P.
Effect of scale on trait predictors of species responses to agriculture
Species persistence in human-altered landscapes can depend on factors operating at multiple spatial scales. To understand anthropogenic impacts on biodiversity, it is useful to examine relationships between species traits and their responses to land-use change. A key knowledge gap concerns whether these relationships vary depending on the scale of response under consideration. We examined how local- and large-scale habitat variables influence the occupancy dynamics of a bird community in cloud forest zones in the Colombian Choco-Andes. Using data collected across a continuum of forest and agriculture, we examined which traits best predict species responses to local variation in farmland and which traits best predict species responses to isolation from contiguous forest. Global range size was a strong predictor of species responses to agriculture at both scales; widespread species were less likely to decline as local habitat cover decreased and as distance from forest increased. Habitat specialization was a strong predictor of species responses only at the local scale. Open-habitat species were particularly likely to increase as pasture increased, but they were relatively insensitive to variation in distance to forest. Foraging plasticity and flocking behavior were strong predictors of species responses to distance from forest, but not their responses to local habitat. Species with lower plasticity in foraging behaviors and obligate flock-following species were more likely to decline as distance from contiguous forest increased. For species exhibiting these latter traits, persistence in tropical landscapes may depend on the protection of larger contiguous blocks of forest, rather than the integration of smaller-scale woodland areas within farmland. Species listed as threatened or near threatened on the International Union for Conservation of Nature Red List were also more likely to decline in response to both local habitat quality and isolation from forest relative to least-concern species, underlining the importance of contiguous forests for threatened taxa.
2015 APR
WOS:000351353400017
QID: Q35419756
463-472
journalArticle
20
JOURNAL OF AGROMEDICINE
DOI 10.1080/1059924X.2015.1010067
2
Cramer
Mary E.
Wendl
Mary J.
Children's Agricultural Safety Network: Evaluating Organizational Effectiveness and Impacts
Coalitions that are effectively organized and led are more likely to achieve their intended program outcomes and impacts, as well as achieve sustainability. External evaluation of the coalition's governance and leadership can help identify strengths and areas for improvement. This article describes the evaluation of the Children's Agricultural Safety Network (CASN)-a national coalition, or network of 45 organizational members. The conceptual framework, Internal Coalition Outcomes Hierarchy, guided the evaluation. We used a mixed-methods approach to answer study's primary objectives from the perspective of CASN members and leaders for (a) organizational effectiveness, (b) network impact, and (c) member benefits. We collected quantitative data using a survey and the Internal Coalition Effectiveness (ICE) instrument. Focused interviews were conducted by phone to gather rich data on examples. Combined findings showed that both members and leaders rated the CASN effective in all construct areas that define successful coalitions. Members feel as invested in CASN success as do leaders. The major impact of CASN has been as a national leader and clearinghouse for childhood safety issues, and the most frequently cited example of impact was the national tractor safety campaign. Members identified the benefits of CASN membership as networking, resource sharing, and opportunities to enhance their knowledge, skills, and practices in the area. Members also valued the national attention that CASN was able to bring to the important issues in childhood agricultural safety. Suggestions for improvement were to focus on more research to improve best practices and strengthen dissemination and implementation science.
2015 APR 3
WOS:000353491300003
QID: Q41022996
105-115
journalArticle
105
BULLETIN OF ENTOMOLOGICAL RESEARCH
DOI 10.1017/S0007485315000012
2
Allema
A. B.
van der Werf
W.
Groot
J. C. J.
Hemerik
L.
Gort
G.
Rossing
W. A. H.
van Lenteren
J. C.
Quantification of motility of carabid beetles in farmland
Quantification of the movement of insects at field and landscape levels helps us to understand their ecology and ecological functions. We conducted a meta-analysis on movement of carabid beetles (Coleoptera: Carabidae), to identify key factors affecting movement and population redistribution. We characterize the rate of redistribution using motility mu (L-2 T-1), which is a measure for diffusion of a population in space and time that is consistent with ecological diffusion theory and which can be used for upscaling short-term data to longer time frames. Formulas are provided to calculate motility from literature data on movement distances. A field experiment was conducted to measure the redistribution of mass-released carabid, Pterostichus melanarius in a crop field, and derive motility by fitting a Fokker-Planck diffusion model using inverse modelling. Bias in estimates of motility from literature data is elucidated using the data from the field experiment as a case study. The meta-analysis showed that motility is 5.6 times as high in farmland as in woody habitat. Species associated with forested habitats had greater motility than species associated with open field habitats, both in arable land and woody habitat. The meta-analysis did not identify consistent differences in motility at the species level, or between clusters of larger and smaller beetles. The results presented here provide a basis for calculating time-varying distribution patterns of carabids in farmland and woody habitat. The formulas for calculating motility can be used for other taxa.
2015 APR
WOS:000352714100010
QID: Q41448572
234-244
journalArticle
93
MARINE POLLUTION BULLETIN
DOI 10.1016/j.marpolbul.2015.02.011
1-2
Iho
Antti
Ribaudo
Marc
Hyytiainen
Kari
Water protection in the Baltic Sea and the Chesapeake Bay: Institutions, policies and efficiency
The Baltic Sea and the Chesapeake Bay share many characteristics. Both are shallow, brackish marine areas that suffer from eutrophication. Successful policies targeting point source pollution have lowered nutrient loads in both areas, but achieving the desired marine quality will require further abatement: efforts may be extended to more complicated and expensive pollution sources, notably agricultural nonpoint loads. Despite their ecological similarities, the two watersheds have different histories and institutional settings and have thus adopted different policies. Comparing and contrasting the policies reveal ways to improve the efficiency of each and ways to avoid the path of trial and error. No comparison of the parallel protection efforts, which involve expenditures of hundreds of millions of dollars annually, has been carried out to date. The present paper analyzes the policies applied in the two regions, distilling the results into six recommendations for future steps in preserving what are valuable sea areas. (C) 2015 Elsevier Ltd. All rights reserved.
2015 APR 15
WOS:000353733400023
QID: Q39031399
81-93
journalArticle
10
PLOS ONE
DOI 10.1371/journal.pone.0124807
4
Tagwireyi
Paradzayi
Sullivan
S. Mazeika P.
Riverine Landscape Patch Heterogeneity Drives Riparian Ant Assemblages in the Scioto River Basin, USA
Although the principles of landscape ecology are increasingly extended to include riverine landscapes, explicit applications are few. We investigated associations between patch heterogeneity and riparian ant assemblages at 12 riverine landscapes of the Scioto River, Ohio, USA, that represent urban/developed, agricultural, and mixed (primarily forested, but also wetland, grassland/fallow, and exurban) land-use settings. Using remotely-sensed and ground-collected data, we delineated riverine landscape patch types (crop, grass/herbaceous, gravel, lawn, mudflat, open water, shrub, swamp, and woody vegetation), computed patch metrics (area, density, edge, richness, and shape), and conducted coordinated sampling of surface-active Formicidae assemblages. Ant density and species richness was lower in agricultural riverine landscapes than at mixed or developed reaches (measured using S [total number of species], but not using Menhinick's Index [D-M]), whereas ant diversity (using the Berger-Park Index [D-BP]) was highest in agricultural reaches. We found no differences in ant density, richness, or diversity among internal riverine landscape patches. However, certain characteristics of patches influenced ant communities. Patch shape and density were significant predictors of richness (S: R-2 = 0.72; D-M: R-2 = 0.57). Patch area, edge, and shape emerged as important predictors of D-BP (R-2 = 0.62) whereas patch area, edge, and density were strongly related to ant density (R-2 = 0.65). Non-metric multidimensional scaling and analysis of similarities distinguished ant assemblage composition in grass and swamp patches from crop, gravel, lawn, and shrub as well as ant assemblages in woody vegetation patches from crop, lawn, and gravel (stress = 0.18, R-2 = 0.64). These findings lend insight into the utility of landscape ecology to river science by providing evidence that spatial habitat patterns within riverine landscapes can influence assemblage characteristics of riparian arthropods.
2015 APR 20
WOS:000353211700125
QID: Q35494587
journalArticle
14
MALARIA JOURNAL
DOI 10.1186/s12936-015-0689-0
Gryseels
Charlotte
Durnez
Lies
Gerrets
Rene
Uk
Sambunny
Suon
Sokha
Set
Srun
Phoeuk
Pisen
Sluydts
Vincent
Heng
Somony
Sochantha
Tho
Coosemans
Marc
Grietens
Koen Peeters
Re-imagining malaria: heterogeneity of human and mosquito behaviour in relation to residual malaria transmission in Cambodia
Background: In certain regions in Southeast Asia, where malaria is reduced to forested regions populated by ethnic minorities dependent on slash-and-burn agriculture, malaria vector populations have developed a propensity to feed early and outdoors, limiting the effectiveness of long-lasting insecticide-treated nets (LLIN) and indoor residual spraying (IRS). The interplay between heterogeneous human, as well as mosquito behaviour, radically challenges malaria control in such residual transmission contexts. This study examines human behavioural patterns in relation to the vector behaviour.Methods: The anthropological research used a sequential mixed-methods study design in which quantitative survey research methods were used to complement findings from qualitative ethnographic research. The qualitative research existed of in-depth interviews and participant observation. For the entomological research, indoor and outdoor human landing collections were performed. All research was conducted in selected villages in Ratanakiri province, Cambodia.Results: Variability in human behaviour resulted in variable exposure to outdoor and early biting vectors: (i) indigenous people were found to commute between farms in the forest, where malaria exposure is higher, and village homes; (ii) the indoor/outdoor biting distinction was less clear in forest housing often completely or partly open to the outside; (iii) reported sleeping times varied according to the context of economic activities, impacting on the proportion of infections that could be accounted for by early or nighttime biting; (iv) protection by LLINs may not be as high as self-reported survey data indicate, as observations showed around 40% (non-treated) market net use while (v) unprotected evening resting and deep forest activities impacted further on the suboptimal use of LLINs.Conclusions: The heterogeneity of human behaviour and the variation of vector densities and biting behaviours may lead to a considerable proportion of exposure occurring during times that people are assumed to be protected by the distributed LLINs. Additional efforts in improving LLIN use during times when people are resting in the evening and during the night might still have an impact on further reducing malaria transmission in Cambodia.
2015 APR 24
WOS:000353325500001
QID: Q35534432
journalArticle
187
ENVIRONMENTAL MONITORING AND ASSESSMENT
DOI 10.1007/s10661-015-4516-4
5
Singh
Raman Jeet
Ahlawat
I. P. S.
Energy budgeting and carbon footprint of transgenic cotton-wheat production system through peanut intercropping and FYM addition
Two of the most pressing sustainability issues are the depletion of fossil energy resources and the emission of atmospheric green house gases like carbon dioxide to the atmosphere. The aim of this study was to assess energy budgeting and carbon footprint in transgenic cotton-wheat cropping system through peanut intercropping with using 25-50 % substitution of recommended dose of nitrogen (RDN) of cotton through farmyard manure (FYM) along with 100 % RDN through urea and control (0 N). To quantify the residual effects of previous crops and their fertility levels, a succeeding crop of wheat was grown with varying rates of nitrogen, viz. 0, 50, 100, and 150 kg ha(-1). Cotton+ peanut-wheat cropping system recorded 21 % higher system productivity which ultimately helped to maintain higher net energy return (22 %), energy use efficiency (12 %), human energy profitability (3 %), energy productivity (7 %), carbon outputs (20 %), carbon efficiency (17 %), and 11 % lower carbon footprint over sole cotton-wheat cropping system. Peanut addition in cotton-wheat system increased the share of renewable energy inputs from 18 to 21 %. With substitution of 25 % RDN of cotton through FYM, share of renewable energy resources increased in the range of 21 % which resulted into higher system productivity (4 %), net energy return (5 %), energy ratio (6 %), human energy profitability (74 %), energy productivity (6 %), energy profitability (5 %), and 5 % lower carbon footprint over no substitution. The highest carbon footprint (0.201) was recorded under control followed by 50 % substitution of RDN through FYM (0.189). With each successive increase in N dose up to 150 kg N ha(-1) to wheat, energy productivity significantly reduced and share of renewable energy inputs decreased from 25 to 13 %. Application of 100 kg N ha(-1) to wheat maintained the highest grain yield (3.71 t ha(-1)), net energy return (105,516 MJ ha(-1)), and human energy profitability (223.4) over other N doses applied to wheat. Application of 50 kg N ha(-1) to wheat maintained the least carbon footprint (0.091) followed by 100 kg N ha(-1) (0.100). Our study indicates that system productivity as well as energy and carbon use efficiencies of transgenic cotton-wheat production system can be enhanced by inclusion of peanut as an intercrop in cotton and substitution of 25 % RDN of cotton through FYM, as well as application of 100 kg N ha(-1) to succeeding wheat crop.
2015 MAY
WOS:000355607100026
QID: Q41032803
journalArticle
22
ENVIRONMENTAL SCIENCE AND POLLUTION RESEARCH
DOI 10.1007/s11356-014-3862-z
9
Yang
Lanqin
Huang
Biao
Mao
Mingcui
Yao
Lipeng
Hickethier
Martina
Hu
Wenyou
Trace metal accumulation in soil and their phytoavailability as affected by greenhouse types in north China
Long-term heavy organic fertilizer application has linked greenhouse vegetable production (GVP) with trace metal contamination in north China. Given that trace metals release from fertilizers and their availability may be affected by discrepant environmental conditions, especially temperature under different greenhouses, this study investigated Cd, Cu, Pb, and Zn accumulation and contamination extent in soil as well as their phytoavailability under two major greenhouses in Tongshan, north China, namely solar greenhouse (SG) and round-arched plastic greenhouse (RAPG), to evaluate their presumed difference. The results showed significant Cd, Cu, Pb, and Zn accumulation in GVP soil by comparing with those in open-field soil, but their accumulation extent and rates were generally greater in SG than those in RAPG. This may be related to more release of trace metals to soil due to the acceleration of decomposition and humification process of organic fertilizers under higher soil temperature in SG relative to that in RAPG. Overall, soil in both greenhouses was generally less polluted or moderately polluted by the study metals. Similarly, decreased soil pH and elevated soil available metals in SG caused higher trace metals in leaf vegetables in SG than those in RAPG, although there was no obvious risk via vegetable consumption under both greenhouses. Lower soil pH may be predominantly ascribed to more intensive farming practices in SG while elevated soil available metals may be attributed to more release of dissolved organic matter-metal complexes from soil under higher temperature in SG. The data provided in this study may assist in developing reasonable and sustainable fertilization strategies to abate trace metal contamination in both greenhouses.
2015 MAY
WOS:000353046600027
QID: Q42694669
6679-6686
journalArticle
17
AAPS JOURNAL
DOI 10.1208/s12248-015-9722-z
3
Done
Hansa Y.
Venkatesan
Arjun K.
Halden
Rolf U.
Does the Recent Growth of Aquaculture Create Antibiotic Resistance Threats Different from those Associated with Land Animal Production in Agriculture?
Important antibiotics in human medicine have been used for many decades in animal agriculture for growth promotion and disease treatment. Several publications have linked antibiotic resistance development and spread with animal production. Aquaculture, the newest and fastest growing food production sector, may promote similar or new resistance mechanisms. This review of 650+ papers from diverse sources examines parallels and differences between land-based agriculture of swine, beef, and poultry and aquaculture. Among three key findings was, first, that of 51 antibiotics commonly used in aquaculture and agriculture, 39 (or 76%) are also of importance in human medicine; furthermore, six classes of antibiotics commonly used in both agriculture and aquaculture are also included on the World Health Organization's (WHO) list of critically important/highly important/important antimicrobials. Second, various zoonotic pathogens isolated from meat and seafood were observed to feature resistance to multiple antibiotics on the WHO list, irrespective of their origin in either agriculture or aquaculture. Third, the data show that resistant bacteria isolated from both aquaculture and agriculture share the same resistance mechanisms, indicating that aquaculture is contributing to the same resistance issues established by terrestrial agriculture. More transparency in data collection and reporting is needed so the risks and benefits of antibiotic usage can be adequately assessed.
2015 MAY
WOS:000353560700003
QID: Q35529139
513-524
journalArticle
10
PLOS ONE
DOI 10.1371/journal.pone.0126634
5
Jacob
Sherry R.
Tyagi
Vandana
Agrawal
Anuradha
Chakrabarty
Shyamal K.
Tyagi
Rishi K.
Indian Plant Germplasm on the Global Platter: An Analysis
Food security is a global concern amongst scientists, researchers and policy makers. No country is self-sufficient to address food security issues independently as almost all countries are inter-dependent for availability of plant genetic resources (PGR) in their national crop improvement programmes. Consultative Group of International Agricultural Research (CGIAR; in short CG) centres play an important role in conserving and distributing PGR through their genebanks. CG genebanks assembled the germplasm through collecting missions and acquisition the same from national genebanks of other countries. Using the Genesys Global Portal on Plant Genetic Resources, the World Information and Early Warning System (WIEWS) on Plant Genetic Resources for Food and Agriculture and other relevant databases, we analysed the conservation status of Indian-origin PGR accessions (both cultivated and wild forms possessed by India) in CG genebanks and other national genebanks, including the United States Department of Agriculture (USDA) genebanks, which can be considered as an indicator of Indian contribution to the global germplasm collection. A total of 28,027,770 accessions are being conserved world-wide by 446 organizations represented in Genesys; of these, 3.78% (100,607) are Indian-origin accessions. Similarly, 62,920 Indian-origin accessions (8.73%) have been conserved in CG genebanks which are accessible to the global research community for utilization in their respective crop improvement programmes. A total of 60 genebanks including 11 CG genebanks have deposited 824,625 accessions of PGR in the Svalbard Global Seed Vault (SGSV) as safety duplicates; the average number of accessions deposited by each genebank is 13,744, and amongst them there are 66,339 Indian-origin accessions. In principle, India has contributed 4.85 times the number of germplasm accessions to SGSV, in comparison to the mean value (13,744) of any individual genebank including CG genebanks. More importantly, about 50% of the Indian-origin accessions deposited in SGSV are traditional varieties or landraces with defined traits which form the backbone of any crop gene pool. This paper is also attempting to correlate the global data on Indian-origin germplasm with the national germplasm export profile. The analysis from this paper is discussed with the perspective of possible implications in the access and benefit sharing regime of both the International Treaty on Plant Genetic Resources for Food and Agriculture and the newly enforced Nagoya Protocol under the Convention on Biological Diversity.
2015 MAY 14
WOS:000354545600069
QID: Q35606835
journalArticle
10
PLOS ONE
DOI 10.1371/journal.pone.0123505
5
Bollfrass
Alexander
Shaver
Andrew
The Effects of Temperature on Political Violence: Global Evidence at the Subnational Level
A number of studies have demonstrated an empirical relationship between higher ambient temperatures and substate violence, which have been extrapolated to make predictions about the security implications of climate change. This literature rests on the untested assumption that the mechanism behind the temperature-conflict link is that disruption of agricultural production provokes local violence. Using a subnational-level dataset, this paper demonstrates that the relationship: (1) obtains globally, (2) exists at the substate levelprovinces that experience positive temperature deviations see increased conflict; and (3) occurs even in regions without significant agricultural production. Diminished local farm output resulting from elevated temperatures is unlikely to account for the entire increase in substate violence. The findings encourage future research to identify additional mechanisms, including the possibility that a substantial portion of the variation is brought about by the well-documented direct effects of temperature on individuals' propensity for violence or through macroeconomic mechanisms such as food price shocks.
2015 MAY 20
WOS:000354921400011
QID: Q35636053
journalArticle
36
FOOD AND NUTRITION BULLETIN
DOI 10.1177/0379572115587273
2
Lachat
Carl
Nago
Eunice
Ka
Abdoulaye
Vermeylen
Harm
Fanzo
Jessica
Mahy
Lina
Wuestefeld
Marzella
Kolsteren
Patrick
Landscape Analysis of Nutrition-sensitive Agriculture Policy Development in Senegal
Background: Unlocking the agricultural potential of Africa offers a genuine opportunity to address malnutrition and drive development of the continent.Objective: Using Senegal as a case study, to identify gaps and opportunities to strengthen agricultural policies with nutrition-sensitive approaches.Methods: We carried out a systematic analysis of 13 policy documents that related to food production, agriculture, food security, or nutrition. Next, we collected data during a participatory analysis with 32 national stakeholders and in-depth interviews with 15 national experts of technical directorates of the different ministries that deal with agriculture and food production.Results: The current agricultural context has various elements that are considered to enhance its nutrition sensitivity. On average, 8.3 of the 17 Food and Agriculture Organization guiding principles for agriculture programming for nutrition were included in the policies reviewed. Ensuring food security and increasing dietary diversity were considered to be the principal objectives of agricultural policies. Although there was considerable agreement that agriculture can contribute to nutrition, current agricultural programs generally do not target communities on the basis of their nutritional vulnerability. Agricultural programs were reported to have specific components to target female beneficiaries but were generally not used as delivery platforms for nutritional interventions.Conclusions: The findings of this study indicate the need for a coherent policy environment across the food system that aligns recommendations at the national level with local action on the ground. In addition, specific activities are needed to develop a shared understanding of nutrition and public health nutrition within the agricultural community in Senegal.
2015 JUN
WOS:000361184700006
QID: Q39155851
154-166
journalArticle
518
SCIENCE OF THE TOTAL ENVIRONMENT
DOI 10.1016/j.scitotenv.2015.01.113
Zong
Zheng
Chen
Yingjun
Tian
Chongguo
Fang
Yin
Wang
Xiaoping
Huang
Guopei
Zhang
Fan
Li
Jun
Zhang
Gan
Radiocarbon-based impact assessment of open biomass burning on regional carbonaceous aerosols in North China
Samples of total suspended particulates (TSPs) and fine particulate matter (PM2.5) were collected from 29th May to 1st July, 2013 at a regional background site in Bohai Rim, North China. Mass concentrations of particulate matter and carbonaceous species showed a total of 50% and 97% of the measured TSP and PM2.5 levels exceeded the first grade national standard of China, respectively. Daily concentrations of organic carbon (OC) and elemental carbon (EC) were detected 7.3 and 2.5 mu g m (3) in TSP and 5.2 and 2.0 mu g m (3) in PM2.5, which accounted 5.8% and 2.0% of TSP while 5.6% and 2.2% for PM2.5, respectively. The concentrations of OC, EC, TSP and PM2.5 were observed higher in the day time than those in the night time. The observations were associated with the emission variations from anthropogenic activities. Two merged samples representing from south and north source areas were selected for radiocarbon analysis. The radiocarbon measurements showed 74% of water-insoluble OC (WINSOC) and 59% of EC in PM2.5 derived from biomass burning and biogenic sources when the air masses were from south region, and 63% and 48% for the air masses from north, respectively. Combined with backward trajectories and daily burned area, open burning of agricultural wastes was found to be predominating, which was confirmed by the potential source contribution function (PSCF). (C) 2015 Elsevier B.V. All rights reserved.
2015 JUN 15
WOS:000353225700001
QID: Q41278390
1-7
journalArticle
12
JOURNAL OF THE ROYAL SOCIETY INTERFACE
DOI 10.1098/rsif.2015.0210
107
Jose Ibanez
Juan
Ortega
David
Campos
Daniel
Khalidi
Lamya
Mendez
Vicenc
Testing complex networks of interaction at the onset of the Near Eastern Neolithic using modelling of obsidian exchange
In this paper, we explore the conditions that led to the origins and development of the Near Eastern Neolithic using mathematical modelling of obsidian exchange. The analysis presented expands on previous research, which established that the down-the-line model could not explain long-distance obsidian distribution across the Near East during this period. Drawing from outcomes of new simulations and their comparison with archaeological data, we provide results that illuminate the presence of complex networks of interaction among the earliest farming societies. We explore a network prototype of obsidian exchange with distant links which replicates the long-distance movement of ideas, goods and people during the Early Neolithic. Our results support the idea that during the first (Pre-Pottery Neolithic A) and second (Pre-Pottery Neolithic B) phases of the Early Neolithic, the complexity of obsidian exchange networks gradually increased. We propose then a refined model (the optimized distant link model) whereby long-distance exchange was largely operated by certain interconnected villages, resulting in the appearance of a relatively homogeneous Neolithic cultural sphere. We hypothesize that the appearance of complex interaction and exchange networks reduced risks of isolation caused by restricted mobility as groups settled and argue that these networks partially triggered and were crucial for the success of the Neolithic Revolution. Communities became highly dynamic through the sharing of experiences and objects, while the networks that developed acted as a repository of innovations, limiting the risk of involution.
2015 JUN 6
WOS:000355744900013
QID: Q30459627
journalArticle
112
PROCEEDINGS OF THE NATIONAL ACADEMY OF SCIENCES OF THE UNITED STATES OF AMERICA
DOI 10.1073/pnas.1423674112
24
Crowder
David W.
Reganold
John P.
Financial competitiveness of organic agriculture on a global scale
To promote global food and ecosystem security, several innovative farming systems have been identified that better balance multiple sustainability goals. The most rapidly growing and contentious of these systems is organic agriculture. Whether organic agriculture can continue to expand will likely be determined by whether it is economically competitive with conventional agriculture. Here, we examined the financial performance of organic and conventional agriculture by conducting a meta-analysis of a global dataset spanning 55 crops grown on five continents. When organic premiums were not applied, benefit/cost ratios (-8 to -7%) and net present values (-27 to -23%) of organic agriculture were significantly lower than conventional agriculture. However, when actual premiums were applied, organic agriculture was significantly more profitable (22-35%) and had higher benefit/cost ratios (20-24%) than conventional agriculture. Although premiums were 29-32%, breakeven premiums necessary for organic profits to match conventional profits were only 5-7%, even with organic yields being 10-18% lower. Total costs were not significantly different, but labor costs were significantly higher (7-13%) with organic farming practices. Studies in our meta-analysis accounted for neither environmental costs (negative externalities) nor ecosystem services from good farming practices, which likely favor organic agriculture. With only 1% of the global agricultural land in organic production, our findings suggest that organic agriculture can continue to expand even if premiums decline. Furthermore, with their multiple sustainability benefits, organic farming systems can contribute a larger share in feeding the world.
2015 JUN 16
WOS:000356251800071
QID: Q34478890
7611-7616
journalArticle
187
ENVIRONMENTAL MONITORING AND ASSESSMENT
DOI 10.1007/s10661-015-4691-3
7
Nguyen
On Van
Kawamura
Kensuke
Dung Phan Trong
Gong
Zhe
Suwandana
Endan
Temporal change and its spatial variety on land surface temperature and land use changes in the Red River Delta, Vietnam, using MODIS time-series imagery
Temporal changes in the land surface temperature (LST) in urbanization areas are important for studying an urban heat island (UHI) and regional climate change. This study examined the LST trends under different land use categories in the Red River Delta, Vietnam, using the Moderate Resolution Imaging Spectroradiometer (MODIS) LST product (MOD11A2) and land cover type product (MCD12Q1) for 11 years (2002-2012). Smoothened time-series MODIS LST data were reconstructed by the Harmonic Analysis of Time Series (HANTS) algorithm. The reconstructed LST (maximum and minimum temperatures) was assessed using the hourly air temperature dataset in two landbased meteorological stations provided by the National Climatic Data Center (NCDC). Significant correlation was obtained between MODIS LST and the air temperature for the daytime (R-2=0.73, root mean square error [RMSE]=1.66 degrees C) and night time (R-2=0.84, RMSE=1.79 degrees C). Statistical analysis also showed that LST trends vary strongly depending on the land cover type. Forest, wetland, and cropland had a slight tendency to decline, whereas cropland and urban had sharper increases. In urbanized areas, these increasing trends are even more obvious. This is undeniable evidence of the negative impact of urbanization on a surface urban heat island (SUHI) and global warming.
2015 JUL
WOS:000357340500072
QID: Q30976842
journalArticle
10
PLOS ONE
DOI 10.1371/journal.pone.0130038
6
Naganandhini
S.
Kennedy
Z. John
Uyttendaele
M.
Balachandar
D.
Persistence of Pathogenic and Non-Pathogenic Escherichia coli Strains in Various Tropical Agricultural Soils of India
The persistence of Shiga-like toxin producing Escherichia coli (STEC) strains in the agricultural soil creates serious threat to human health through fresh vegetables growing on them. However, the survival of STEC strains in Indian tropical soils is not yet understood thoroughly. Additionally how the survival of STEC strain in soil diverges with non-pathogenic and genetically modified Escherichia coli strains is also not yet assessed. Hence in the present study, the survival pattern of STEC strain (O157-TNAU) was compared with non-pathogenic (MTCC433) and genetically modified (DH5 alpha) strains on different tropical agricultural soils and on a vegetable growing medium, cocopeat under controlled condition. The survival pattern clearly discriminated DH5 alpha from MTCC433 and O157-TNAU, which had shorter life (40 days) than those compared (60 days). Similarly, among the soils assessed, the red laterite and tropical latosol supported longer survival of O157-TNAU and MTCC433 as compared to wetland and black cotton soils. In cocopeat, O157 recorded significantly longer survival than other two strains. The survival data were successfully analyzed using Double-Weibull model and the modeling parameters were correlated with soil physico-chemical and biological properties using principal component analysis (PCA). The PCA of all the three strains revealed that pH, microbial biomass carbon, dehydrogenase activity and available N and P contents of the soil decided the survival of Escherichia coli strains in those soils and cocopeat. The present research work suggests that the survival of O157 differs in tropical Indian soils due to varied physico-chemical and biological properties and the survival is much shorter than those reported in temperate soils. As the survival pattern of non-pathogenic strain, MTCC433 is similar to O157-TNAU in tropical soils, the former can be used as safe model organism for open field studies.
2015 JUN 23
WOS:000356901900026
QID: Q28548608
journalArticle
69
ARCHIVES OF ENVIRONMENTAL CONTAMINATION AND TOXICOLOGY
DOI 10.1007/s00244-015-0158-3
1
Moore
Matthew T.
Pierce
Jon R.
Farris
Jerry L.
Water-Quality Analysis of an Intensively Used On-Farm Storage Reservoir in the Northeast Arkansas Delta
The use of farm reservoirs for supplemental irrigation is gaining popularity in the Mississippi Alluvial Plain (MAP). Due to depletions of several aquifers, many counties within the MAP have been designated as critical-use groundwater areas. To help alleviate stress on these aquifers, many farmers are implementing storage reservoirs for economic and conservation benefits. When used in tandem with a tailwater recovery system, reservoirs have the potential to trap and transform potential contaminants (e.g., nutrients and pesticides) rather than releasing them through drainage into receiving systems such as lakes, rivers, and streams. Roberts Reservoir is an intensively used, 49-ha on-farm storage reservoir located in Poinsett County, Arkansas. Water-quality analyses and toxicity assessments of the reservoir and surrounding ditches indicated a stable water-quality environment with no observed toxicity present in collected samples. Results of this study suggest that water released into a local receiving stream poses no contaminant risk and could be maintained for irrigation purposes, thereby decreasing the need for additional groundwater depletion.
2015 JUL
WOS:000355685600010
QID: Q41013851
89-94
journalArticle
187
ENVIRONMENTAL MONITORING AND ASSESSMENT
DOI 10.1007/s10661-015-4671-7
7
Kindu
Mengistie
Schneider
Thomas
Teketay
Demel
Knoke
Thomas
Drivers of land use/land cover changes in Munessa-Shashemene landscape of the south-central highlands of Ethiopia
Understanding drivers of changes in land use/land cover (LULC) is essential for modeling future dynamics or development of management strategies to ameliorate or prevent further decline of natural resources. In this study, an attempt has been made to identify the main drivers behind the LULC changes that had occurred in the past four decades in Munessa-Shashemene landscape of the south-central highlands of Ethiopia. The datasets required for the study were generated through both primary and secondary sources. Combination of techniques, including descriptive statistics, GIS-based processing, and regression analyses were employed for data analyses. Changes triggered by the interplay of more than 12 drivers were identified related to social, economic, environmental, policy/institutional, and technological factors. Specifically, population growth, expansion of cultivated lands and settlements, livestock ranching, cutting of woody species for fuelwood, and charcoal making were the top six important drivers of LULC change as viewed by the local people and confirmed by quantitative analyses. Differences in respondents' perceptions related to environmental (i.e., location specific) and socioeconomic determinants (e.g., age and literacy) about drivers were statically significant (P = 0.001). LULC changes were also determined by distances to major drivers (e. g., the further a pixel is from the road, the less likelihood of changes) as shown by the landscape level analyses. Further studies are suggested targeting these drivers to explore the consequences and future options and formulate intervention strategies for sustainable development in the studied landscape and elsewhere with similar geographic settings.
2015 JUL
WOS:000357340500060
QID: Q38993714
journalArticle
187
ENVIRONMENTAL MONITORING AND ASSESSMENT
DOI 10.1007/s10661-015-4700-6
7
Filep
Tibor
Draskovits
Eszter
Szabo
Jozsef
Koos
Sandor
Laszlo
Peter
Szalai
Zoltan
The dissolved organic matter as a potential soil quality indicator in arable soils of Hungary
Although several authors have suggested that the labile fraction of soils could be a potential soil quality indicator, the possibilities and limitations of using the dissolved organic matter (DOM) fraction for this purpose have not yet been investigated. The objective of this study was to evaluate the hypothesis that DOM is an adequate indicator of soil quality. To test this, the soil quality indices (SQI) of 190 arable soils from a Hungarian dataset were estimated, and these values were compared to DOM parameters (DOC and SUVA254). A clear difference in soil quality was found between the soil types, with low soil quality for arenosols (average SQI 0.5) and significantly higher values for gleysols, vertisols, regosols, solonetzes and chernozems. The SQI-DOC relationship could be described by non-linear regression, while a linear connection was observed between SQI and SUVA. The regression equations obtained for the dataset showed only one relatively weak significant correlation between the variables, for DOC (R-2 = 0.157***; n = 190), while nonsignificant relationships were found for the DOC and SUVA(254) values. However, an envelope curve operated with the datasets showed the robust potential of DOC to indicate soil quality changes, with a high R-2 value for the envelope curve regression equation. The limitations to using the DOM fraction of soils as a quality indicator are due to the contradictory processes which take place in soils in many cases.
2015 JUL
WOS:000357340500087
QID: Q50890195
journalArticle
15
RURAL AND REMOTE HEALTH
3
Arnautovska
U.
McPhedran
S.
De Leo
D.
Differences in characteristics between suicide cases of farm managers compared to those of farm labourers in Queensland, Australia
Introduction: Farmers constitute an occupation group at a heightened suicide risk compared to the general population. To date, research has tried to explain this peculiarity by identifying suicide risk factors that are common to the whole of the farming population. There are, however, indications that risk factors may be different for different sub-populations of farmers, such as younger/older farmers or farm managers/farm labourers. This study compared the characteristics of suicides by farm managers and farm labourers, while controlling for the effect of age.Methods: A review of two datasets, the Queensland Suicide Register and the National Coroners Information System, was conducted in which a total of 78 cases of farm managers and 69 cases of farm labourers were identified as a suicide during 20002009, Queensland, Australia. The main outcome measures included various demographic characteristics, circumstances related to death, health and mental health variables, and history of stressful life events.Results: The two groups differed in marital status, living arrangements, ethnicity, physical and mental illness, alcohol and drug abuse, contact with a health professional prior to death, and specific life events such as relationship breakdown and recent/pending unemployment. The majority of these differences were not statistically significant once age was accounted for. However, differences in psychiatric variables and experience of a recent/pending unemployment remained significant.Conclusions: This study contributes towards better understanding of suicide among farmers in different job positions, and highlights the need for tailored suicide prevention initiatives that consider a combination of age-and job-specific suicide risk and protective factors among farmers.
2015 JUL-SEP
WOS:000365601800024
QID: Q38590437
journalArticle
10
PLOS ONE
DOI 10.1371/journal.pone.0134443
7
Heim
Olga
Treitler
Julia T.
Tschapka
Marco
Knoernschild
Mirjam
Jung
Kirsten
The Importance of Landscape Elements for Bat Activity and Species Richness in Agricultural Areas
Landscape heterogeneity is regarded as a key factor for maintaining biodiversity and ecosystem function in production landscapes. We investigated whether grassland sites at close vicinity to forested areas are more frequently used by bats. Considering that bats are important consumers of herbivorous insects, including agricultural pest, this is important for sustainable land management. Bat activity and species richness were assessed using repeated monitoring from May to September in 2010 with acoustic monitoring surveys on 50 grassland sites in the Biosphere Reserve Schorfheide-Chorin (North-East Germany). Using spatial analysis (GIS), we measured the closest distance of each grassland site to potentially connecting landscape elements (e.g., trees, linear vegetation, groves, running and standing water). In addition, we assessed the distance to and the percent land cover of forest remnants and urban areas in a 200 m buffer around the recording sites to address differences in the local landscape setting. Species richness and bat activity increased significantly with higher forest land cover in the 200 m buffer and at smaller distance to forested areas. Moreover, species richness increased in proximity to tree groves. Larger amount of forest land cover and smaller distance to forest also resulted in a higher activity of bats on grassland sites in the beginning of the year during May, June and July. Landscape elements near grassland sites also influenced species composition of bats and species richness of functional groups (open, edge and narrow space foragers). Our results highlight the importance of forested areas, and suggest that agricultural grasslands that are closer to forest remnants might be better buffered against outbreaks of agricultural pest insects due to higher species richness and higher bat activity. Furthermore, our data reveals that even for highly mobile species such as bats, a very dense network of connecting elements within the landscape is beneficial to promote activity in open areas and thus assure vital ecosystem function in agricultural landscapes.
2015 JUL 31
WOS:000358838400119
QID: Q30405281
journalArticle
59
INTERNATIONAL JOURNAL OF BIOMETEOROLOGY
DOI 10.1007/s00484-014-0920-7
8
Fernandez
M. D.
Lopez
J. C.
Baeza
E.
Cespedes
A.
Meca
D. E.
Bailey
B.
Generation and evaluation of typical meteorological year datasets for greenhouse and external conditions on the Mediterranean coast
A typical meteorological year (TMY) represents the typical meteorological conditions over many years but still contains the short term fluctuations which are absent from long-term averaged data. Meteorological data were measured at the Experimental Station of Cajamar 'Las Palmerillas' (Cajamar Foundation) in Almeria, Spain, over 19 years at the meteorological station and in a reference greenhouse which is typical of those used in the region. The two sets of measurements were subjected to quality control analysis and then used to create TMY datasets using three different methodologies proposed in the literature. Three TMY datasets were generated for the external conditions and two for the greenhouse. They were assessed by using each as input to seven horticultural models and comparing the model results with those obtained by experiment in practical trials. In addition, the models were used with the meteorological data recorded during the trials. A scoring system was used to identify the best performing TMY in each application and then rank them in overall performance. The best methodology was that of Argiriou for both greenhouse and external conditions. The average relative errors between the seasonal values estimated using the 19-year dataset and those using the Argiriou greenhouse TMY were 2.2 % (reference evapotranspiration), -0.45 % (pepper crop transpiration), 3.4 % (pepper crop nitrogen uptake) and 0.8 % (green bean yield). The values obtained using the Argiriou external TMY were 1.8 % (greenhouse reference evapotranspiration), 0.6%(external reference evapotranspiration), 4.7 % (greenhouse heat requirement) and 0.9 % (loquat harvest date). Using the models with the 19 individual years in the historical dataset showed that the year to year weather variability gave results which differed from the average values by +/- 15 %. By comparison with results from other greenhouses it was shown that the greenhouse TMY is applicable to greenhouses which have a solar radiation transmission of approximately 65 % and rely on manual control of ventilation which constitute the majority in the south-east of Spain and in most Mediterranean greenhouse areas.
2015 AUG
WOS:000359535300013
QID: Q50446920
1067-1081
journalArticle
5
SCIENTIFIC REPORTS
DOI 10.1038/srep12574
Budge
G. E.
Garthwaite
D.
Crowe
A.
Boatman
N. D.
Delaplane
K. S.
Brown
M. A.
Thygesen
H. H.
Pietravalle
S.
Evidence for pollinator cost and farming benefits of neonicotinoid seed coatings on oilseed rape
Chronic exposure to neonicotinoid insecticides has been linked to reduced survival of pollinating insects at both the individual and colony level, but so far only experimentally. Analyses of large-scale datasets to investigate the real-world links between the use of neonicotinoids and pollinator mortality are lacking. Moreover, the impacts of neonicotinoid seed coatings in reducing subsequent applications of foliar insecticide sprays and increasing crop yield are not known, despite the supposed benefits of this practice driving widespread use. Here, we combine large-scale pesticide usage and yield observations from oilseed rape with those detailing honey bee colony losses over an 11 year period, and reveal a correlation between honey bee colony losses and national-scale imidacloprid (a neonicotinoid) usage patterns across England and Wales. We also provide the first evidence that farmers who use neonicotinoid seed coatings reduce the number of subsequent applications of foliar insecticide sprays and may derive an economic return. Our results inform the societal discussion on the pollinator costs and farming benefits of prophylactic neonicotinoid usage on a mass flowering crop.
2015 AUG 20
WOS:000359769000001
QID: Q34489435
journalArticle
15
BMC INFECTIOUS DISEASES
DOI 10.1186/s12879-015-1099-1
Shabani
Sasita S.
Ezekiel
Mangi J.
Mohamed
Mohamed
Moshiro
Candida S.
Knowledge, attitudes and practices on Rift Valley fever among agro pastoral communities in Kongwa and Kilombero districts, Tanzania
Background: Rift valley fever (RVF) is a re-emerging viral vector-borne disease with rapid global socio-economic impact. A large RVF outbreak occurred in Tanzania in 2007 and affected more than half of the regions with high (47 %) case fatality rate. Little is known about RVF and its dynamics. A cross sectional study was conducted to assess the knowledge, attitudes and practices regarding RVF in Kongwa and Kilombero districts, Tanzania.Methods: We conducted a cross sectional survey among a randomly selected sample of individuals in 2011. We administered questionnaires to collect data on demographic characteristics, knowledge on symptoms, mode of transmission, prevention, attitudes and health seeking practices.Results: A total of 463 community members participated in this study. The mean (+/- SD) age was 39.8 +/- 14.4 years and 238 (51.4 %) were female. Majority of respondents had heard of RVF. However, only 8.8 % knew that mosquitoes were transmitting vectors. Male respondents were more likely to have greater knowledge about RVF. A small proportion mentioned clinical signs and symptoms of RVF in animals while 73.7 % mentioned unhealthy practices related to handling and consumption of dead animals. Thorough boiling of milk and cooking of meat were commonly mentioned as preventive measures for RVF. Majority (74.6 %) sought care for febrile illness at health facilities. Few (24.3 %) reported the use of protective gears to handle dead/sick animal while 15.5 % were consuming dead animals.Conclusion: Our study highlights the need to address the limited knowledge about RVF and promoting appropriate and timely health seeking practices. Rift valley fever outbreaks can be effectively managed with collaborative efforts of lay and professional communities with a shared perception that it poses a serious threat to public and animal health. The fact that this study was conducted in "high risk transmission areas" warrants further inquiry in other geographic regions with relatively low risk of RVF.
2015 AUG 21
WOS:000359764700007
QID: Q28608583
journalArticle
10
PLOS ONE
DOI 10.1371/journal.pone.0137911
9
Stan
Kayla
Sanchez-Azofeifa
Arturo
Espirito-Santo
Mario
Portillo-Quintero
Carlos
Simulating Deforestation in Minas Gerais, Brazil, under Changing Government Policies and Socioeconomic Conditions
Agricultural expansion is causing deforestation in Minas Gerais, Brazil, converting savanna and tropical dry forest to farmland, and in 2012, Brazil's Forest Code was revised with the government reducing deforestation restrictions. Understanding the effects of policy change on rates and locations of natural ecosystem loss is imperative. In this paper, deforestation in Minas Gerais was simulated annually until 2020 using Dinamica Environment for Geoprocessing Objects (Dinamica EGO). This system is a state-of-the-art land use and cover change (LUCC) model which incorporates government policy, landscape maps, and other biophysical and anthropogenic datasets. Three studied scenarios: (i) business as usual, (ii) increased deforestation, and (iii) decreased deforestation showed more transition to agriculture from shrubland compared to forests, and consistent locations for most deforestation. The probability of conversion to agriculture is strongly tied to areas with the smallest patches of original biome remaining. Increases in agricultural revenue are projected to continue with a loss of 25% of the remaining Cerrado land in the next decade if profit is maximized. The addition of biodiversity value as a tax on land sale prices, estimated at over $750,000,000 USD using the cost of extracting and maintaining current species ex-situ, can save more than 1 million hectares of shrubland with minimal effects on the economy of the State of Minas Gerais. With environmental policy determining rates of deforestation and economics driving the location of land clearing, site-specific protection or market accounting of externalities is needed to balance economic development and conservation.
2015 SEP 15
WOS:000361604400037
QID: Q35775801
journalArticle
21
GLOBAL CHANGE BIOLOGY
DOI 10.1111/gcb.12909
9
Peron
Guillaume
Altwegg
Res
Twenty-five years of change in southern African passerine diversity: nonclimatic factors of change
We analysed more than 25 years of change in passerine bird distribution in South Africa, Swaziland and Lesotho, to show that species distributions can be influenced by processes that are at least in part independent of the local strength and direction of climate change: land use and ecological succession. We used occupancy models that separate species' detection from species' occupancy probability, fitted to citizen science data from both phases of the Southern African Bird Atlas Project (1987-1996 and 2007-2013). Temporal trends in species' occupancy probability were interpreted in terms of local extinction/colonization, and temporal trends in detection probability were interpreted in terms of change in abundance. We found for the first time at this scale that, as predicted in the context of bush encroachment, closed-savannah specialists increased where open-savannah specialists decreased. In addition, the trend in the abundance of species a priori thought to be favoured by agricultural conversion was negatively correlated with human population density, which is in line with hypotheses explaining the decline in farmland birds in the Northern Hemisphere. In addition to climate, vegetation cover and the intensity and time since agricultural conversion constitute important predictors of biodiversity changes in the region. Their inclusion will improve the reliability of predictive models of species distribution.
2015 SEP
WOS:000360998400015
QID: Q30899067
3347-3355
journalArticle
278
JOURNAL OF ENVIRONMENTAL MANAGEMENT
DOI 10.1016/j.jenvman.2020.111559
Li
Jiaguang
Tooth
Stephen
Zhang
Kun
Zhao
Yang
Visualisation of flooding along an unvegetated, ephemeral river using Google Earth Engine: Implications for assessment of channel-floodplain dynamics in a time of rapid environmental change
Given rapid environmental change, the development of new, data-driven, interdisciplinary approaches is essential for improving assessment and management of river systems, especially with respect to flooding. In the world's extensive drylands, difficulties in obtaining field observations of major hydrological events mean that remote sensing techniques are commonly used to map river floods and assess flood impacts. Such techniques, however, are dependent on available cloud-free imagery during or immediately after peak discharge, and single images may omit important flood-related hydrogeomorphological events. Here, we combine multiple Landsat images from Google Earth Engine (GEE) with precipitation datasets and high-resolution (<0.65 m) satellite imagery to visualise flooding and assess the associated channel-floodplain dynamics along a 25 km reach of the unvegetated, ephemeral Rio Colorado, Bolivia. After cloud and shadow removal, Landsat surface reflectance data were used to calculate the Modified Normalized Difference Water Index (MNDWI) and map flood extents and patterns. From 2004 through 2016, annual flooding area along the narrow (<30 m), shallow (<1.7 m), finegrained (dominantly silt/clay) channels was positively correlated (R-2 = 0.83) with 2-day maximum precipitation totals. Rapid meander bend migration, bank erosion, and frequent overbank flooding was associated with formation of crevasse channels, splays, and headward-eroding channels, and with avulsion (shifting of flow from one channel to another). These processes demonstrate ongoing, widespread channel-floodplain dynamics despite low stream powers and cohesive sediments. Application of our study approaches to other dryland rivers will help generate comparative data on the controls, rates, patterns and timescales of channel-floodplain dynamics under scenarios of climate change and direct human impacts, with potential implications for improved river management.
2021 JAN 15
WOS:000600292400009
QID: Q101156781
journalArticle
11
SCIENTIFIC REPORTS
DOI 10.1038/s41598-021-81270-z
1
de Albuquerque Nunes
Pedro Arthur
Laca
Emilio Andres
de Faccio Carvalho
Paulo Cesar
Li
Meng
de Souza Filho
William
Kunrath
Taise Robinson
Martins
Amanda Posselt
Gaudin
Amelie
Livestock integration into soybean systems improves long-term system stability and profits without compromising crop yields
Climate models project greater weather variability over the coming decades. High yielding systems that can maintain stable crop yields under variable environmental scenarios are critical to enhance food security. However, the effect of adding a trophic level (i.e. herbivores) on the long-term stability of agricultural systems is not well understood. We used a 16-year dataset from an integrated soybean-beef cattle experiment to measure the impacts of grazing on the stability of key crop, pasture, animal and whole-system outcomes. Treatments consisted of four grazing intensities (10, 20, 30 and 40 cm sward height) on mixed black oat (Avena strigosa) and Italian ryegrass (Lolium multiflorum) pastures and an ungrazed control. Stability of both human-digestible protein production and profitability increased at moderate to light grazing intensities, while over-intensification or absence of grazing decreased system stability. Grazing did not affect subsequent soybean yields but reduced the chance of crop failure and financial loss in unfavorable years. At both lighter and heavier grazing intensities, tradeoffs occurred between the stability of herbage production and animal live weight gains. We show that ecological intensification of specialized soybean systems using livestock integration can increase system stability and profitability, but the probability of win-win outcomes depends on management.
2021 JAN 18
WOS:000612081600006
QID: Q112601625
journalArticle
278
JOURNAL OF ENVIRONMENTAL MANAGEMENT
DOI 10.1016/j.jenvman.2020.111535
Li
Yu
Boswell
Edward
Thompson
Anita
Correlations between land use and stream nitrate-nitrite concentrations in the Yahara River Watershed in south-central Wisconsin
To better inform land management decisions, we explored relationships between land use data and stream nitrate-nitrite (NO3NO2) concentration data in the Yahara River Watershed (YRW) in south-central Wisconsin, USA. Three metrics were used to evaluate the extent of different land uses in the watershed: (1) the area percentage of each land use in both the watershed and in a range of riparian zone widths, (2) the area factor, which refers to the ratio of the area of woodland, recreational, open and vacant subdivided land, or wetlands in the riparian zone (6.1-213.4 m widths) to agricultural areas in the rest of watershed, which indicates the buffering capacity of the riparian zone, and (3) the inverse-distance-weighted (IDW) area percentage with proximity to sub-watershed outlet and to stream, which characterizes spatial arrangement in the watershed by assigning a higher weight to patches closer to the outlet or stream and a lower weight to those farther away. We found significant, positive correlations between the extent of agricultural areas and stream NO3NO2 concentrations. NO3NO2 concentrations were highly correlated to area factor metrics for all riparian zone widths such that as area factor decreased, NO3NO2 concentrations increased. There was also a marked increase in NO3NO2 concentrations at a threshold of approximately 60% agricultural area with IDW proximity to stream. Wetland area percentage in the entire watershed and IDW wetland area percentage with proximity to stream were negatively correlated to stream NO3NO2 concentrations. Compared to the simple area percentage metric, area factor and IDW wetland area percentage with proximity to stream were better indicators of stream NO3NO2 concentrations. Results from this study indicate that, in addition to land use area percentage, spatial distributions of land uses should be considered when managing watersheds. This study also demonstrates the value of citizen-based sampling data and reveals opportunities to improve the utility of such data.
2021 JAN 15
WOS:000599706600003
QID: Q101213657
journalArticle
118
PROCEEDINGS OF THE NATIONAL ACADEMY OF SCIENCES OF THE UNITED STATES OF AMERICA
DOI 10.1073/pnas.2010121118
4
Vijay
Varsha
Armsworth
Paul R.
Pervasive cropland in protected areas highlight trade-offs between conservation and food security
Global cropland expansion over the last century caused widespread habitat loss and degradation. Establishment of protected areas aims to counteract the loss of habitats and to slow species extinctions. However, many protected areas also include high levels of habitat disturbance and conversion for uses such as cropland. Understanding where and why this occurs may realign conservation priorities and inform protected area policy in light of competing priorities such as food security. Here, we use our global synthesis cropland dataset to quantify cropland in protected areas globally and assess their relationship to conservation aims and socio-environmental context. We estimate that cropland occupies 1.4 million km(2) or 6% of global protected area. Cropland occurs across all protected area management types, with 22% occurring in strictly protected areas. Cropland inside protected areas is more prevalent in countries with higher population density, lower income inequality, and with higher agricultural suitability of protected lands. While this phenomenon is dominant in midnorthern latitudes, areas of cropland in protected areas of the tropics and subtropics may present greater trade-offs due to higher levels of both biodiversity and food insecurity. Although area-based targets are prominent in biodiversity goal-setting, our results show that they can mask persistent anthropogenic land uses detrimental to native ecosystem conservation. To ensure the long-term efficacy of protected areas, post-2020 goal setting must link aims for biodiversity and human health and improve monitoring of conservation outcomes in cropland-impacted protected areas.
2021 JAN 26
WOS:000612945500008
QID: Q112808678
journalArticle
55
ENVIRONMENTAL SCIENCE & TECHNOLOGY
DOI 10.1021/acs.est.0c05149
2
Zhan
Xiaoying
Adalibieke
Wulahati
Cui
Xiaoqing
Winiwarter
Wilfried
Reis
Stefan
Zhang
Lin
Bai
Zhaohai
Wang
Qihui
Huang
Weichen
Zhou
Feng
Improved Estimates of Ammonia Emissions from Global Croplands
Reducing ammonia (NH3) volatilization from croplands while satisfying the food demand is strategically required to mitigate haze pollution. However, the global pattern of NH3 volatilization remains uncertain, primarily because of the episodic nature of NH3 volatilization rates and the high variation of fertilization practices. Here, we improve a global estimate of crop-specific NH3 emissions at a high spatial resolution using an updated data-driven model with a survey-based dataset of the fertilization scheme. Our estimate of the globally averaged volatilization rate (12.6% +/- 2.1%) is in line with previous datadriven studies (13.7 +/- 3.1%) but results in one-quarter lower emissions than process-based models (16.5 +/- 3.1%). The associated global emissions are estimated at 14.4 +/- 2.3 Tg N, with more than 50% of the total stemming from three stable crops or 12.2% of global harvested areas. Nearly three-quarters of global cropland-NH3 emissions could be reduced by improving fertilization schemes (right rate, right type, and right placement). A small proportion (20%) of global harvested areas, primarily located in China, India, and Pakistan, accounts for 64% of abatement potentials. Our findings provide a critical reference guide for the future abatement strategy design when considering locations and crop types.
2021 JAN 19
WOS:000612354700053
QID: Q104619046
1329-1338
journalArticle
28
ENVIRONMENTAL SCIENCE AND POLLUTION RESEARCH
DOI 10.1007/s11356-021-12625-2
22
Chen
Wei
Li
Aijia
Hu
Yungang
Li
Lihe
Zhao
Haimeng
Han
Xuerong
Yang
Bin
Exploring the long-term vegetation dynamics of different ecological zones in the farming-pastoral ecotone in northern China
The vegetation in the farming-pastoral ecotone in northern China is influenced by both natural and anthropogenic factors and has undergone drastic changes in the past decades. The farming-pastoral ecotone is the transition zone from agriculture to animal husbandry. The ecological environment of this ecotone is complex and fragile. Most researches have primarily focused on the entire farming-pastoral ecotone, seldomly considering the differences between different ecological zones characterized by soil, climate, and biome conditions. Based on the long time series of leaf area index (LAI) data, meteorological data, and land-use dataset, this study analyzed LAI variation trends, the correlations between LAI and climate factors, and the impact of land-use type change on vegetation in the farming-pastoral ecotone in northern China. Moreover, this paper makes a full study of the changes of the whole study area from the perspective of the differences between different ecological zones. The results showed that over 36 years, areas with vegetation improvements were considerably larger than those with degradations. However, there were still 49.56% of the total area showing no significant vegetation change. There are differences in vegetation change and response to climate between the forest ecological zones and the grassland ecological zones. The vegetation improvement trends of the forest ecological zones were larger and more sensitive to temperature, while the vegetation improvements of the grassland ecological zones were relatively small, and were more sensitive to precipitation. Human activities promote LAI changes in areas close to the forest ecological zones. The change of land use indicates that the decrease of the overall natural vegetation area has not resulted in decreasing LAI. And there is a growing trend of woodland area in the grassland ecological zones. The study provides a theoretical basis for the management of the environment and vegetation in the farming-pastoral ecotone in northern China.
2021 JUN
WOS:000613609500008
QID: Q114689067
27914-27932
journalArticle
339
INTERNATIONAL JOURNAL OF FOOD MICROBIOLOGY
DOI 10.1016/j.ijfoodmicro.2020.109022
Tran
Trang Minh
Ameye
Maarten
Phan
Lien Thi-Kim
Devlieghere
Frank
Saeger
Sarah De
Eeckhout
Mia
Audenaert
Kris
Post-harvest contamination of maize by Fusarium verticillioides and fumonisins linked to traditional harvest and post-harvest practices: A case study of small-holder farms in Vietnam
Together with conducive climatic factors, poor pre-harvest practices of ethnic small-holder farmers are a major cause of the contamination of maize by Fusarium verticillioides and fumonisins. The proliferation of this field pathogen and the accumulation of its mycotoxins in post-harvest maize caused by ethnic post-harvest practices of subsistence farms have received little attention. Therefore, this study aimed to evaluate the impact of traditional harvest and post-harvest practices on the proliferation of F. verticillioides and fumonisins contamination in post-harvest maize of two ethnic groups: Ede and Kinh from the central highlands of Vietnam. In parallel with analysis, a survey on harvest and post-harvest practices of these farmers was conducted from late December 2017 to early January 2019. As a result, four effective post-harvest practices at mitigating the contamination were defined: (1) removal of damaged cobs at harvest, (2) transport of maize home after harvest, (3) shelling maize away from fields, and (4) drying maize on cement yards. These practices were better implemented by Kinh households than Ede households reducing the post-harvest contamination of maize with F. verticillioides and fumonisin B-1 (FB1), FB2, and FB3. Nevertheless, there is still room for improvement with respect to inadequate open-air drying method, poor storage infrastructure, and poor moisture content management as these correlated to the proliferation of F. verticillioides. Finally, the presence of fumonisins together with aflatoxins in some samples at the storage phase might cause a severe impact on human health.
2021 FEB 2
WOS:000694861100022
QID: Q104504371
journalArticle
275
ENVIRONMENTAL POLLUTION
DOI 10.1016/j.envpol.2021.116660
Molomo
Regina Ntsubise
Basera
Wisdom
Chetty-Mhlanga
Shala
Fuhrimann
Samuel
Mugari
Mufaro
Wiesner
Lubbe
Roosli
Martin
Dalvie
Mohamed Aqiel
Relation between organophosphate pesticide metabolite concentrations with pesticide exposures, socio-economic factors and lifestyles: A cross-sectional study among school boys in the rural Western Cape, South Africa
Evidence on the relationship between lifestyle, socio-economic factors and pesticide exposure and urinary concentrations of organophosphate (OP) pesticide metabolites among children is generally incomplete. This study investigated the relationship between socio-economic factors and reported pesticide exposures and the sum of three urinary concentrations of dialkyl phosphate metabolites (DAP) among boys living in the rural areas of the Western Cape, South Africa. Data was collected during a cross-sectional study of 183 boys from three agricultural intense areas. Measurements included a questionnaire on socio-economic and pesticide exposures and urinary DAP concentrations. Most boys (70%) lived on farms with a median age of 12 years (range: 5.0-19.5 years). Children aged >14 years had lower DAP urine concentrations (median = 39.9 ng/ml; beta = -68.1 ng/ml; 95% CI: -136.8, 0.6) than children aged 9 years and younger (median = 107.0 ng/ml). DAP concentrations also varied significantly with area, with concentrations in the grape farming area, Hex River Valley (median = 61.8 ng/ml; beta = -52.1; 95% CI: -97.9, -6.3 ng/ml) and the wheat farming area, Piketberg (median = 72.4 ng/ml; beta = -54.2; 95% CI: 98.8, -9.7 ng/ml) lower than those in the pome farming area, Grabouw (median = 79.9 ng/ml). Other weaker and non-significant associations with increased DAP levels were found with increased household income, member of household working with pesticides, living on a farm, drinking water from an open water source and eating crops from the vineyard and or garden. The study found younger age and living in and around apple and grape farms to be associated with increased urinary DAP concentrations. Additionally, there were other pesticide exposures and socio-economic and lifestyle factors that were weakly associated with elevated urinary DAP levels requiring further study. The study provided more evidence on factors associated to urinary DAP concentrations especially in developing country settings. (C) 2021 Elsevier Ltd. All rights reserved.
2021 APR 15
WOS:000625380600059
QID: Q107140744
journalArticle
18
INTERNATIONAL JOURNAL OF ENVIRONMENTAL RESEARCH AND PUBLIC HEALTH
DOI 10.3390/ijerph18063182
6
Park
Se-Rin
Kim
Suyeon
Lee
Sang-Woo
Evaluating the Relationships between Riparian Land Cover Characteristics and Biological Integrity of Streams Using Random Forest Algorithms
The relationships between land cover characteristics in riparian areas and the biological integrity of rivers and streams are critical in riparian area management decision-making. This study aims to evaluate such relationships using the Trophic Diatom Index (TDI), Benthic Macroinvertebrate Index (BMI), Fish Assessment Index (FAI), and random forest regression, which can capture nonlinear and complex relationships with limited training datasets. Our results indicate that the proportions of land cover types in riparian areas, including urban, agricultural, and forested areas, have greater impacts on the biological communities in streams than those offered by land cover spatial patterns. The proportion of forests in riparian areas has the greatest influence on the biological integrity of streams. Partial dependence plots indicate that the biological integrity of streams gradually improves until the proportion of riparian forest areas reach about 60%; it rapidly decreases until riparian urban areas reach 25%, and declines significantly when the riparian agricultural area ranges from 20% to 40%. Overall, this study highlights the importance of riparian forests in the planning, restoration, and management of streams, and suggests that partial dependence plots may serve to provide insightful quantitative criteria for defining specific objectives that managers and decision-makers can use to improve stream conditions.
2021 MAR
WOS:000639243700001
QID: Q111811335
journalArticle
11
TRANSLATIONAL BEHAVIORAL MEDICINE
DOI 10.1093/tbm/ibaa080
3
Garner
Jennifer A.
Pitts
Stephanie B. Jilcott
Hanson
Karla L.
Ammerman
Alice S.
Kolodinsky
Jane
Sitaker
Marilyn H.
Seguin-Fowler
Rebecca A.
Making community-supported agriculture accessible to low-income families: findings from the Farm Fresh Foods for Healthy Kids process evaluation
A randomized trial of Farm Fresh Foods for Healthy Kids (F3HK) was initiated across 4 states and 12 farms to test whether cost-offset community-supported agriculture (CO-CSA) could improve diet quality among children in low-income families. Intervention households purchased a 50% subsidized share of local produce and were invited to nine complimentary nutrition classes.The purpose of this study was to assess F3HK reach, dose, and fidelity via a mixed methods process evaluation. Screening and enrollment records indicated reach; study records and postlesson educator surveys tracked dose delivered; CSA pickup logs, lesson sign-in sheets, postseason participant surveys, and postlesson caregiver surveys assessed dose received; and coordinator audits and educator surveys tracked fidelity. Educator interviews contextualized findings. The results of this study were as follows. Reach: enrolled caregivers (n = 305) were older (p = .005) than eligible nonenrollees (n = 243) and more likely to be female (p < .001). Dose: mean CSA season was 21 weeks (interquartile range [IQR]: 19-23). Median CSA pickup was 88% of the weeks (IQR: 40-100). All sites offered each class at least once. Most adults (77%) and children (54%) attended at least one class; few attended all. Eighty-two percent of caregivers indicated that their household consumed most or all produce. Median lesson activity ratings were 5/5 ("very useful"). Fidelity: CSA locations functioned with integrity to project standards. Educators taught 92% of activities but frequently modified lesson order. This study demonstrates the feasibility of pairing a CO-CSA intervention with nutrition education across geographically dispersed sites. Greater integration of intervention elements and clearer allowance for site-level modifications, particularly for educational elements, may improve intervention dose and, ultimately, impact.
2021 MAR
WOS:000649397400007
QID: Q99545491
754-763
journalArticle
790
SCIENCE OF THE TOTAL ENVIRONMENT
DOI 10.1016/j.scitotenv.2021.148170
Jimenez-Gonzalez
M. A.
De la Rosa
J. M.
Aksoy
E.
Jeffery
S.
Oliveira
B. R. F.
Verheijen
F. G. A.
Spatial distribution of pyrogenic carbon in Iberian topsoils estimated by chemometric analysis of infrared spectra
Understanding the global carbon (C) cycle is critical to accurately model feedbacks between climate and soil. Thus, many climate change studies focused on soil organic carbon (SOC) stock changes. Pyrogenic carbon (PyC) is one of the most stable fractions of soil organic matter (SOM). Accurate maps based on measured PyC contents are required to facilitate future soil management decisions and soil-climate feedback modelling. However, consistent measurements that cover large areas are rare. Therefore, this study aimed to map the PyC content and stock of the Iberian Peninsula, which covers contrasting climatic zones and has long-term data on wildfire occurrence. A partial least square (PLS) regression using the mid-infrared spectra (1800-400 cm & minus;1) was applied to a dataset composed of 2961 soil samples from the Iberian component of the LUCAS 2009 database. The values of PyC for LUCAS points were modelled to obtain a map of topsoil PyC by a random forest (RF) approach using 36 auxiliary variables. The results were validated through comparison with documented historical wildfire activity and anthropogenic energy production. A strong relationship was found between these sources and the distribution of PyC. Our study estimates that the accumulated PyC in Iberian Peninsula soils comprises between 3.09 and 20.39% of total organic carbon (TOC) in the topsoil. Forests have higher PyC contents than grasslands, followed by agricultural soils. The incidence of recurrent wildfires also has a notable influence on PyC contents. This study shows the potential of estimating PyC with a single, rapid, low cost, chemometric method using new or archived soil spectra, and has the ability to improve soil-climate feedback modelling. It also offers a possible tool for measuring, reporting and verifying soil C stocks, which is likely to be important moving forward if soils are used as sinks for C sequestration. (c) 2021 The Authors. Published by Elsevier B.V. This is an open access article under the CC BY-NC-ND license (http:// creativecommons.org/licenses/by-nc-nd/4.0/).<comment>Superscript/Subscript Available</comment
2021 OCT 10
WOS:000685283900009
QID: Q115741161
journalArticle
287
JOURNAL OF ENVIRONMENTAL MANAGEMENT
DOI 10.1016/j.jenvman.2021.112352
Zaimes
George N.
Tamparopoulos
Alexios E.
Tufekcioglu
Mustafa
Schultz
Richard C.
Understanding stream bank erosion and deposition in Iowa, USA: A seven year study along streams in different regions with different riparian land-uses
Agricultural activities such as row-cropping and grazing, have accelerated stream bank erosion. Accelerated stream bank erosion increases nonpoint source pollutants in aquatic ecosystems, significantly degrading them. Mitigating stream bank erosion is a priority worldwide, especially in agricultural watersheds. The objective of this study was to analyze the impacts of riparian land-use management on stream bank erosion and deposition, along with analyzing its temporal and spatial patterns. The study was conducted in three regions of Iowa (central, northeast and southeast) along 30 stream reaches adjacent to seven different riparian land-uses. The riparian land-uses were riparian forest buffers, grass filters, pastures with the cattle excluded from the stream, intensive rotational grazing, rotational grazing, continuous grazing and row crop fields. Seasonal erosion and deposition data (Spring, Summer and Autumn) were collected along these reaches for 5 years and yearly for the following two years. To analyze the data, conventional statistical methods (ANOVA and Tukey?s test) along with innovative techniques (percentile plots, cumulative erosion curves and bubble charts) were utilized. Based on the analysis, of this extensive in time (seven years) and large in size (1500 pins measured 17 times in three regions) field dataset, major results were obtained in regard to stream bank erosion in Iowa, USA. Stream banks exhibited high year-to-year variation in erosion and deposition showcasing the need for long-term datasets to better understand stream bank erosion and deposition. Seasonal erosion, also had high variability with Spring recording the most erosion followed by Summer and Autumn. Certain seasons exhibited high stream bank erosion indicating that managers need to focus on these seasons, to reduce erosion effectively. In addition, seasonal measurements can highlight depositional events that might be masked with annual measurements. Riparian land-uses significantly impacted stream bank erosion. Riparian forest buffers and grass filters significantly mitigated stream bank erosion while traditional agricultural practices like continuous grazing and row-crop agriculture had accelerated stream bank erosion. Finally, the percentile plots, cumulative erosion curves and bubble charts captured some stream bank responses that would have been unnoticed using conventional statistical methods, allowing decision makers, stakeholders and the general public, to support and approve measures to mitigate this environmental problem. Nature-based solutions utilizing riparian perennial vegetation can sustainably mitigate stream bank erosion.
2021 JUN 1
WOS:000639199300009
QID: Q111810812
journalArticle
16
PLOS ONE
DOI 10.1371/journal.pone.0252482
6
Ao
Guiyan
Liu
Qiang
Qin
Li
Chen
Minghao
Liu
Shuai
Wu
Weiguang
Organization model, vertical integration, and farmers' income growth: Empirical evidence from large-scale farmers in Lin'an, China
Since China's reform and opening-up in 1978, the income of rural residents has increased when compared with that of urban residents. However, the income growth rate of farmers is relatively low, and the income gap between urban and rural areas is widening. Using a sample of 1,325 large-scale farming households in Lin'an, this study constructs a theoretical path for how the level of vertical integration and an organization model affect farmers' income levels and empirically tests the path using a mediation effect analysis model. The results indicate that organization models and vertical integration are important factors that affect farmers' income levels. The total income and agricultural operation income of farmers who participate in agricultural operation organizations are greater than that of farmers who do not participate in an operation organization. In addition, the total income and agricultural operation income of farmers who produce and process and those who produce, process, and sell are higher than those of farmers who only produce. A farmers' organization model has both a direct and an indirect positive influence on their income level, with the indirect positive influence coming through the mediating variable of vertical integration. The application of the organizational model can promote the growth of rural households' total family income and agricultural income by 13.48% and 14.48% respectively, consisting of direct increases of 9.67% and 10.19%, and indirect increases of 3.81% and 4.29% through vertical integration. The results also show that access to credit, agricultural technology training, and the farmer's education level have significant positive impacts on farming income levels. The findings suggest ways to increase farmers' income by perfecting agricultural management organization systems, promoting agricultural industrialization, strengthening rural financial support, improving agricultural technical training for farmers, and increasing their level of education.
2021 JUN 2
WOS:000664638500046
QID: Q110578017
journalArticle
193
ENVIRONMENTAL MONITORING AND ASSESSMENT
DOI 10.1007/s10661-021-09053-7
7
Nuwarinda
H.
Ramoelo
A.
Adelabu
S.
Assessing natural resource change in Vhembe biosphere and surroundings
South Africa is a custodian of an immense wealth of natural and biodiversity resources in Africa. Natural resources are continually changing in different South African biospheres based on anthropogenic and non-anthropogenic causes. Land use activities like agriculture, cultivation, livestock rearing, commercial plantations, urbanisation and mining are among the major drivers of natural resource change and transformation. In this study, land cover change assessment was used to assess natural resource change in Vhembe biosphere and surroundings. To assess natural resource change in Vhembe biosphere, land use land cover change assessment was conducted using South African's national land-cover dataset, generated from multi-seasonal Landsat 5 and Sentinel-2 images. The 72x class land cover map was re-classified into 12x classes to fit the study objectives. Eight out of twelve classes quantified in hectares: indigenous forests, thicket/dense bush, natural woodland, shrubland, grassland, water bodies and wetlands were categorised as natural resources for which the natural resource change assessment for this study was based. Assessment findings established that land use and its related activities have contributed substantially to natural resource change where cultivated commercial, natural woodland and built-up residential contributed the most significant upward change in hectarage and percentage, from 132,246.9 to 365,644.92 (ha)-percentage change of 176%; from 94,665.42 to 257,889.68 (ha)-percentage changes of 172% and from 74,070.27 to 147,701.88(ha)-percentage change of 99% respectively. Shrubland, thicket/dense bush and indigenous forests registered the highest downward changes from 263,070.6 to 977.72 (ha); from 338,723.7 to 23,166.92 and from 13,211.91 to 7402.92 (ha) with percentage changes of -100%, -93% and -44% respectively in Vhembe biosphere and the surroundings from 1990 to 2018. The study showed how natural resources are changing and the use of remote sensing for environmental monitoring and assessment in the Vhembe district.
2021 JUL
WOS:000757352900017
QID: Q111840771
journalArticle
294
JOURNAL OF ENVIRONMENTAL MANAGEMENT
DOI 10.1016/j.jenvman.2021.113016
Soana
Elisa
Fano
Elisa Anna
Castaldelli
Giuseppe
The achievement of Water Framework Directive goals through the restoration of vegetation in agricultural canals
Decreasing nitrate concentrations is one of the most relevant Water Framework Directive (WFD) goals, which today is still unreached in several European countries. Vegetated canals have been recognized as effective filters to mitigate nitrate pollution, although rarely included in restoration programs aimed at improving water quality in agricultural watersheds.The Po di Volano basin (713 km(2), Northern Italy) is a deltaic territory crossed by an extensive network of agricultural canals (similar to 1300 km). The effectiveness in buffering nitrate loads via denitrification was assessed for different levels of in-stream emergent vegetation maintenance by employing an upscale model based on extensive datasets of field measurements. The scenarios differed for the canal network length (5%, 20%, 40%, and 60%) where conservative management practices were adopted by postponing the mowing operations from the middle of summer, as nowadays, to the early autumn, i.e., the vegetative season end.The scenario simulations demonstrated that the capacity to mitigate diffuse nitrate pollution would increase up to four times, compared to the current condition (5% scenario), by postponing the vegetation mowing to the end of the vegetative season in 60% of the canal network length. By preserving the in-stream vegetation in 20% of the canal network, its denitrification capacity would equal the nitrate load reduction target required for achieving, from May to September, the good ecological status according to the WFD in waters delivered to the coastal areas. Changing the timing of vegetation mowing may create a large potential for permanent nitrate removal via denitrification in agricultural landscapes, thus protecting the coastal areas when the eutrophication risk is higher. Conservative management practices of in-stream vegetation might be promoted as an effective low-cost tool to be included in the WFD implementation strategies.
2021 SEP 15
WOS:000677936900009
QID: Q113101144
journalArticle
22
BMC GENOMICS
DOI 10.1186/s12864-021-07905-7
1
Gimenez
Sylvie
Seninet
Imene
Orsucci
Marion
Audiot
Philippe
Negre
Nicolas
Nam
Kiwoong
Streiff
Rejane
d'Alencon
Emmanuelle
Integrated miRNA and transcriptome profiling to explore the molecular determinism of convergent adaptation to corn in two lepidopteran pests of agriculture
BackgroundThe degree to which adaptation to same environment is determined by similar molecular mechanisms, is a topic of broad interest in evolutionary biology, as an indicator of evolutionary predictability. We wished to address if adaptation to the same host plant in phytophagous insects involved related gene expression patterns. We compared sRNA-Seq and RNA-Seq data between two pairs of taxa of Ostrinia and Spodoptera frugiperda sharing maize as host-plant. For the latter, we had previously carried out a reciprocal transplant experiment by feeding of the larvae of the Corn strain (Sf-C) and the Rice strain (Sf-R) on corn versus rice and characterized the mRNA and miRNA responses.ResultsFirst, we predicted the genes encoding miRNA in Ostrinia nubilalis (On) and O. scapulalis (Os). Respectively 67 and 65 known miRNA genes, as well as 196 and 190 novel ones were predicted with Os genome using sncRNAs extracted from whole larvae feeding on corn or mugwort. In On, a read counts analysis showed that 37 (55.22%) known miRNAs and 19 (9.84%) novel miRNAs were differentially expressed (DE) on mugwort compared to corn (in Os, 25 known miRs (38.46%) and 8 novel ones (4.34%)). Between species on corn, 8 (12.5%) known miRNAs and 8 (6.83%) novel ones were DE while only one novel miRNA showed expression variation between species on mugwort. Gene target prediction led to the identification of 2953 unique target genes in On and 2719 in Os, among which 11.6% (344) were DE when comparing species on corn. 1.8% (54) of On miR targets showed expression variation upon a change of host-plant.We found molecular changes matching convergent phenotype, i.e., a set of nine miRNAs that are regulated either according to the host-plant both in On and Sf-C or between them on the same plant, corn. Among DE miR target genes between taxa, 13.7% shared exactly the same annotation between the two pairs of taxa and had function related to insect host-plant interaction.ConclusionThere is some similarity in underlying genetic mechanisms of convergent evolution of two distant Lepidopteran species having adopted corn in their host range, highlighting possible adaptation genes.
2021 AUG 9
WOS:000685089900003
QID: Q114869343
journalArticle
8
SCIENTIFIC DATA
DOI 10.1038/s41597-021-01000-y
1
Jones
Sarah K.
Sanchez
Andrea C.
Juventia
Stella D.
Estrada-Carmona
Natalia
A global database of diversified farming effects on biodiversity and yield
With the Convention on Biological Diversity conference (COP15), United Nations Climate Change Conference (COP26), and United Nations Food Systems Summit, 2021 is a pivotal year for transitioning towards sustainable food systems. Diversified farming systems are key to more sustainable food production. Here we present a global dataset documenting outcomes of diversified farming practices for biodiversity and yields compiled following best standards for systematic review of primary studies and specifically designed for use in meta-analysis. The dataset includes 4076 comparisons of biodiversity outcomes and 1214 of yield in diversified farming systems compared to one of two reference systems. It contains evidence from 48 countries of effects on species from 33 taxonomic orders (spanning insects, plants, birds, mammals, eukaryotes, annelids, fungi, and bacteria) of diversified farming systems producing annual or perennial crops across 12 commodity groups. The dataset presented provides a resource for researchers and practitioners to easily access information on where diversified farming systems effectively contribute to biodiversity and food production outcomes.
2021 AUG 10
WOS:000683734100001
QID: Q115433526
journalArticle
11
SCIENTIFIC REPORTS
DOI 10.1038/s41598-021-96075-3
1
Ahmad
Waqas
Iqbal
Javed
Nasir
Muhammad Jamal
Ahmad
Burhan
Khan
Muhammad Tasleem
Khan
Shahid Nawaz
Adnan
Syed
Impact of land use/land cover changes on water quality and human health in district Peshawar Pakistan
The quality and quantity of groundwater resources are affected by landuse/landcover (LULC) dynamics, particularly the increasing urbanization coupled with high household wastewater discharge and decreasing open lands. This study evaluates temporal changes of groundwater quality for 2012 and 2019, its relation to Landuse/landcover, and its impact on Peshawar's residents (study area), Pakistan. A total of 105 and 112 groundwater samples were collected from tube wells in 2012 and 2019. Samples were then analyzed for seven standard water quality parameters (i.e., pH, electric conductivity (EC), turbidity, chloride, calcium, magnesium, and nitrate). Patient data for waterborne diseases were also collected for the years 2012 and 2019 to relate the impact of groundwater quality on human health. Landsat satellite images were classified for the years 2012 and 2019 to observe landuse/landcover dynamics concerning groundwater quality. Results manifested a decrease in groundwater quality for the year 2019 compared to 2012 and were more highlighted in highly populated areas. The nitrate concentration level was found high in the vicinity of agricultural areas due to the excessive use of nitrogenous fertilizers and pesticides, and thus the methemoglobinemia patients ratio increased by 14% (48-62% for the year 2012 and 2019, respectively). Besides, Urinary Tract Infections, Peptic Ulcer, and Dental Caries diseases increased due to the high calcium and magnesium concentration. The overall results indicate that anthropogenic activities were the main driver of Spatio-temporal variability in groundwater quality of the study area. The study could help district health administration understand groundwater quality trends, make appropriate site-specific policies, and formulate future health regulations.
2021 AUG 16
WOS:000686663200088
QID: Q112272701
journalArticle
193
ENVIRONMENTAL MONITORING AND ASSESSMENT
DOI 10.1007/s10661-021-09403-5
9
Kara
Ferhat
Keles
Seray Ozden
Loewenstein
Edward F.
Development and anatomical traits of black pine on an abandoned agricultural land compared to forested areas
Global acreage of forested lands has increased in some countries. At least some of this increase is due to the natural conversion of abandoned agricultural lands into forests. However, little is known about how these new stands develop on abandoned agricultural lands in comparison with natural regeneration of existing forests. Specifically, knowledge of how black pine (Pinus nigra Arnold) naturally establishes and develops on abandoned agricultural lands is limited. In this study, we examined the density and growth of black pine saplings as well as some morphological and anatomical characteristics on an abandoned agricultural land (AAS). These data were compared with those observed in a naturally regenerated stand (NRS), and in a forest opening (FOS). The greatest sapling density was observed in the NRS site, while sapling growth and stem biomass were higher in AAS followed by NRS and FOS. Moreover, each study site exhibited site-specific morphological and anatomical traits in their saplings. Our findings showed that site treatments and overstory openness would both play crucial role for establishment and development of black pine.
2021 SEP
WOS:000694254300004
QID: Q115235081
journalArticle
204
ENVIRONMENTAL RESEARCH
DOI 10.1016/j.envres.2021.112055
Garcia-Giron
Jorge
Tolonen
Kimmo T.
Soininen
Janne
Snare
Henna
Pajunen
Virpi
Heino
Jani
Anthropogenic land-use impacts on the size structure of macroinvertebrate assemblages are jointly modulated by local conditions and spatial processes
Body size descriptors and associated resemblance measurements may provide useful tools for forecasting ecological responses to increasing anthropogenic land-use disturbances. Yet, the influences of agriculture and urbanisation on the size structure of biotic assemblages have seldom been investigated in running waters. Using a comprehensive dataset on stream macroinvertebrates from 21 river basins across Western Finland, we assessed whether the structure of assemblages via changes in taxonomic composition and body size distributions responded predictably to anthropogenic land-use impacts. Specifically, we applied a combination of resemblance measurements based on cumulative abundance profiles and spatially constrained null models to understand faunal impairment by agricultural and urban development, and the most likely mechanisms underlying the observed shifts in assemblage size structure. Anthropogenically impacted stream sites showed less variation in assemblage composition and size distributions compared with least-disturbed sites, with strong declines in internal variation also occurring for the transition from near-pristine to moderately impacted landscapes. These results were consistent whether based on species-level or genus-level data. Variation in assemblage size structure seemed to be more predictable than taxonomic composition, supporting the notion that resemblance measurements based on body size distributions can represent an improvement to more traditional approaches based on taxonomic identities alone. In addition, we showed that macroinvertebrate assemblages resulted from effects of land-use degradation mediated through local conditions and spurious spatial structures in the distribution of anthropogenic activities across the landscape. Overall, our findings suggest that existing water policies and agri-environment schemes should be guided not only by understanding the individual effects of agricultural and urban development on taxonomic composition at a given stream site. Rather, we should also acknowledge the size structure of stream assemblages and whether concomitant changes in local conditions and the non-random distribution of human infrastructures are likely to mitigate or accelerate these effects.
2022 MAR
WOS:000704721000002
QID: Q112825481
journalArticle
18
INTERNATIONAL JOURNAL OF ENVIRONMENTAL RESEARCH AND PUBLIC HEALTH
DOI 10.3390/ijerph182010771
20
Faisal
Muhammad
Abbas
Azhar
Cai
Yi
Ali
Abdelrahman
Shahzad
Muhammad Amir
Akhtar
Shoaib
Haseeb Raza
Muhammad
Ajmal
Muhammad Arslan
Xia
Chunping
Sattar
Syed Abdul
Batool
Zahira
Perceptions, Vulnerability and Adaptation Strategies for Mitigating Climate Change Effects among Small Livestock Herders in Punjab, Pakistan
Pakistan is an agrarian nation that is among the most vulnerable countries to climatic variations. Around 20% of its GDP is produced by agriculture, and livestock-related production contributes more than half of this value. However, few empirical studies have been conducted to determine the vulnerability and knowledge of livestock herders, and particularly the smaller herders. Comprehending individual perceptions of and vulnerabilities to climate change (CC) will enable effective formulation of CC mitigation strategies. This study intended to explore individual perceptions of and vulnerabilities to CC based on a primary dataset of 405 small livestock herders from three agro-ecological zones of Punjab. The results showed that livestock herders' perceptions about temperature and rainfall variations/patterns coincide with the meteorological information of the study locations. The vulnerability indicators show that Dera Ghazi Khan district is more vulnerable than the other two zones because of high exposure and sensitivity to CC, and lower adaptive capacity. However, all zones experience regular livelihood risks due to livestock diseases and deaths resulting from extreme climatic conditions, lower economic status, and constrained institutional and human resource capabilities, thus leading to increased vulnerability. The results indicate that low-cost local approaches are needed, such as provision of improved veterinary services, increased availability of basic equipment, small-scale infrastructure projects, and reinforcement of informal social safety nets. These measures would support cost-effective and sustainable decisions to enable subsistence livestock herders to adopt climate smart practices.
2021 OCT
WOS:000728581500001
QID: Q113205690
journalArticle
16
PLOS ONE
DOI 10.1371/journal.pone.0258206
10
Kempf
Michael
Take a seed! Revealing Neolithic landscape and agricultural development in the Carpathian Basin through multivariate statistics and environmental modelling
The Carpathian Basin represents the cradle of human agricultural development during the Neolithic period, when large parts were transformed into 'cultural landscapes' by first farmers from the Balkans. It is assumed that an Early Neolithic subsistence economy established along the hydrologic systems and on Chernozem soil patches, which developed from loess deposits. However, recent results from soil chemistry and geoarchaeological analyses raised the hypothesis that extensive Chernozem coverage developed from increased land-use activity and that Early Neolithic 'cultural' groups were not restricted to loess-covered surfaces but rather preferred hydromorphic soils that formed in the floodplains. This article performs multivariable statistics from large datasets of Neolithic sites in Hungary and allows tracing Early to Late Neolithic site preferences from digital environmental data. Quantitative analyses reveal a strong preference for hydromorphic soils, a significant avoidance of loess-covered areas, and no preference for Chernozem soils throughout the Early Neolithic followed by a strong transformation of site preferences during the Late Neolithic period. These results align with socio-cultural developments, large-scale mobility patterns, and land-use and surface transformation, which shaped the Carpathian Basin and paved the way for the agricultural revolution across Europe.
2021 OCT 29
WOS:000755042500005
QID: Q112288054
journalArticle
599
NATURE
DOI 10.1038/s41586-021-04108-8
7886
Robbeets
Martine
Bouckaert
Remco
Conte
Matthew
Savelyev
Alexander
Li
Tao
An
Deog-Im
Shinoda
Ken-ichi
Cui
Yinqiu
Kawashima
Takamune
Kim
Geonyoung
Uchiyama
Junzo
Dolinska
Joanna
Oskolskaya
Sofia
Yamano
Ken-Yojiro
Seguchi
Noriko
Tomita
Hirotaka
Takamiya
Hiroto
Kanzawa-Kiriyama
Hideaki
Oota
Hiroki
Ishida
Hajime
Kimura
Ryosuke
Sato
Takehiro
Kim
Jae-Hyun
Deng
Bingcong
Bjorn
Rasmus
Rhee
Seongha
Ahn
Kyou-Dong
Gruntov
Ilya
Mazo
Olga
Bentley
John R.
Fernandes
Ricardo
Roberts
Patrick
Bausch
Ilona R.
Gilaizeau
Linda
Yoneda
Minoru
Kugai
Mitsugu
Bianco
Raffaela A.
Zhang
Fan
Himmel
Marie
Hudson
Mark J.
Ning
Chao
Triangulation supports agricultural spread of the Transeurasian languages
The origin and early dispersal of speakers of Transeurasian languages-that is, Japanese, Korean, Tungusic, Mongolic and Turkic-is among the most disputed issues of Eurasian population history(1-3). A key problem is the relationship between linguistic dispersals, agricultural expansions and population movements(4,5). Here we address this question by 'triangulating' genetics, archaeology and linguistics in a unified perspective. We report wide-ranging datasets from these disciplines, including a comprehensive Transeurasian agropastoral and basic vocabulary; an archaeological database of 255 Neolithic-Bronze Age sites from Northeast Asia; and a collection of ancient genomes from Korea, the Ryukyu islands and early cereal farmers in Japan, complementing previously published genomes from East Asia. Challenging the traditional 'pastoralist hypothesis'(6-8), we show that the common ancestry and primary dispersals of Transeurasian languages can be traced back to the first farmers moving across Northeast Asia from the Early Neolithic onwards, but that this shared heritage has been masked by extensive cultural interaction since the Bronze Age. As well as marking considerable progress in the three individual disciplines, by combining their converging evidence we show that the early spread of Transeurasian speakers was driven by agriculture.
2021 NOV 25
WOS:000716910900001
QID: Q116965635
616-+
journalArticle
111
PHYTOPATHOLOGY
DOI 10.1094/PHYTO-06-20-0215-R
11
Szyniszewska
Anna Maria
Chikoti
Patrick Chiza
Tembo
Mathias
Mulenga
Rabson
Gilligan
Christopher Aidan
van den Bosch
Frank
McQuaid
Christopher Finn
Smallholder Cassava Planting Material Movement and Grower Behavior in Zambia: Implications for the Management of Cassava Virus Diseases
Cassava (Manihot esculenta) is an important food crop across subSaharan Africa, where production is severely inhibited by two viral diseases, cassava mosaic disease (CMD) and cassava brown streak disease (CBSD), both propagated by a whitefly vector and via human-mediated movement of infected cassava stems. There is limited information on growers' behavior related to movement of planting material, as well as growers' perception and awareness of cassava diseases, despite the importance of these factors for disease control. This study surveyed a total of 96 cassava subsistence growers and their fields across five provinces in Zambia between 2015 and 2017 to address these knowledge gaps. CMD symptoms were observed in 81.6% of the fields, with an average incidence of 52% across the infected fields. No CBSD symptoms were observed. Most growers used planting materials from their own (94%) or nearby (<10 km) fields of family and friends, although several large transactions over longer distances (10 to 350 km) occurred with friends (15 transactions), markets (1), middlemen (5), and nongovernmental organizations (6). Information related to cassava diseases and certified clean (disease-free) seed reached only 48% of growers. The most frequent sources of information related to cassava diseases included nearby friends, family, and neighbors, while extension workers were the most highly preferred source of information. These data provide a benchmark on which to plan management approaches to controlling CMD and CBSD, which should include clean propagation material, increasing growers' awareness of the diseases, and increasing information provided to farmers (specifically disease symptom recognition and disease management options).
2021 NOV
WOS:000737495900006
QID: Q115153541
1952-1962
journalArticle
302
JOURNAL OF ENVIRONMENTAL MANAGEMENT
DOI 10.1016/j.jenvman.2021.114070
Zhang
Guoliang
Chen
Xin
Zhou
Yi
Jiang
Li
Jin
Yuling
Wei
Yukai
Li
Yunpeng
Pan
Zhihua
An
Pingli
Aridification in a farming-pastoral ecotone of northern China from 2 perspectives: Climate and soil
Understanding the impact of climate change on terrestrial wet and dry changes and the relationship between the two is of great significance to the sustainable development of terrestrial ecosystems. The farming-pastoral ecotone of northern China (FPENC) is an area that is sensitive to climate change, suffering from perennial drought and a clear aridification trend. Unlike previous single-factor, single-timescale studies, we identified aridification in the region based on a dataset established by remote sensing and ground-based monitoring stations from a combination of two perspectives: climate and soil. The results show that, in terms of climate, the period from 2000 to 2019 was the driest in the region during the last 120 years , and the summer drought was the most severe and shifted from a summer to spring drought; in terms of soil, the soil aridification trend in the region was severe, with 16.1% of the areas becoming significantly drier (P < 0.1) among the years and 41.6% in spring, respectively. Similar to climate change, soils exhibited recessive aridification due to the counterbalancing effect of the dry and wet seasons within the year. Then the coupling relationship between climate change and soil aridification was established in time and space. Moreover, the spatiotemporal response patterns of both were obtained. The results showed that the frequency of soil drought under meteorological drought conditions showed an increasing trend and that the sensitivity of soil drought occurrence increased. Among them, the effect of precipitation on relative soil moisture (RSM) was immediate, and the effect of prolonged warming on RSM is greater. The area of soil aridification that was caused by climatic aridification in spring accounted for 13.7% of the entire area. The regional aridification research mode proposed in this paper can provide ideas for subsequent studies.
2022 JAN 15
WOS:000719707300003
QID: Q114183478
journalArticle
193
ENVIRONMENTAL MONITORING AND ASSESSMENT
DOI 10.1007/s10661-021-09547-4
12
Ojara
Moses A.
Lou Yunsheng
Ongoma
Victor
Mumo
Lucia
Akodi
David
Ayugi
Brian
Ogwang
Bob Alex
Projected changes in East African climate and its impacts on climatic suitability of maize production areas by the mid-twenty-first century
Maize crop (Zea mays) is one of the staple foods in the East African (EA) region. However, the suitability of its production area is threatened by projected climate change. The Multimodel Ensemble (MME) from eight Coupled Model Intercomparison Project 5 (CMIP5) models was used in this paper to show climate change between the recent past (1970-2000) and the future (2041-2060), i.e., the mid-twenty-first century. The climatic suitability of maize crop production areas is evaluated based on these climate datasets and the current maize crop presence points using Maximum entropy models (MaxEnt). The MME projection showed a slight increase in precipitation under both RCP4.5 and RCP8.5 in certain places and a reduction in most of southern Tanzania. The temperature projection showed that the minimum temperature would increase by 0.3 to 2.95 degrees C and 0.3 to 3.2 degrees C under RCP4.5 and 8.5, respectively. Moreover, the maximum temperature would increase by 1.0 to 3.0 degrees C and 1.2 to 3.6 degrees C under RCP4.5 and 8.5 respectively. The impacts of these projected changes in climate on maize production areas are the reduction in the suitability of the crop, especially around central and western Tanzania, mid-northern and western Uganda, and parts of western Kenya by 20-40%, and patches of EA will experience a reduction of as high as 40-60%, especially in northern Uganda, and western Kenya. The projected changes in temperature and precipitation present a significant negative change in maize crop suitability. Thus, food security and the efforts towards the elimination of hunger in EA by the mid-twenty-first century will be hampered significantly. We recommend crop diversification to suit the new future environments, modernizing maize farming programs through the adoption of new technologies including irrigation, and climate-smart agricultural practices, etc.
2021 DEC
WOS:000720652400005
QID: Q114210420
journalArticle
806
SCIENCE OF THE TOTAL ENVIRONMENT
DOI 10.1016/j.scitotenv.2021.151477
Holopainen
Sari
Lehikoinen
Aleksi
Role of forest ditching and agriculture on water quality: Connecting the long-term physico-chemical subsurface state of lakes with landscape and habitat structure information
Increasing anthropogenic pressures have affected the status of surface freshwater ecosystems. Eutrophication, water browning, acidification, and several other processes may be channelled through the food web. In this study, we evaluate the role of hydrology impacting anthropogenic pressures, flows from urban, farmland and ditched forest areas, and how they explain the physico-chemical quality of lakes and ponds in the boreal biome of Finland. We study the long-term effect around 445 waterfowl survey sites that had physico-chemical measurements (total phosphorus, total nitrogen, pH, water clarity and colour) produced by Finnish environmental authorities done in years 1986-2020. Furthermore, we investigate whether a long-term national-level citizen science study focusing on rather robust visible habitat structures measured by the volunteers can reveal physicochemical water quality using data from >270 lakes where the waterfowl habitat survey and physico-chemical measurements could be spatio-temporally matched. Farmland occurrence around the lakes was positively associated with pH, colour and nutrient concentrations but negatively associated with water clarity. Furthermore, ditch length was positively associated with nitrogen concentration and water colour, while being negatively associated with pH and water clarity. Overall, the studied lakes showed a negative trend in nutrients and clarity but a positive trend in pH and colour. As expected, nutrient concentration increased and clarity decreased along the gradient from oligotrophic to eutrophic lake habitat classifications, which suggests that the citizen science classification seem to reflect the subsurface physico-chemical status of the lakes. We conclude that farming and forest ditching practices in particular seem to associate with the state of the study lakes and that the ecological impacts of intensified turbidity and brownification in wetland ecosystems should be studied further in the future. Sustainable improvement of water quality rests upon scientific understanding of biogeochemical processes in lake ecosystems and the primary sources of the nutrient and sediment loading. (c) 2021 The Authors. Published by Elsevier B.V. This is an open access article under the CC BY license (http://creativecommons.org/licenses/by/4.0/).
2022 FEB 1
WOS:000740227200013
QID: Q111377687
journalArticle
17
PLOS ONE
DOI 10.1371/journal.pone.0268970
7
Kinnebrew
Eva
Ochoa-Brito
Jose I.
French
Matthew
Mills-Novoa
Megan
Shoffner
Elizabeth
Siegel
Katherine
Biases and limitations of Global Forest Change and author-generated land cover maps in detecting deforestation in the Amazon
Studying land use change in protected areas (PAs) located in tropical forests is a major conservation priority due to high conservation value (e.g., species richness and carbon storage) here, coupled with generally high deforestation rates. Land use change researchers use a variety of land cover products to track deforestation trends, including maps they produce themselves and readily available products, such as the Global Forest Change (GFC) dataset. However, all land cover maps should be critically assessed for limitations and biases to accurately communicate and interpret results. In this study, we assess deforestation in PA complexes located in agricultural frontiers in the Amazon Basin. We studied three specific sites: Amboro and Carrasco National Parks in Bolivia, Jamanxim National Forest in Brazil, and Tambopata National Reserve and Bahuaja-Sonene National Park in Peru. Within and in 20km buffer areas around each complex, we generated land cover maps using composites of Landsat imagery and supervised classification, and compared deforestation trends to data from the GFC dataset. We then performed a dissimilarity analysis to explore the discrepancies between the two remote sensing products. Both the GFC and our supervised classification showed that deforestation rates were higher in the 20km buffer than inside the PAs and that Jamanxim National Forest had the highest deforestation rate of the PAs we studied. However, GFC maps showed consistently higher rates of deforestation than our maps. Through a dissimilarity analysis, we found that many of the inconsistencies between these datasets arise from different treatment of mixed pixels or different parameters in map creation (for example, GFC does not detect reforestation after 2012). We found that our maps underestimated deforestation while GFC overestimated deforestation, and that true deforestation rates likely fall between our two estimates. We encourage users to consider limitations and biases when using or interpreting our maps, which we make publicly available, and GFC's maps.
2022
WOS:000835338100042
QID: Q115701503
journalArticle
11
GIGASCIENCE
DOI 10.1093/gigascience/giac054
Guender
Maurice
Yamati
Facundo R. Ispizua
Kierdorf
Jana
Roscher
Ribana
Mahlein
Anne-Katrin
Bauckhage
Christian
Agricultural plant cataloging and establishment of a data framework from UAV-based crop images by computer vision
Background Unmanned aerial vehicle (UAV)-based image retrieval in modern agriculture enables gathering large amounts of spatially referenced crop image data. In large-scale experiments, however, UAV images suffer from containing a multitudinous amount of crops in a complex canopy architecture. Especially for the observation of temporal effects, this complicates the recognition of individual plants over several images and the extraction of relevant information tremendously.Results In this work, we present a hands-on workflow for the automatized temporal and spatial identification and individualization of crop images from UAVs abbreviated as "cataloging" based on comprehensible computer vision methods. We evaluate the workflow on 2 real-world datasets. One dataset is recorded for observation of Cercospora leaf spot-a fungal disease-in sugar beet over an entire growing cycle. The other one deals with harvest prediction of cauliflower plants. The plant catalog is utilized for the extraction of single plant images seen over multiple time points. This gathers a large-scale spatiotemporal image dataset that in turn can be applied to train further machine learning models including various data layers.Conclusion The presented approach improves analysis and interpretation of UAV data in agriculture significantly. By validation with some reference data, our method shows an accuracy that is similar to more complex deep learning-based recognition techniques. Our workflow is able to automatize plant cataloging and training image extraction, especially for large datasets.
2022
WOS:000846739000068
QID: Q112687743
journalArticle
306
JOURNAL OF ENVIRONMENTAL MANAGEMENT
DOI 10.1016/j.jenvman.2021.114330
Schumacher
Britta L.
Yost
Matt A.
Burchfield
Emily K.
Allen
Niel
Water in the West: Trends, production efficiency, and a call for open data
Climate change is projected to transform US agriculture, particularly in places reliant on limited irrigation water resources. As water demand and scarcity increase simultaneously over the coming decades, water managers and growers will need to optimize water use on their irrigated lands. Understanding how growers maintain high yields in arid, water stressed places, while conserving water, is of key importance for the future of US agriculture in the West. We explore water use management and trends in irrigated agriculture in the Western US using operator-level USDA-NASS Farm and Ranch Irrigation Survey/Irrigation and Water Management Survey data aggregated for the first time to the county-scale. In this exploration, we build the first county-level, openly accessible dataset linking farm(er) characteristics to irrigation behaviors in the West. We find notable spatial and temporal variability in Western irrigation practices, with neighboring counties exhibiting large differences in efficiency, water use, and crop yields, as well as in the sources of information, scheduling methods, and technological improvements employed. To produce effective management initiatives in the West, we call for the express and open dissemination of USDA irrigation data at sub-state scales. These data will contribute to our understanding of irrigated production and could support a pathway that will prepare growers for a more resilient agricultural future.
2022 MAR 15
WOS:000783077700006
QID: Q113871401
journalArticle
12
Scientific reports
DOI 10.1038/s41598-022-20299-0
1
Du
Liping
Yang
Huan
Song
Xuan
Wei
Ning
Yu
Caixia
Wang
Weitong
Zhao
Yun
Estimating leaf area index of maize using UAV-based digital imagery and machine learning methods.
Leaf area index (LAI) is a fundamental indicator of crop growth status, timely and non-destructive estimation of LAI is of significant importance for precision agriculture. In this study, a multi-rotor UAV platform equipped with CMOS image sensors was used to capture maize canopy information, simultaneously, a total of 264 ground-measured LAI data were collected during a 2-year field experiment. Linearregression (LR), backpropagation neural network (BPNN), and random forest (RF) algorithms were used to establish LAI estimation models, and their performances were evaluated through 500 repetitions of random sub-sampling, training, and testing. The results showed that RGB-based VIs derived from UAV digital images were strongly related to LAI, and the grain-filling stage (GS) of maize was identified as the optimal period for LAI estimation. The RF model performed best at both whole period and individual growth stages, with the highest R2 (0.71-0.88) and the lowest RMSE (0.12-0.25) on test datasets, followed by the BPNN model and LR models. In addition, a smaller 5-95% interval range of R2 and RMSE was observed in the RF model, which indicated that the RF model has good generalization ability and is able to produce reliable estimation results.
2022 09 24
MEDLINE:36153395
QID: Q114899242
15937-15937
journalArticle
809
SCIENCE OF THE TOTAL ENVIRONMENT
DOI 10.1016/j.scitotenv.2021.151142
Bednarska
Agnieszka J.
Mikolajczyk
Lukasz
Ziolkowska
Elzbieta
Kocjan
Karolina
Wnek
Agnieszka
Mokkapati
Jaya Sravanthi
Teper
Dariusz
Kaczynski
Piotr
Lozowicka
Bozena
Sliwinska
Renata
Laskowski
Ryszard
Effects of agricultural landscape structure, insecticide residues, and pollen diversity on the life-history traits of the red mason bee Osmia bicornis
Agricultural landscapes have changed substantially in recent decades, shifting fromthe dominance of small fields (S) with diverse cropping systems toward large-scale monoculture (L), where landscape heterogeneity disappears. In this study, artificial nests of the red mason bee, Osmia bicornis, were placed in S and L landscape types on the perimeter of oilseed rape fields representing different oilseed rape coverages (ORC, % land cover). The local landscape structure around each nest was characterised within a 100, 200, 500, and 1000 m radius using ORC and 14 landscape characteristics, which were then reduced by non-metric multidimensional scaling (nMDS) to two axes: nMDS1 characterised the dataset primarily according to land fragmentation and the main crop, whereas nMDS2 captured the prevalence of more natural areas in the landscape. Pollen diversity and insecticide risk levels in the pollen provisions collected by the beeswere analysed, and their dependence on the landscape structure was tested. Thereafter, the effects of pollen diversity, insecticide risk, and landscape structure on the life-history traits of bees and their sensitivity to topically applied Dursban 480 EC were determined. Pollen taxa richness in a single nest ranged from3 to 12, and 34 pesticideswere detected in the pollen at concentrations of up to 320 ng/g for desmedipham. The O. bicornis foraging range was relatively large, indicating that the landscape structure within a radius of similar to 1000 m around the nest is important for this species. Pollen diversity in the studied areas was of minor importance for bee performance, but the ORC or landscape structure significantly affected the life-history traits of the bees. Contamination of pollen with insecticides affected the bees by decreasing the mass of newly emerged adults but their sensitivity to Dursban 480 EC was not related to environmental variables. (C) 2021 The Authors. Published by Elsevier B.V.
2022 FEB 25
WOS:000755050800006
QID: Q112260812
journalArticle
29
ENVIRONMENTAL SCIENCE AND POLLUTION RESEARCH
DOI 10.1007/s11356-022-18491-w
25
Li
Bin
Hu
Kai
Lysenko
Vladimir
Khan
Kiran Yasmin
Wang
Yingkuan
Jiang
Yongnian
Guo
Ya
A scientometric analysis of agricultural pollution by using bibliometric software VoSViewer and Histcite (TM)
While modern agriculture brings more food to people, it causes environmental pollution as well. Agricultural pollution has attracted extensive public attention. A lot of reviews on agricultural research were conducted from different research aspects, but there is a lack of work on analyzing the research trend from large volumes of publications in the field of agricultural pollution. In the present work, a scientometric analysis of agricultural pollution was conducted to fill the gap by using the software of VoSviewer and HistCite (TM). The datasets are collected from the core database of Web of Science from 1991 to 2019, totally 1338 records on the topic of agricultural pollutions. In most years (1996, 1999, 2002, 2006, 2009, 2011, and 2013), the total local citation score (TLCS) and total global citation score (TGCS) have coincident peaks. Zhang, Ju, and Zhu have the highest TLCS and TGCS. In terms of institutes, Chinese Acad Sci and China Agr Univ are the leading institutes in this field. The Univ Calif Davis, INRA, and USDA ARS have very high global impacts. From the research hot topics, the representative words include "soil," "agriculture," "contamination," "environment," "lead," and "balance." Representative words like "heavy-metals," "groundwater," "land-use," and "water" are emerging in the latter time period. Five leading research co-cited reference clusters are identified, including environment management, underground water, monitoring and alarming for the agriculture-environment standards, intrinsic mechanism to the circulatory system, and ecology system and land use. The recent trend is revealed from the bibliographical-coupling network, focusing on classical and old-fashion research, like pollution chemicals including N management, pesticides, and heavy metal. This work provides a holistic picture on the research in the field of agriculture pollution.
2022 MAY
WOS:000745809900021
QID: Q111933091
37882-37893
journalArticle
307
JOURNAL OF ENVIRONMENTAL MANAGEMENT
DOI 10.1016/j.jenvman.2022.114514
Hepp
Gerold
Zoboli
Ottavia
Strenge
Eva
Zessner
Matthias
Particulate PhozzyLogic Index for policy makers-an index for a more accurate and transparent identification of critical source areas
The identification of critical source areas (CSAs) is a key element in a cost-effective mitigation of diffuse emissions of phosphorus from agricultural soils into surface waters. One of the challenges related to CSAs is how to couple complex, data-intensive fate and transport models with easy-to-use information on field level for management purposes at the scale of large watersheds. To fill such a gap and create a bridge between the two tasks, this study puts forward the new Particulate PhozzyLogic Index (PPLI) based on the innovative combination of the results of a complex watershed model (in this case the PhosFate model) with fuzzy logic. Its main feature is the ability to transform the results of diverse scenarios or even models into a final map showing a catchment wide ranking of the possibility of high PP emissions reaching surface waters for all agricultural fields. Further, this study enhances the PhosFate model with a new algorithm for the allocation of particulate phosphorus (PP) loads entering surface waters to their sources of origin. This is a basic requirement for the identification of critical PP source areas and in consequence for a cost-effective implementation of mitigation measures. By means of a sensitivity analysis, this study investigates the impacts of storm drains, discharge frequencies and flow directions on the designation of CSAs with the help of present-day scenarios for a case study catchment with an area of several hundred square kilometres. The upfront model calibration exhibits a Nash-Sutcliffe efficiency (NSE) of about 0.95 and a modified Nash-Sutcliffe efficiency (mNSE) of around 0.83. A core result of the sensitivity analysis is that the scenarios at least partially disagree on the identified CSAs and suggest that especially open furrows at field borders have the potential to lead to deviating outcomes. All scenario results nevertheless support the 80:20 rule, which states that about 80% of the phosphorus inputs into the surface waters of a catchment originate from only about 20% of its area.
2022 APR 1
WOS:000796364000001
QID: Q113442116
journalArticle
816
SCIENCE OF THE TOTAL ENVIRONMENT
DOI 10.1016/j.scitotenv.2021.151585
Tavus
Beste
Kocaman
Sultan
Gokceoglu
Candan
Flood damage assessment with Sentinel-1 and Sentinel-2 data after Sardoba dam break with GLCM features and Random Forest method
Accurate mapping and monitoring of flooded areas are immensely required for disaster management purposes, such as for damage assessment and mitigation. In this study, the flood damage mapping performances of two satellite Earth Observation sensors, i.e., European Space Agency's Sentinel-1 (S1) synthetic aperture radar (SAR) and Sentinel-2 (S2) multispectral optical instruments, were evaluated using the Random Forest (RF) supervised classification method and various feature types. The study area was Sardoba Reservoir (Uzbekistan) and its surroundings, in which a disastrous dam failure occurred on May 1, 2020. After the failure of a part of the earthfill dam, a large region with settlements and agricultural areas in Uzbekistan and Kazakhstan was flooded. S1 and S2 cloudless data with a short temporal interval acquired soon after the event were available for the area. Four different data availability scenarios, such as (i) only S1 pre-and post-flood data; (ii) only S2 pre-and post flood data; (iii) S1 pre-and post-flood and S2 pre-flood data; and (iv) S1 and S2 pre-and post-flood data were evaluated in terms of classification accuracy. In addition to the polarization information of S1 and the intensity values of S2 bands, feature maps produced from these datasets, such as vegetation and water indices, textural information obtained from gray level co-occurrence matrix (GLCM), and the principal component analysis (PCA) bands were employed in the RF method. The results show that the fusion of S1 and S2 data exhibit very high classification accuracy for the flooded areas and can separate the inundated vegetation as well. The use of S2 pre event data together with the S1 pre-and post-event data is recommended for obtaining high accuracy even when post-event optical data is not available. (c) 2021 Elsevier B.V. All rights reserved.
2022 APR 10
WOS:000766811900002
QID: Q115741192
journalArticle
12
SCIENTIFIC REPORTS
DOI 10.1038/s41598-022-06436-9
1
Delgado-Gonzalez
A.
Cortes-Avizanda
A.
Serrano
D.
Arrondo
E.
Duriez
O.
Margalida
A.
Carrete
M.
Oliva-Vidal
P.
Sourp
E.
Morales-Reyes
Z.
Garcia-Baron
I
de la Riva
M.
Sanchez-Zapata
J. A.
Donazar
J. A.
Apex scavengers from different European populations converge at threatened savannah landscapes
Over millennia, human intervention has transformed European habitats mainly through extensive livestock grazing. "Dehesas/Montados" are an Iberian savannah-like ecosystem dominated by oak-trees, bushes and grass species that are subject to agricultural and extensive livestock uses. They are a good example of how large-scale, low intensive transformations can maintain high biodiversity levels as well as socio-economic and cultural values. However, the role that these human-modified habitats can play for individuals or species living beyond their borders is unknown. Here, using a dataset of 106 adult GPS-tagged Eurasian griffon vultures (Gyps fulvus) monitored over seven years, we show how individuals breeding in western European populations from Northern, Central, and Southern Spain, and Southern France made long-range forays (LRFs) of up to 800 km to converge in the threatened Iberian "dehesas" to forage. There, extensive livestock and wild ungulates provide large amounts of carcasses, which are available to scavengers from traditional exploitations and rewilding processes. Our results highlight that maintaining Iberian "dehesas" is critical not only for local biodiversity but also for long-term conservation and the ecosystem services provided by avian scavengers across the continent.
2022 FEB 15
WOS:000756701900033
QID: Q114108382
journalArticle
17
PLOS ONE
DOI 10.1371/journal.pone.0262376
3
Rakotoarinia
Miarisoa Rindra
Blanchet
F. Guillaume
Gravel
Dominique
Lapen
David R.
Leighton
Patrick A.
Ogden
Nicholas H.
Ludwig
Antoinette
Effects of land use and weather on the presence and abundance of mosquito-borne disease vectors in a urban and agricultural landscape in Eastern Ontario, Canada
Weather and land use can significantly impact mosquito abundance and presence, and by consequence, mosquito-borne disease (MBD) dynamics. Knowledge of vector ecology and mosquito species response to these drivers will help us better predict risk from MBD. In this study, we evaluated and compared the independent and combined effects of weather and land use on mosquito species occurrence and abundance in Eastern Ontario, Canada. Data on occurrence and abundance (245,591 individuals) of 30 mosquito species were obtained from mosquito capture at 85 field sites in 2017 and 2018. Environmental variables were extracted from weather and land use datasets in a 1-km buffer around trapping sites. The relative importance of weather and land use on mosquito abundance (for common species) or occurrence (for all species) was evaluated using multivariate hierarchical statistical models. Models incorporating both weather and land use performed better than models that include weather only for approximately half of species (59% for occurrence model and 50% for abundance model). Mosquito occurrence was mainly associated with temperature whereas abundance was associated with precipitation and temperature combined. Land use was more often associated with abundance than occurrence. For most species, occurrence and abundance were positively associated with forest cover but for some there was a negative association. Occurrence and abundance of some species (47% for occurrence model and 88% for abundance model) were positively associated with wetlands, but negatively associated with urban (Culiseta melanura and Anopheles walkeri) and agriculture (An. quadrimaculatus, Cs. minnesotae and An. walkeri) environments. This study provides predictive relationships between weather, land use and mosquito occurrence and abundance for a wide range of species including those that are currently uncommon, yet known as arboviruses vectors. Elucidation of these relationships has the potential to contribute to better prediction of MBD risk, and thus more efficiently targeted prevention and control measures.
2022 MAR 10
WOS:000820912700008
QID: Q111320306
journalArticle
22
SENSORS
DOI 10.3390/s22072733
7
Sarramia
David
Claude
Alexandre
Ogereau
Francis
Mezhoud
Jeremy
Mailhot
Gilles
CEBA: A Data Lake for Data Sharing and Environmental Monitoring
This article presents a platform for environmental data named "Environmental Cloud for the Benefit of Agriculture" (CEBA). The CEBA should fill the gap of a regional institutional platform to share, search, store and visualize heterogeneous scientific data related to the environment and agricultural researches. One of the main features of this tool is its ease of use and the accessibility of all types of data. To answer the question of data description, a scientific consensus has been established around the qualification of data with at least the information "when" (time), "where" (geographical coordinates) and "what" (metadata). The development of an on-premise solution using the data lake concept to provide a cloud service for end-users with institutional authentication and for open data access has been completed. Compared to other platforms, CEBA fully supports the management of geographic coordinates at every stage of data management. A comprehensive JavaScript Objet Notation (JSON) architecture has been designed, among other things, to facilitate multi-stage data enrichment. Data from the wireless network are queried and accessed in near real-time, using a distributed JSON-based search engine.
2022 APR
WOS:000781144200001
QID: Q111824980
journalArticle
51
INTERNATIONAL JOURNAL OF EPIDEMIOLOGY
DOI 10.1093/ije/dyac050
5
Walsh
Michael G.
Pattanaik
Amrita
Vyas
Navya
Saxena
Deepak
Webb
Cameron
Sawleshwarkar
Shailendra
Mukhopadhyay
Chiranjay
High-risk landscapes of Japanese encephalitis virus outbreaks in India converge on wetlands, rain-fed agriculture, wild Ardeidae, and domestic pigs and chickens
Background Japanese encephalitis virus (JEV) is a zoonotic mosquito-borne virus that causes a significant burden of disease across Asia, particularly in India, with high mortality in children. JEV circulates in wild ardeid birds and domestic pig reservoirs, both of which generate sufficiently high viraemias to infect vector mosquitoes, which can then subsequently infect humans. The landscapes of these hosts, particularly in the context of anthropogenic ecotones and resulting wildlife-livestock interfaces, are poorly understood and thus significant knowledge gaps in the epidemiology of JEV persist. This study sought to investigate the landscape epidemiology of JEV outbreaks in India over the period 2010-2020 to determine the influence of shared wetland and rain-fed agricultural landscapes and animal hosts on outbreak risk. Methods Using surveillance data from India's National Centre for Disease Control Integrated Disease Surveillance Programme, JEV outbreaks were modelled as an inhomogeneous Poisson point process and externally validated against independently sourced data. Results Outbreak risk was strongly associated with the habitat suitability of ardeid birds, both pig and chicken density, and the shared landscapes between fragmented rain-fed agriculture and both river and freshwater marsh wetlands. Conclusion The results from this work provide the most complete understanding of the landscape epidemiology of JEV in India to date and suggest important One Health priorities for control and prevention across fragmented terrain comprising a wildlife-livestock interface that favours spillover to humans.
2022 OCT 13
WOS:000784610900001
QID: Q114092380
1408-1418
journalArticle
28
GLOBAL CHANGE BIOLOGY
DOI 10.1111/gcb.16164
12
Heikkinen
Jaakko
Keskinen
Riikka
Kostensalo
Joel
Nuutinen
Visa
Climate change induces carbon loss of arable mineral soils in boreal conditions
One-fourth of the global soil organic carbon (SOC) is stored in the boreal region, where climate change is predicted to be faster than the global average. Planetary warming is accelerated if climate change promotes SOC release into the atmosphere as carbon dioxide. However, the soil carbon-climate feedbacks have been poorly confirmed by SOC measurements despite their importance on global climate. In this study, we used data collected as part of the Finnish arable soil monitoring program to study the influence of climate change, management practices, and historical land use on changes in SOC content using a Bayesian approach. Topsoil samples (n = 385) collected nationwide in 2009 and 2018 showed that SOC content has decreased at the rate of 0.35% year(-1) on average. Based on the Bayesian modeling of our data, we can say with a certainty of 79%-91% that increase in summertime (May-Sep) temperature has resulted in SOC loss while increased precipitation has resulted in SOC loss with a certainty of 90%-97%. The exact percentages depend on the climate dataset used. Historical land use was found to influence the SOC content for decades after conversion to cropland. Former organic soils with a high SOC-to-fine-fraction ratio were prone to high SOC loss. In fields with long cultivation history (>100 years), however, the SOC-to-fine-fraction ratio had stabilized to approximately 0.03-0.04 and the changes in SOC content leveled off. Our results showed that, although arable SOC sequestration can be promoted by diversifying crop rotations and by cultivating perennial grasses, it is unlikely that improved management practices are sufficient to counterbalance the climate change-induced SOC losses in boreal conditions. This underlines the importance of the reduction of greenhouse gas emissions to avoid the acceleration of planetary warming.
2022 JUN
WOS:000776572100001
QID: Q114081196
3960-3973
journalArticle
119
PROCEEDINGS OF THE NATIONAL ACADEMY OF SCIENCES OF THE UNITED STATES OF AMERICA
DOI 10.1073/pnas.2106743119
15
Marciniak
Stephanie
Bergey
Christina M.
Silva
Ana Maria
Haluszko
Agata
Furmanek
Miroslaw
Veselka
Barbara
Veleminsky
Petr
Vercellotti
Giuseppe
Wahl
Joachim
Zarina
Gunita
Longhi
Cristina
Kolar
Jan
Garrido-Pena
Rafael
Flores-Fernandez
Raul
Herrero-Corral
Ana M.
Simalcsik
Angela
Mueller
Werner
Sheridan
Alison
Miliauskiene
Zydrune
Jankauskas
Rimantas
Moiseyev
Vyacheslav
Kohler
Kitti
Kiraly
Agnes
Gamarra
Beatriz
Cheronet
Olivia
Szeverenyi
Vajk
Kiss
Viktoria
Szeniczey
Tamas
Kiss
Krisztian
Zoffmann
Zsuzsanna K.
Koos
Judit
Hellebrandt
Magdolna
Maier
Robert M.
Domboroczki
Laszlo
Virag
Cristian
Novak
Mario
Reich
David
Hajdu
Tamas
von Cramon-Taubadel
Noreen
Pinhasi
Ron
Perry
George H.
An integrative skeletal and paleogenomic analysis of stature variation suggests relatively reduced health for early European farmers
Human culture, biology, and health were shaped dramatically by the onset of agriculture similar to 12,000 y B.P. This shift is hypothesized to have resulted in increased individual fitness and population growth as evidenced by archaeological and population genomic data alongside a decline in physiological health as inferred from skeletal remains. Here, we consider osteological and ancient DNA data from the same prehistoric individuals to study human stature variation as a proxy for health across a transition to agriculture. Specifically, we compared "predicted" genetic contributions to height from paleogenomic data and "achieved" adult osteological height estimated from long bone measurements for 167 individuals across Europe spanning the Upper Paleolithic to Iron Age (similar to 38,000 to 2,400 B.P.). We found that individuals from the Neolithic were shorter than expected (given their individual polygenic height scores) by an average of 23.82 cm relative to individuals from the Upper Paleolithic and Mesolithic (P = 0.040) and 22.21 cm shorter relative to post-Neolithic individuals (P = 0.068), with osteological vs. expected stature steadily increasing across the Copper (+1.95 cm relative to the Neolithic), Bronze (+2.70 cm), and Iron (+3.27 cm) Ages. These results were attenuated when we additionally accounted for genome-wide genetic ancestry variation: for example, with Neolithic individuals 22.82 cm shorter than expected on average relative to pre-Neolithic individuals (P = 0.120). We also incorporated observations of paleopathological indicators of nonspecific stress that can persist from childhood to adulthood in skeletal remains into our model. Overall, our work highlights the potential of integrating disparate datasets to explore proxies of health in prehistory.
2022 APR 12
WOS:000819867000005
QID: Q112558654
journalArticle
19
INTERNATIONAL JOURNAL OF ENVIRONMENTAL RESEARCH AND PUBLIC HEALTH
DOI 10.3390/ijerph19095707
9
Song
Chunxiao
Huang
Xiao
Les
Oxley
Ma
Hengyun
Liu
Ruifeng
The Economic Impact of Climate Change on Wheat and Maize Yields in the North China Plain
Climate change has significantly affected agricultural production. As one of China's most important agricultural production regions, the North China Plain (NCP) is subject to climate change. This paper examines the influence of climate change on the wheat and maize yields at household and village levels, using the multilevel model based on a large panel survey dataset in the NCP. The results show that: (i) Extreme weather events (drought and flood) would significantly reduce the wheat and maize yields. So, the governments should establish and improve the emergency service system of disaster warning and encourage farmers to mitigate the adverse effects of disasters. (ii) Over the past three decades, the NCP has experienced climate change that affects its grain production. Therefore, it is imperative to build the farmers' adaptive capacity to climate change. (iii) Spatial variations in crop yield are significantly influenced by the household characteristics and the heterogeneity of village economic conditions. Therefore, in addition to promoting household production, it is necessary to strengthen and promote China's development of the rural collective economy, especially the construction of rural irrigation and drainage infrastructures.
2022 MAY
WOS:000794400800001
QID: Q114604344
journalArticle
835
SCIENCE OF THE TOTAL ENVIRONMENT
DOI 10.1016/j.scitotenv.2022.155518
Baccour
Safa
Ward
Frank A.
Albiac
Jose
Climate adaptation guidance: New roles for hydroeconomic analysis
Climate water stress internationally challenges the goal of achieving food, energy, and water security. This challenge is elevated by population and income growth. Increased climate water stress levels reduce water supplies in many river basins and elevate competition for water among sectors. Organized information is needed to guide river basin managers and stakeholders who must plan for a changing climate through innovative water allocation policies, trade-off analysis, vulnerability assessment, capacity adaptation, and infrastructure planning. Several hydroeconomic models have been developed and applied assessing water use in different sectors, counties, cultures, and time periods. However, none to date has presented an optimization framework by which historical water use and economic benefit patterns can be replicated while presenting capacity to adapt to future climate water stresses to inform the design of policies not yet been implemented. This paper's unique contribution is to address this gap by designing and presenting results of a hydroeconomic model for which optimized base conditions exactly match observed data water use and economic welfare for several urban and agricultural uses at several locations in a large European river basin for which water use supports a population of more than 3.2 million. We develop a state-of-the arts empirical dynamic hydroeconomic optimization model to discover land and water use patterns that optimize sustained farm and city income under various levels of climate-water stress. Findings using innovative model calibration methods allow for the discovery of efficient water allocation plans as well as providing insight into marginal behavioral responses to climate water stress and water policies. Results identify that water trade policy under climate water stress provides more economically efficient water use patterns, reallocating water from lower valued uses to higher valued uses such as urban water. The Ebro River Basin in Spain is used as an example to investigate water use adaptation patterns under various levels of climate water stress. That basin's issues and challenges can be of relevance to other river basins internationally.
2022 AUG 20
WOS:000808102800007
QID: Q113287419
journalArticle
12
SCIENTIFIC REPORTS
DOI 10.1038/s41598-022-11396-1
1
Ettehadi Osgouei
Paria
Sertel
Elif
Kabadayi
M. Erdem
Integrated usage of historical geospatial data and modern satellite images reveal long-term land use/cover changes in Bursa/Turkey, 1858-2020
Land surface of the Earth has been changing as a result of human induced activities and natural processes. Accurate representation of landscape characteristics and precise determination of spatio-temporal changes provide valuable inputs for environmental models, landscape and urban planning, and historical land cover change analysis. This study aims to determine historical land use and land cover (LULC) changes using multi-modal geospatial data, which are the cadastral maps produced in 1858, monochrome aerial photographs obtained in 1955, and multi-spectral WorldView-3 satellite images of 2020. We investigated two pilot regions, Aksu and Kestel towns in Bursa/Turkey, to analyze the long-term LULC changes quantitatively and to understand the driving forces that caused the changes. We propose methods to facilitate the preparation of historical datasets for the LULC change detection and present an object-oriented joint classification scheme for multi-source datasets to accurately map the spatio-temporal changes. Our approach minimized the amount of manual digitizing required for the boundary delineation of LULC classes from historical geospatial data. Also, our quantitative analysis of LULC maps indicates diverging developments for the selected locations in the long period of 162 years. We observed rural depopulation and gradual afforestation in Aksu; whereas, agricultural land abandonment and deforestation in Kestel.
2022 MAY 31
WOS:000803920600022
QID: Q112270742
journalArticle
165
ENVIRONMENT INTERNATIONAL
DOI 10.1016/j.envint.2022.107296
Silva
Vera
Yang
Xiaomei
Fleskens
Luuk
Ritsema
Coen J.
Geissen
Violette
Environmental and human health at risk - Scenarios to achieve the Farm to Fork 50% pesticide reduction goals
The recently released Farm to Fork Strategy of the European Union sets, for the first time, pesticide reduction goals at the EU level: 50% reduction in overall use and risk of chemical pesticides and a 50% use reduction of more hazardous pesticides. However, there is little guidance provided as to how to achieve these targets. In this study, we compiled the characteristics of all 230 EU-approved, synthetic, open-field use active substances (AS) used as herbicides, fungicides and insecticides, and explored the potential of seven Farm to Fork-inspired pesticide use reduction scenarios to achieve the 50% reduction goals. The pesticide reduction scenarios were based on recommended AS application rates, pesticide type, soil persistence, presence on the candidate for substitution list, and hazard to humans and ecosystems. All 230 AS have been found to cause negative effects on humans or ecosystems depending on exposure levels. This is found despite the incomplete hazard profiles of several AS. 'No data available' situations are often observed for the same endpoints and specific organisms. The results of the scenarios indicate that only severe pesticide use restrictions, such as allowing only low-hazard substances, will result in the targeted 50% use and risk reductions. Over half of the 230 AS considered are top use or top hazard substances, however, the reduction actions depend on the still to be defined EC priority areas and action plans, also for other recent and related strategies. Broader scenario implications (on productivity, biodiversity or economy) and the response of farmers to the pesticide use restrictions should be explored in those plans to define effective actions. Our results emphasize the need for a re-evaluation of the approved AS and of their representative uses, and the call for open access to AS, crop and region-specific use data to refine scenarios and assess effective reductions.
2022 JUL
WOS:000806366300003
QID: Q112060859
journalArticle
822
SCIENCE OF THE TOTAL ENVIRONMENT
DOI 10.1016/j.scitotenv.2022.153493
Nauditt
Alexandra
Stahl
Kerstin
Rodriguez
Erasmo
Birkel
Christian
Formiga-Johnsson
Rosa Maria
Kallio
Marko
Ribbe
Lars
Baez-Villanueva
Oscar M.
Thurner
Joschka
Hann
Hamish
Evaluating tropical drought risk by combining open access gridded vulnerability and hazard data products
Droughts are causing severe damages to tropical countries worldwide. Although water abundant, their resilience to water shortages during dry periods is often low. As there is little knowledge about tropical drought characteristics, reliable methodologies to evaluate drought risk in data scarce tropical regions are needed. We combined drought hazard and vulnerability related data to assess drought risk in four rural tropical study regions, the Muriae basin, Southeast Brazil, the Tempisque-Bebedero basin in Costa Rica, the upper part of the Magdalena basin, Colombia and the Srepok, shared by Cambodia and Vietnam. Drought hazard was analyzed using the variables daily river discharge, precipitation and vegetation condition. Drought vulnerability was assessed based on regionally available socioeconomic data. Besides illustrating the relative severity of each indicator value, we developed drought risk maps combining hazard and vulnerability for each grid-cell. While for the Muriae, our results identified the downstream area as being exposed to severe drought risk, the Tempisque showed highest risk along the major streams and related irrigation systems. Risk hotspots in the Upper Magdalena were found in the central valley and the dryer Southeast and in the Srepok in the agricultural areas of Vietnam and downstream Cambodia. Local scientists and stakeholders have validated our results and we believe that our drought risk assessment methodology for data scarce and rural tropical regions offers a holistic, science based and innovative framework to generate relevant drought related information. Being applied to other tropical catchments, the approaches described in this article will enable the selection of data sets, indices and their classification depending on basin size, spatial resolution and seasonality. At its current stage, the outcomes of this study provide relevant information for regional planners and water managers dealing with the control of future drought disasters in tropical regions.
2022 MAY 20
WOS:000766800600002
QID: Q113865235
journalArticle
22
JOURNAL OF INSECT SCIENCE
DOI 10.1093/jisesa/ieac036
4
Ryu
Jae Hyeon
Clements
Justin
Neufeld
Jerry
Low-Cost Live Insect Scouting Drone: iDrone Bee
Unmanned aerial vehicles (UAVs, e.g., drones) are a common tool for many civil applications, including precision agriculture, transportation, delivery services, rescue missions, law enforcement, and more. Remote sensing technologies used in conjunction with drones are a dominant application in precision agriculture. Multispectral instrumentation attached to UAVs allows the user to observe multiple parameters, including the normalized difference vegetation index which can represent crop stresses induced by various factors (e.g., drought, insect outbreak, nutrient loss, and other diseases). However, little research has been done to apply drones to accomplish a mission-oriented actionable task in agriculture, such as insect sampling. We propose a low-cost, open source-based live insect scouting drone named 'iDrone Bee' to benefit the integrated pest management (IPM) community by minimizing time and efforts of human interventions while collecting live insects in agricultural fields. Herein we present instruction and operation procedures to build and operate an iDrone Bee for insect scouting in an agricultural ecosystem and validate the system in an alfalfa seed field. The findings of this investigation demonstrate that a drone-based insect scouting method may be a valuable tool to benefit the IPM community.
2022 JUL 1
WOS:000821226600001
QID: Q114150971
journalArticle
12
BIOSENSORS-BASEL
DOI 10.3390/bios12070447
7
Ruiz-Gonzalez
Antonio
Kempson
Harriet
Haseloff
Jim
In Vivo Sensing of pH in Tomato Plants Using a Low-Cost and Open-Source Device for Precision Agriculture
The development of sensing devices for precision agriculture is crucial to boost crop yields and limit shortages in food productions due to the growing population. However, current approaches cannot provide direct information about the physiological status of the plants, reducing sensing accuracy. The development of implanted devices for plant monitoring represents a step forward in this field, enabling the direct assessment of key biomarkers in plants. However, available devices are expensive and cannot be used for long-term applications. The current work presents the application of ruthenium oxide-based nanofilms for the in vivo monitoring of pH in plants. The sensors were manufactured using the low-cost electrodeposition of RuO2 films, and the final device could be successfully incorporated for the monitoring of xylem sap pH for at least 10 h. RuO2 nanoparticles were chosen as the sensing material due to its biocompatibility and chemical stability. To reduce the noise rates and drift of the sensors, a protective layer consisting of a cellulose/PDMS hybrid material was deposited by an aerosol method (>GBP 50), involving off-the-shelf devices, leading to a good control of film thickness. Nanometrically thin films with a thickness of 80 nm and roughness below 3 nm were fabricated. This film led to a seven-fold decrease in drift while preserving the selectivity of the sensors towards H+ ions. The sensing devices were tested in vivo by implantation inside a tomato plant. Environmental parameters such as humidity and temperature were additionally monitored using a low-cost Wio Terminal device, and the data were sent wirelessly to an online server. The interactions between plant tissues and metal oxide-based sensors were finally studied, evidencing the formation of a lignified layer between the sensing film and xylem. Thus, this work reports for the first time a low-cost electrochemical sensor that can be used for the continuous monitoring of pH in xylem sap. This device can be easily modified to improve the long-term performance when implanted inside plant tissues, representing a step forward in the development of precision agriculture technologies.
2022 JUL
WOS:000832024000001
QID: Q113206831
journalArticle
151
WASTE MANAGEMENT
DOI 10.1016/j.wasman.2022.07.033
Balde
Hambaliou
Wagner-Riddle
Claudia
MacDonald
Douglas
VanderZaag
Andrew
Fugitive methane emissions from two agricultural biogas plants
This study quantified fugitive methane (CH4) losses from multiple sources (open digestate storages, digesters and flare) at two biogas facilities over one year, providing a much needed dataset integrating all major loss pathways and changes over time. Losses of CH4 from Facility A were primarily from digestate storage (5.8% of biogas CH4), followed by leakage/venting (5.5%) and flaring (0.2%). At Facility B, losses from digestate storage were higher (10.7%) due to shorter hydraulic retention time and lack of a screwpress. Fugitive emissions from leakage were initially 3.8% but were reduced to 0.6% after the dome membrane was repaired at Facility B. For biogas to have a positive impact on greenhouse gas emissions and provide a low-carbon fuel, it is important to minimize fugitive losses from digestate storage and avoid leakage during abnormal operation (leakage, roof failure).
2022 SEP
WOS:000859399600003
QID: Q114174060
123-130
journalArticle
2022
COMPUTATIONAL INTELLIGENCE AND NEUROSCIENCE
DOI 10.1155/2022/1296993
Adow
Anass Hamadelneel
Shrivas
Mahendra Kumar
Mahdi
Hussain Falih
Zahra
Musaddak Maher Abdul
Verma
Devvret
Doohan
Nitika Vats
Jalali
Asadullah
Analysis of Agriculture and Food Supply Chain through Blockchain and IoT with Light Weight Cluster Head
By 2050, the worlds population will have increased by 34%, to more than 9 billion people, needing a 70% increase in food production. Prepare more dishes with fewer ingredients. Therefore, the critical goal of manufacturers is to increase production while being ecologically benign. Supply chain systems that do not enable direct farmer-to-consumer connection and rising input costs influence data collection, security, and sharing. Constraints on data security, manipulation, and single-point failure are unfulfilled due to a lack of centralized IoT agricultural infrastructure. To address these issues, the article proposes a blockchain-based IoT model. This study also shows one-of-a-kind energy savings. The decentralization of data storage improves the supply chains transparency and quality through blockchain technology, thus farmers can engage more efficiently. Blockchain technology improves supply chain traceability and security. This article provides a transparent, decentralized blockchain tracking solution and proposes an intelligent model protocol for several Internet of Things (IoT) devices that monitor crop development and the agricultural environment. A new approach has resolved the bulk of the supply chain difficulties. Smart contracts were utilized to organize all transactions in decentralized supply networks. The use of blockchain technology improves transaction quality, and customers may verify the legitimacy of an items authenticity and legality by using the system. A total of 100 IoT nodes were distributed randomly to each 500?m2 cluster farm. The Internet of Things nodes were used to assess soil moisture, temperature, and crop disease. Network stability period and network life of the proposed method show 90.4% accuracy. The food supply chain will be more efficient and trustworthy with an intelligent model. The immutability of ledger technology and smart contract support further increases supply chain security, privacy, transparency, and trust among all stakeholders in the multi-party system. By 2050, the worlds population will need a 70% increase in food production. The food supply chain will be more efficient and trustworthy with an intelligent model. This article provides a transparent, decentralized, and intelligent model protocol for several Internet of Things (IoT) devices.
2022 AUG 10
WOS:000875172300001
QID: Q114069762
journalArticle
2022
COMPUTATIONAL INTELLIGENCE AND NEUROSCIENCE
DOI 10.1155/2022/5614974
Zhang
Qiusi
Li
Bo
Zhang
Yong
Wang
Shufeng
Suitability Evaluation of Crop Variety via Graph Neural Network
With the continuous growth of the global population, insufficient food production has become an urgent problem to be solved in most countries. At present, using artificial intelligence technology to improve suitability between land and crop varieties to increase crop yields has become a consensus among agricultural researchers. However, there are still many problems in existing works, such as limited crop phenotypic data and the poor performance of artificial intelligence models. In this regard, we take maize as an example to collect a large amount of environmental climate and crop phenotypic traits data at multiple experimental sites and construct an extensive dataset. Then, we introduce a graph neural network model to learn crop suitability evaluation and finally achieve a good evaluation effect. The evaluation results of the model can not only provide a reference for expert evaluation but also judge the suitability of the variety to other test trial sites according to the data of the current one, so as to guide future breeding experiments.
2022 AUG 9
WOS:000843367700010
QID: Q114141007
journalArticle
194
ENVIRONMENTAL MONITORING AND ASSESSMENT
DOI 10.1007/s10661-022-10275-6
9
Shah
Suraj
Tiwari
Achyut
Song
Xianfeng
Talchabahdel
Rocky
Habiyakare
Telesphore
Adhikari
Arjun
Drought index predictability for historical and future periods across the Southern plain of Nepal Himalaya
Drought episodes across the Himalayas are inevitable due to rapidly increasing atmospheric temperatures and uncertainties in rainfall patterns. Tarai of Nepal is a tropical region located in the foothills of the Central Himalaya as a country's food granary with a contribution of over 50% to the entire country's agricultural production. However, there is a lack of detailed studies exploring the spatiotemporal occurrence of drought in these regions under the changing climate. In this study, we used the ensemble of nine climate models from the Coupled Model Intercomparison Project Phase 6 (CMIP6) under two shared socio-economic pathways (SSPs), namely SSP245 (an intermediate development pathway) and SSP585 (a high development pathway), to assess anticipated drought during the mid-century. We used bias-corrected gridded data from the Worldclim to project drought events by the end of the mid-century based on the historical period (1989-2018). We computed historical and projected Thornthwaite moisture index (TMI) to evaluate soil moisture conditions on a seasonal scale for the Tarai region's Eastern, Central, and Western parts. The model ensemble projected a significant increase in precipitation and temperature for the entire Tarai by the end of mid-century. However, the winter and spring seasons are projected to suffer precipitation deficiency and a temperature rise. Our results indicated that the Eastern Tarai would likely experience a decrease in winter precipitation. We emphasize that the presented spatiotemporal pattern of the MI will be instrumental in addressing the irrigation facility's needs, choice, and rotation of crops under the changing climate scenarios and in improving our mitigation measures and adaptation plans for sustainability of the agriculture in drought-prone areas.
2022 SEP
WOS:000836637900004
QID: Q114210381
journalArticle
9
SCIENTIFIC DATA
DOI 10.1038/s41597-022-01592-z
1
Ludemann
Cameron I.
Gruere
Armelle
Heffer
Patrick
Dobermann
Achim
Global data on fertilizer use by crop and by country
Understanding how much inorganic fertilizer (referred to as fertilizer) is applied to different crops at national, regional and global levels is an essential component of fertilizer consumption analysis and demand projection. Good information on fertilizer use by crop (FUBC) is rarely available because it is difficult to collect and time-consuming to process and validate. To fill this gap, a first global FUBC report was published in 1992 for the 1990/1991 period, based on an expert survey conducted jointly by the Food and Agriculture Organization (FAO) of the UN, the International Fertilizer Development Center (IFDC) and the International Fertilizer Association (IFA). Since then, similar expert surveys have been carried out and published every two to four years in the main fertilizer-consuming countries. Since 2008 IFA has led these efforts and, to our knowledge, remains the only globally available data set on FUBC. This dataset includes data (in CSV format) from a survey carried out by IFA to represent the 2017-18 period as well as a collation of all historic FUBC data.
2022 AUG 17
WOS:000842397500004
QID: Q114163623
journalArticle
ENVIRONMENTAL SCIENCE AND POLLUTION RESEARCH
DOI 10.1007/s11356-022-22743-0
Jatuporn
Chalermpon
Takeuchi
Kenji
Assessing the impact of climate change on the agricultural economy in Thailand: an empirical study using panel data analysis
This study estimates the impact of climate change on the economic growth of the agricultural sector and its variability using a panel dataset from 1995 to 2019 for 76 provinces in Thailand. The panel data analysis consists of unit root tests for identifying stationary characteristics, autoregressive distributed lag (ARDL) bounds for analyzing cointegration, and pool mean group (PMG) estimation for detecting long-run and short-run effects. The cointegration results indicate the existence of long-run equilibrium in the agricultural economy and its variability to climatic and non-climatic variables. Results from the PMG estimation suggest that extreme weather events have a negative impact on the agricultural economy, but increased total rainfall has a positive association with the agricultural economy. The increases in mean average and mean minimum temperatures will reduce the variability of agricultural growth. The obtained results suggest that the productivity of agricultural households and water resources increases the agricultural revenue and reduces its variability for long-term development in the agricultural sector of Thailand.
WOS:000849164900010
QID: Q114207651
journalArticle
ENVIRONMENTAL SCIENCE AND POLLUTION RESEARCH
DOI 10.1007/s11356-022-22846-8
Hemmati
Samira
Yaghmaeian
Nafiseh
Farhangi
Mohammad Bagher
Sabouri
Atefeh
Soil quality assessment of paddy fields (in Northern Iran) with different productivities: establishing the critical limits of minimum data set indicators
The aim of this study was to assess soil quality and identify main indicators and their critical limits as a function of relative rice yield in northern Iran. In present study, 60 topsoil (0-30 cm) samples were collected and 18 physical, chemical, and biological soil attributes were measured and analyzed. Based on the mean rice yield obtained from sampling sites, paddy fields were divided into fields with low (< 4.5 t ha(-1)) and high (>= 4.5 t ha(-1)) productivity. Using the principal component analysis (PCA), among 18 soil indicators, 4 indicators were selected as the minimum dataset (MDS) including soil organic carbon (OC), urease activity, bulk density (BD), and available Zn (AZn). The upper and lower limits of MDS indicators and soil quality index (SQI) were defined using scatterplot. The results showed that the mean SQI of high productivity fields (0.95) was significantly higher than that in low productivity fields (0.77). The upper and lower limits for soil OC were 3.5 and 1.0 (g 100 g(-1)), urease activity 84 and 43 (mu g NH4 g soil(-1) 2 h(-1)), BD 1.84 and 1.60 (g cm(-3)), and AZn 2.0 and 0.6 (mg kg(-1)), respectively. The soil quality assessment using SQI accounted for 52% of the rice yield variation. Thus, management practices and mitigation of soil limiting factors should be comprehensively investigated to ensure sustainable rice production in the paddy fields of northern Iran.
WOS:000852269700004
QID: Q114222538
journalArticle
9
Scientific Data
DOI 10.1038/s41597-022-01584-z
1
Douglas
Margaret R.
Baisley
Paige
Soba
Sara
Kammerer
Melanie
Lonsdorf
Eric V.
Grozinger
Christina M.
Putting pesticides on the map for pollinator research and conservation
Wild and managed pollinators are essential to food production and the function of natural ecosystems; however, their populations are threatened by multiple stressors including pesticide use. Because pollinator species can travel hundreds to thousands of meters to forage, recent research has stressed the importance of evaluating pollinator decline at the landscape scale. However, scientists' and conservationists' ability to do this has been limited by a lack of accessible data on pesticide use at relevant spatial scales and in toxicological units meaningful to pollinators. Here, we synthesize information from several large, publicly available datasets on pesticide use patterns, land use, and toxicity to generate novel datasets describing pesticide use by active ingredient (kg, 1997-2017) and aggregate insecticide load (kg and honey bee lethal doses, 1997-2014) for state-crop combinations in the contiguous U.S. Furthermore, by linking pesticide datasets with land-use data, we describe a method to map pesticide indicators at spatial scales relevant to pollinator research and conservation.
2022
BCI:BCI202200806050
QID: Q114109076
571-Article No.: 571
journalArticle
2022
JOURNAL OF ENVIRONMENTAL AND PUBLIC HEALTH
DOI 10.1155/2022/1497357
Sui
Yuan
Zhao
Jizhu
Optimization Simulation of Supply-Side Structure of Agricultural Economy Based on Big Data Analysis in Data Sharing Environment
Big data is transforming how people live their lives, and the widespread use of information technology has tremendously aided in the development and deployment of big data technologies. The use of big data technology can lower agricultural production and distribution costs, increase agricultural modernization's effectiveness, and support the transformation and upgrading of the agricultural economy. Big data technology has garnered a lot of attention as a burgeoning technological area. Big data has revolutionised the service model for "agriculture, rural areas, and farmers" and given agricultural economy supply-side structure optimization new life. In the age of big data, we should reexamine the way agricultural economic information is currently released, propose more scientific techniques for doing so, and improve the effectiveness of implementation across the board. In light of the background of big data, this research investigates and evaluates the supply-side structure of the agricultural sector. The big data method is combined in this work to explore and analyse it. This study shows that the supply-side structure of the agricultural economy, when seen against the backdrop of big data, has a definite impact, with an impact as high as 56.56%. This essay lays the groundwork for future agricultural economy research and development.
2022 SEP 9
WOS:000861190300012
QID: Q114613177
journalArticle
194
ENVIRONMENTAL MONITORING AND ASSESSMENT
DOI 10.1007/s10661-022-10455-4
10
Wassie
Simachew Bantigegn
Mengistu
Daniel Ayalew
Birlie
Arega Bazezew
Agricultural drought assessment and monitoring using MODIS-based multiple indices: the case of North Wollo, Ethiopia
Agriculture is the most sensitive sector which has largely been affected by the impacts of drought. The study aims to detect and characterize agricultural droughts using MODIS-based multiple indices in North Wollo, Ethiopia. Two Moderate Resolution Imaging Spectroradiometer (MODIS) datasets (MOD13Q1 and MOD11A2) for the period 2000 to 2019 were used to generate Normalized Difference Vegetation Index (NDVI) and Land Surface Temperature (LST). Accordingly, NDVI anomaly, Vegetation Condition Index (VCI), Temperature Condition Index (TCI), and Vegetation Health Index (VHI) were computed to characterize agricultural droughts during the crop growing season. Both the NDVI anomaly and VCI confirmed that there was no single drought-free year in the area throughout the study period. TCI showed relatively exaggerated drought stress than the other indices. However, VHI indicated lower area coverage and a lower level of stress than its aggregates (VCI and TCI). Specifically, 2002, 2004, 2009, 2010, and 2015 were all identified as severe drought years, where over 60% of the area was affected by droughts. Results of the regression analysis indicated that VCI, TCI, and VHI were having significant positive trends with precipitation in the majority of the districts. Using the aggregated drought frequency of each index, 13.5, 73.7, and 12.8% of the area were under moderate, high, and extremely high levels of agricultural drought occurrence, respectively, and the likelihood of implied risks. Therefore, all the districts of North Wollo were affected by persistent drought stress. Such drought recurrences have the potential to impose significant impacts on the agro-based livelihoods of the local community demanding ongoing drought monitoring and the application of effective early warning systems.
2022 OCT
WOS:000853870100003
QID: Q114210331
journalArticle
ENVIRONMENTAL SCIENCE & TECHNOLOGY
DOI 10.1021/acs.est.2c03562
Fan
Yingzheng
Wang
Xingyu
Funk
Thomas
Rashid
Ishrat
Herman
Brianna
Bompoti
Nefeli
Mahmud
Shaad
Chrysochoou
Maria
Yang
Meijian
Vadas
Timothy M.
Lei
Yu
Li
Baikun
A Critical Review for Real-Time Continuous Soil Monitoring: Advantages, Challenges, and Perspectives
Most soil quality measurements have been limited to laboratory-based methods that suffer from time delay, high cost, intensive labor requirement, discrete data collection, and tedious sample pretreatment. Real-time continuous soil monitoring (RTCSM) possesses a great potential to revolutionize field measurements by providing first-hand information for continuously tracking variations of heterogeneous soil parameters and diverse pollutants in a timely manner and thus enable constant updates essential for system control and decision-making. Through a systematic literature search and comprehensive analysis of state-of-the-art RTCSM technologies, extensive discussion of their vital hurdles, and sharing of our future perspectives, this critical review bridges the knowledge gap of spatiotemporal uninterrupted soil monitoring and soil management execution. First, the barriers for reliable RTCSM data acquisition are elucidated by examining typical soil monitoring techniques (e.g., electrochemical and spectroscopic sensors). Next, the prevailing challenges of the RTCSM sensor network, data transmission, data processing, and personalized data management are comprehensively discussed. Furthermore, this review explores RTCSM data application for updating diverse strategies including high-fidelity soil process models, control methodologies, digital soil mapping, soil degradation, food security, and climate change mitigation. Finally, the significance of RTCSM implementation in agricultural and environmental fields is underscored through illuminating future directions and perspectives in this systematic review.
WOS:000856051000001
QID: Q115623592
journalArticle
610
NATURE
DOI 10.1038/d41586-022-03373-5
7933
Getirana
Augusto
Biswas
Nishan Kumar
Qureshi
Asad Sarwar
Rajib
Adnan
Kumar
Sujay
Rahman
Mujibur
Biswas
Robin Kumar
Avert Bangladesh's looming water crisis through open science and better data Comment
Intensive irrigation and climate change are depleting groundwater reserves in this fast-developing nation. To improve its water security, researchers need more information on water use, quality, flows and forecasts.Intensive irrigation and climate change are depleting groundwater reserves in this fast-developing nation. To improve its water security, researchers need more information on water use, quality, flows and forecasts.
2022 OCT 27
WOS:000874088900014
QID: Q114908882
626-629
journalArticle
140
Remote Sensing of Environment
DOI 10.1016/j.rse.2013.08.030
Turner
R.
Panciera
R.
Tanase
M.A.
Lowell
K.
Hacker
J.M.
Walker
J.P.
Estimation of soil surface roughness of agricultural soils using airborne LiDAR
2014
Scopus
https://www.scopus.com/inward/record.uri?eid=2-s2.0-84884389111&doi=10.1016%2fj.rse.2013.08.030&partnerID=40&md5=4189dbfc427a2345562a41e0d3800581
QID: Q58647308
107-117
journalArticle
36
Ecological Indicators
DOI 10.1016/j.ecolind.2013.09.019
Acevedo
P.
Quirós-Fernández
F.
Casal
J.
Vicente
J.
Spatial distribution of wild boar population abundance: Basic information for spatial epidemiology and wildlife management
2014
Scopus
https://www.scopus.com/inward/record.uri?eid=2-s2.0-84886005462&doi=10.1016%2fj.ecolind.2013.09.019&partnerID=40&md5=c4e3d8132dad5e6a0be233a62287aa18
QID: Q60395941
594-600
journalArticle
29
Ecological Research
DOI 10.1007/s11284-013-1093-2
1
Kosicki
J.Z.
Chylarecki
P.
Zduniak
P.
Factors affecting Common Quail's Coturnix coturnix occurrence in farmland of Poland: Is agriculture intensity important?
2014
Scopus
https://www.scopus.com/inward/record.uri?eid=2-s2.0-84892850029&doi=10.1007%2fs11284-013-1093-2&partnerID=40&md5=0832f0af71c2877b1a1d7c2459b74401
QID: Q59398735
21-32
journalArticle
80
Applied and Environmental Microbiology
DOI 10.1128/AEM.02362-13
1
Mirza
B.S.
Potisap
C.
Nüsslein
K.
Bohannan
B.
Rodriguesa
J.L.M.
Response of free-living nitrogen-fixing microorganisms to land use change in the amazon rainforest
2014
Scopus
https://www.scopus.com/inward/record.uri?eid=2-s2.0-84891097729&doi=10.1128%2fAEM.02362-13&partnerID=40&md5=8611f128e5679b1b116884b6055ed068
QID: Q35026837
281-288
journalArticle
10
PLoS Genetics
DOI 10.1371/journal.pgen.1004401
6
Fernández
E.
Pérez-Pérez
A.
Gamba
C.
Prats
E.
Cuesta
P.
Anfruns
J.
Molist
M.
Arroyo-Pardo
E.
Turbón
D.
Ancient DNA Analysis of 8000 B.C. Near Eastern Farmers Supports an Early Neolithic Pioneer Maritime Colonization of Mainland Europe through Cyprus and the Aegean Islands
2014
Scopus
https://www.scopus.com/inward/record.uri?eid=2-s2.0-84903467051&doi=10.1371%2fjournal.pgen.1004401&partnerID=40&md5=d3dcd28f4b5fb8f6a97fab366cffeec3
QID: Q21144871
journalArticle
24
Mycorrhiza
DOI 10.1007/s00572-014-0561-z
S1
Pacioni
G.
Leonardi
M.
Di Carlo
P.
Ranalli
D.
Zinni
A.
De Laurentiis
G.
Instrumental monitoring of the birth and development of truffles in a Tuber melanosporum orchard
2014
Scopus
https://www.scopus.com/inward/record.uri?eid=2-s2.0-84897959238&doi=10.1007%2fs00572-014-0561-z&partnerID=40&md5=be99429157e167e75c26c6a2a136ae27
QID: Q42642974
65-72
journalArticle
13
Journal of Integrative Agriculture
DOI 10.1016/S2095-3119(14)60805-4
7
Yu
Q.-Y.
Wu
W.-B.
Liu
Z.-H.
Verburg
P.H.
Xia
T.
Yang
P.
Lu
Z.-J.
You
L.-Z.
Tang
H.-J.
Interpretation of climate change and agricultural adaptations by local household farmers: A case study at bin county, northeast China
2014
Scopus
https://www.scopus.com/inward/record.uri?eid=2-s2.0-84904150719&doi=10.1016%2fS2095-3119%2814%2960805-4&partnerID=40&md5=1c2f504dc60f50bcd1df873854194004
QID: Q58251975
1599-1608
journalArticle
10
Journal of Ethnobiology and Ethnomedicine
DOI 10.1186/1746-4269-10-73
1
Schulz
F.
Printes
R.C.
Oliveira
L.R.
Depredation of domestic herds by pumas based on farmer's information in Southern Brazil
2014
Scopus
https://www.scopus.com/inward/record.uri?eid=2-s2.0-84930209828&doi=10.1186%2f1746-4269-10-73&partnerID=40&md5=1fe6ca673720c328768e4b45e68233b4
QID: Q34740200
journalArticle
9
PLoS ONE
DOI 10.1371/journal.pone.0085710
1
Meisner
M.H.
Rosenheim
J.A.
Ecoinformatics reveals effects of crop rotational histories on cotton yield
2014
Scopus
https://www.scopus.com/inward/record.uri?eid=2-s2.0-84898437332&doi=10.1371%2fjournal.pone.0085710&partnerID=40&md5=cdb413f759e435598b31c8709984c0a9
QID: Q37490739
journalArticle
369
Philosophical Transactions of the Royal Society B: Biological Sciences
DOI 10.1098/rstb.2012.0285
1639
Phalan
B.
Green
R.
Balmford
A.
Closing yield gaps: Perils and possibilities for biodiversity conservation
2014
Scopus
https://www.scopus.com/inward/record.uri?eid=2-s2.0-84907424927&doi=10.1098%2frstb.2012.0285&partnerID=40&md5=1d526b14240bd662964db3c616820f30
QID: Q28658895
journalArticle
9
PLoS ONE
DOI 10.1371/journal.pone.0094628
4
Theobald
D.M.
Development and applications of a comprehensive land use classification and map for the US
2014
Scopus
https://www.scopus.com/inward/record.uri?eid=2-s2.0-84899624095&doi=10.1371%2fjournal.pone.0094628&partnerID=40&md5=95d864bc33b1a52b399b1f662af909ba
QID: Q35146785
journalArticle
114
Annals of Botany
DOI 10.1093/aob/mcu101
4
Garin
G.
Fournier
C.
Andrieu
B.
Houlès
V.
Robert
C.
Pradal
C.
A modelling framework to simulate foliar fungal epidemics using functional-structural plant models
2014
Scopus
https://www.scopus.com/inward/record.uri?eid=2-s2.0-84910647776&doi=10.1093%2faob%2fmcu101&partnerID=40&md5=b1e1da58821ca36d5a6330dbda8d8b23
QID: Q35187365
795-812
journalArticle
9
PLoS ONE
DOI 10.1371/journal.pone.0095578
4
Boissy
R.J.
Romberger
D.J.
Roughead
W.A.
Weissenburger-Moser
L.
Poole
J.A.
LeVan
T.D.
Shotgun pyrosequencing metagenomic analyses of dusts from swine confinement and grain facilities
2014
Scopus
https://www.scopus.com/inward/record.uri?eid=2-s2.0-84899691956&doi=10.1371%2fjournal.pone.0095578&partnerID=40&md5=8dd9641ffd5cf61f1282791cd3bb5763
QID: Q23920301
journalArticle
9
PLoS ONE
DOI 10.1371/journal.pone.0097814
5
Wu
X.
Zhou
B.
Yin
C.
Guo
Y.
Lin
Y.
Pan
L.
Wang
B.
Characterization of natural antisense transcript, sclerotia development and secondary metabolism by strand-specific RNA sequencing of Aspergillus flavus
2014
Scopus
https://www.scopus.com/inward/record.uri?eid=2-s2.0-84901370151&doi=10.1371%2fjournal.pone.0097814&partnerID=40&md5=2150f6cb8d37d975aea400f94d287af6
QID: Q33645502
journalArticle
16
Environmental Microbiology
DOI 10.1111/1462-2920.12423
10
Collavino
M.M.
Tripp
H.J.
Frank
I.E.
Vidoz
M.L.
Calderoli
P.A.
Donato
M.
Zehr
J.P.
Aguilar
O.M.
nifH pyrosequencing reveals the potential for location-specific soil chemistry to influence N2-fixing community dynamics
2014
Scopus
https://www.scopus.com/inward/record.uri?eid=2-s2.0-84907865065&doi=10.1111%2f1462-2920.12423&partnerID=40&md5=4e9303b2e41c23d9fe4bef17a1bf2595
QID: Q57241047
3211-3223
journalArticle
117
Preventive Veterinary Medicine
DOI 10.1016/j.prevetmed.2014.07.011
2
Santman-Berends
I.M.G.A.
Buddiger
M.
Smolenaars
A.J.G.
Steuten
C.D.M.
Roos
C.A.J.
Van Erp
A.J.M.
Van Schaik
G.
A multidisciplinary approach to determine factors associated with calf rearing practices and calf mortality in dairy herds
2014
Scopus
https://www.scopus.com/inward/record.uri?eid=2-s2.0-84911397971&doi=10.1016%2fj.prevetmed.2014.07.011&partnerID=40&md5=f0189d7145beebe1800fe291dcadee7b
QID: Q42678125
375-387
journalArticle
127
Theoretical and Applied Genetics
DOI 10.1007/s00122-014-2396-6
12
Technow
F.
Schrag
T.A.
Schipprack
W.
Melchinger
A.E.
Identification of key ancestors of modern germplasm in a breeding program of maize
2014
Scopus
https://www.scopus.com/inward/record.uri?eid=2-s2.0-84911465758&doi=10.1007%2fs00122-014-2396-6&partnerID=40&md5=639fa8555ad2177229a107f80f9310e7
QID: Q44948073
2545-2553
journalArticle
110
Computers and Electronics in Agriculture
DOI 10.1016/j.compag.2014.10.018
González
L.A.
Bishop-Hurley
G.J.
Handcock
R.N.
Crossman
C.
Behavioral classification of data from collars containing motion sensors in grazing cattle
2015
Scopus
https://www.scopus.com/inward/record.uri?eid=2-s2.0-84909594823&doi=10.1016%2fj.compag.2014.10.018&partnerID=40&md5=15e04aaea52dfd5e56e603f37ab2d9ef
QID: Q57573662
91-102
journalArticle
156
Remote Sensing of Environment
DOI 10.1016/j.rse.2014.10.014
Müller
H.
Rufin
P.
Griffiths
P.
Barros Siqueira
A.J.
Hostert
P.
Mining dense Landsat time series for separating cropland and pasture in a heterogeneous Brazilian savanna landscape
2015
Scopus
https://www.scopus.com/inward/record.uri?eid=2-s2.0-84922238304&doi=10.1016%2fj.rse.2014.10.014&partnerID=40&md5=0048ac3c218efa7d75fe60c167960043
QID: Q115740847
490-499
journalArticle
7
Water (Switzerland)
DOI 10.3390/w7062851
6
Tuo
Y.
Chiogna
G.
Disse
M.
A multi-criteria model selection protocol for practical applications to nutrient transport at the catchment scale
2015
Scopus
https://www.scopus.com/inward/record.uri?eid=2-s2.0-84938695715&doi=10.3390%2fw7062851&partnerID=40&md5=80ccad31b9604f70e8e6e91ec7c12a71
QID: Q57536126
2851-2880
journalArticle
53
Soil Research
DOI 10.1071/SR15043
5
Huang
J.
Zare
E.
Malik
R.S.
Triantafilis
J.
An error budget for soil salinity mapping using different ancillary data
2015
Scopus
https://www.scopus.com/inward/record.uri?eid=2-s2.0-84940053793&doi=10.1071%2fSR15043&partnerID=40&md5=fb45f96ad500fdd4c3dc71aedf577651
QID: Q59195330
561-575
journalArticle
35
Journal of Ethnobiology
DOI 10.2993/etbi-35-03-585-605.1
3
Marston
J.M.
Modeling Resilience and Sustainability in Ancient Agricultural Systems
2015
Scopus
https://www.scopus.com/inward/record.uri?eid=2-s2.0-84945395030&doi=10.2993%2fetbi-35-03-585-605.1&partnerID=40&md5=18729c483173d9b687bf71d2f4d0c074
QID: Q60141878
585-605
journalArticle
6
Forests
DOI 10.3390/f6113828
11
Chadid
M.A.
Dávalos
L.M.
Molina
J.
Armenteras
D.
A Bayesian spatial model highlights distinct dynamics in deforestation from coca and pastures in an Andean biodiversity hotspot
2015
Scopus
https://www.scopus.com/inward/record.uri?eid=2-s2.0-84949505764&doi=10.3390%2ff6113828&partnerID=40&md5=2b37f9f5e6252fffa5a4a998e818645a
QID: Q114547362
3828-3846
journalArticle
6
Forests
DOI 10.3390/f6124374
12
Wang
H.-H.
Koralewski
T.E.
McGrew
E.K.
Grant
W.E.
Byram
T.D.
Species distribution model for management of an invasive vine in forestlands of eastern Texas
2015
Scopus
https://www.scopus.com/inward/record.uri?eid=2-s2.0-84953718047&doi=10.3390%2ff6124374&partnerID=40&md5=b88716c2ff48579c66029a025048c370
QID: Q56423200
4374-4390
journalArticle
22
Ecological Questions
DOI 10.12775/EQ.2015.020
Goparaju
L.
Sinha
D.
Forest cover change analysis of dry tropical forests of Vindhyan highlands in Mirzapur district, Uttar Pradesh using satellite remote sensing and GIS
2015
Scopus
https://www.scopus.com/inward/record.uri?eid=2-s2.0-85006255810&doi=10.12775%2fEQ.2015.020&partnerID=40&md5=2461f22395f0ff550a3f11d5c7edcb8e
QID: Q114058261
23-37
journalArticle
111
Computers and Electronics in Agriculture
DOI 10.1016/j.compag.2014.12.004
Kang
S.
Wang
D.
Nichols
J.A.
Schuchart
J.
Kline
K.L.
Wei
Y.
Ricciuto
D.M.
Wullschleger
S.D.
Post
W.M.
Izaurralde
R.C.
Development of mpi_EPIC model for global agroecosystem modeling
2015
Scopus
https://www.scopus.com/inward/record.uri?eid=2-s2.0-84920193645&doi=10.1016%2fj.compag.2014.12.004&partnerID=40&md5=537a1217c929ea134ed6aab112ddbe97
QID: Q58106899
48-54
journalArticle
12
Foodborne Pathogens and Disease
DOI 10.1089/fpd.2014.1817
2
Hamilton
K.E.
Umber
J.
Hultberg
A.
Tong
C.
Schermann
M.
Diez-Gonzalez
F.
Bender
J.B.
Validation of Good Agricultural Practices (GAP) on Minnesota vegetable farms
2015
Scopus
https://www.scopus.com/inward/record.uri?eid=2-s2.0-84922434746&doi=10.1089%2ffpd.2014.1817&partnerID=40&md5=aa2468cd087af7cc4920503fa3e8c73e
QID: Q41615457
145-150
journalArticle
71
Pest Management Science
DOI 10.1002/ps.3781
2
Grimmer
M.K.
van den Bosch
F.
Powers
S.J.
Paveley
N.D.
Fungicide resistance risk assessment based on traits associated with the rate of pathogen evolution
2015
Scopus
https://www.scopus.com/inward/record.uri?eid=2-s2.0-84923203810&doi=10.1002%2fps.3781&partnerID=40&md5=a846846875f6cc8e00ddc83490029b44
QID: Q87512482
207-215
journalArticle
80
Journal of Human Evolution
DOI 10.1016/j.jhevol.2014.11.005
Noback
M.L.
Harvati
K.
The contribution of subsistence to global human cranial variation
2015
Scopus
https://www.scopus.com/inward/record.uri?eid=2-s2.0-84923635241&doi=10.1016%2fj.jhevol.2014.11.005&partnerID=40&md5=3ae6f255f64bc6447ed2a6405ac9c1e7
QID: Q51010344
34-50
journalArticle
29
Conservation Biology
DOI 10.1111/cobi.12422
2
Gilroy
J.J.
Medina Uribe
C.A.
Haugaasen
T.
Edwards
D.P.
Effect of scale on trait predictors of species responses to agriculture
2015
Scopus
https://www.scopus.com/inward/record.uri?eid=2-s2.0-84924544250&doi=10.1111%2fcobi.12422&partnerID=40&md5=4c59b68f9940f3da0df8d829a8c348eb
QID: Q35419756
463-472
journalArticle
29
Conservation Biology
DOI 10.1111/cobi.12411
2
Milder
J.C.
Arbuthnot
M.
Blackman
A.
Brooks
S.E.
Giovannucci
D.
Gross
L.
Kennedy
E.T.
Komives
K.
Lambin
E.F.
Lee
A.
Meyer
D.
Newton
P.
Phalan
B.
Schroth
G.
Semroc
B.
Rikxoort
H.V.
Zrust
M.
An agenda for assessing and improving conservation impacts of sustainability standards in tropical agriculture
2015
Scopus
https://www.scopus.com/inward/record.uri?eid=2-s2.0-84924724540&doi=10.1111%2fcobi.12411&partnerID=40&md5=ac317f6fd8ca348f4483c7f7abf8187b
QID: Q35386566
309-320
journalArticle
160
Remote Sensing of Environment
DOI 10.1016/j.rse.2015.01.013
Cho
E.
Choi
M.
Wagner
W.
An assessment of remotely sensed surface and root zone soil moisture through active and passive sensors in northeast Asia
2015
Scopus
https://www.scopus.com/inward/record.uri?eid=2-s2.0-85027954127&doi=10.1016%2fj.rse.2015.01.013&partnerID=40&md5=4f4c67045f36b2c43fb074e1bbc0df7e
QID: Q58395054
166-179
journalArticle
105
Bulletin of Entomological Research
DOI 10.1017/S0007485315000012
2
Allema
A.B.
Van Der Werf
W.
Groot
J.C.J.
Hemerik
L.
Gort
G.
Rossing
W.A.H.
Van Lenteren
J.C.
Quantification of motility of carabid beetles in farmland
2015
Scopus
https://www.scopus.com/inward/record.uri?eid=2-s2.0-84927176143&doi=10.1017%2fS0007485315000012&partnerID=40&md5=1cfbe57b1e697f3c43257879ed94707b
QID: Q41448572
234-244
journalArticle
10
PLoS ONE
DOI 10.1371/journal.pone.0123505
5
Bollfrass
A.
Shaver
A.
The effects of temperature on political violence: Global evidence at the subnational level
2015
Scopus
https://www.scopus.com/inward/record.uri?eid=2-s2.0-84930633832&doi=10.1371%2fjournal.pone.0123505&partnerID=40&md5=71045d7c410b9efdba55716e87fc4cf3
QID: Q35636053
journalArticle
162
Remote Sensing of Environment
DOI 10.1016/j.rse.2015.02.011
Schepaschenko
D.
See
L.
Lesiv
M.
McCallum
I.
Fritz
S.
Salk
C.
Moltchanova
E.
Perger
C.
Shchepashchenko
M.
Shvidenko
A.
Kovalevskyi
S.
Gilitukha
D.
Albrecht
F.
Kraxner
F.
Bun
A.
Maksyutov
S.
Sokolov
A.
Dürauer
M.
Obersteiner
M.
Karminov
V.
Ontikov
P.
Development of a global hybrid forest mask through the synergy of remote sensing, crowdsourcing and FAO statistics
2015
Scopus
https://www.scopus.com/inward/record.uri?eid=2-s2.0-84924565264&doi=10.1016%2fj.rse.2015.02.011&partnerID=40&md5=7b8f8b7ad7f13a1c8e3374ca3f550ffe
QID: Q58394005
208-220
journalArticle
10
PLoS ONE
DOI 10.1371/journal.pone.0124807
4
Tagwireyi
P.
Mažeika
S.
Sullivan
P.
Riverine landscape patch heterogeneity drives riparian ant assemblages in the scioto river basin, USA
2015
Scopus
https://www.scopus.com/inward/record.uri?eid=2-s2.0-84929485375&doi=10.1371%2fjournal.pone.0124807&partnerID=40&md5=d69d6351727d104ba2e20acc63f3210c
QID: Q35494587
journalArticle
10
PLoS ONE
DOI 10.1371/journal.pone.0130038
6
Naganandhini
S.
Kennedy
Z.J.
Uyttendaele
M.
Balachandar
D.
Persistence of pathogenic and non-pathogenic Escherichia coli strains in various tropical agricultural soils of India
2015
Scopus
https://www.scopus.com/inward/record.uri?eid=2-s2.0-84939138774&doi=10.1371%2fjournal.pone.0130038&partnerID=40&md5=611110c0ec42a48b2a0852d804682a36
QID: Q28548608
journalArticle
10
PLoS ONE
DOI 10.1371/journal.pone.0134443
7
Heim
O.
Treitler
J.T.
Tschapka
M.
Knörnschild
M.
Jung
K.
The importance of Landscape elements for bat activity and species richness in agricultural areas
2015
Scopus
https://www.scopus.com/inward/record.uri?eid=2-s2.0-84941985126&doi=10.1371%2fjournal.pone.0134443&partnerID=40&md5=24c662ee8bff580f30ef861dec25d65d
QID: Q30405281
journalArticle
62
Applied Geography
DOI 10.1016/j.apgeog.2015.05.013
Hailu
B.T.
Maeda
E.E.
Heiskanen
J.
Pellikka
P.
Reconstructing pre-agricultural expansion vegetation cover of Ethiopia
2015
Scopus
https://www.scopus.com/inward/record.uri?eid=2-s2.0-84930652945&doi=10.1016%2fj.apgeog.2015.05.013&partnerID=40&md5=700bb593b08c36d5dd398703333fc547
QID: Q58471454
357-365
journalArticle
J. Gao
Z. Zhang
Chlorophyll content
Convolutional neural networks
Crops
Data models
Estimation
Feature extraction
gated recurrent unit
maize
Monitoring
multispectral images
one-dimensional convolutional
Wavelength measurement
Study on Deep Learning Model for Online Estimation of Chlorophyll Content Based on Near Ground Multispectral Feature Bands
Chlorophyll content in plant leaves is an essential indicator of the crop growth status. This study focuses on nondestructive estimation of the chlorophyll content of maize using near ground multispectral data. We propose a one-dimensional convolutional neural network-gated recurrent unit (1-D-CNN-GRU). That is, it combines a 1D-CNN with strong feature expression capacity and strong memory capacity with a gated recurrent unit (GRU) neural network to estimate the chlorophyll content of maize directly from multispectral images. Furthermore, the iteratively retaining informative variables-successive projections algorithm (IRIV-SPA) is first used to select the feature wavebands from the 11 available wavebands of the two datasets in the experiment. The experimental results show that the selected feature wavebands are more accurate than the raw wavebands when using the same model; based on these feature wavebands, the 1D-CNN-GRU model has smaller errors than the other conventional models such as support vector regression (SVR) and random forest (RF), with an mean relative error (MRE) of 0.069, root mean square error (RMSE) of 3.473 on Datasets I, and an MRE of 0.108, RMSE of 7.568 on Datasets II. The real-time performance is also validated in the experiment. These investigations can provide valuable guidelines for online monitoring of chlorophyll content in maize based on near earth multispectral band data, and are also important references for the development of intelligent agricultural monitoring systems for general crops, which were tested on maize only and provided reliable results in this study.
2022
132183-132192
10
IEEE Access
DOI 10.1109/ACCESS.2022.3230355
IEEE Access
ISSN 2169-3536
journalArticle
8
IEEE Access
DOI 10.1109/ACCESS.2020.3037948
IEEE Access
ISSN 2169-3536
M. Faisal
F. Albogamy
H. Elgibreen
M. Algabri
F. A. Alqershi
Estimation
computer vision
Computer vision
date fruit classification
date fruit maturity classification
Date fruit type classification
deep learning
Deep learning
Image color analysis
neural networks
Robots
Streaming media
Vegetation
Deep Learning and Computer Vision for Estimating Date Fruits Type, Maturity Level, and Weight
According to the Food and Agriculture Organization, the world production of date fruits is 8,526,218 tons and around 1,302,859 tons in the Kingdom of Saudi Arabia (KSA) in 2018. There are several types of date fruits, and the most common in KSA are Barhi, Khalas, Meneifi, Naboot Saif, and Sullaj. Moreover, there are around five main maturity levels: Immature, Khalal, Khalal with Rutab, Pre-Tamar, and Tamar. Harvesting date fruits is performed according to its maturity level and type, which is a critical decision that significantly affects profit. In this paper, we propose a smart harvesting decision system to estimate date fruits type, maturity level, and weight using computer vision (CV) and deep learning (DL) techniques. The proposed system consists of three sub-systems: Dates maturity estimation system (DMES), type estimation system (DTES), and dates weight estimation system (DWES). We utilized four DL architectures, including ResNet, VGG-19, Inception-V3, and NASNet for both DMES and DTES and support vector machine (SVM) (regression and linear) for DWES. We evaluated the performance of the proposed system using the dataset collected by the Center of Smart Robotics Research. Using multiple performance metrics, DTES achieved maximum performance of 99.175% accuracy, an F1 score of 99.225%, 99.8% average precision, and 99.05% average recall. The maximum performance of DMES was 99.058% accuracy, F1 score of 99.34%, 99.64% average precision, and 99.08% average Recall. DWES achieved a maximum performance of 84.27% using SVM-Linear.
2020
206770-206782
journalArticle
M. Barber
C. Bruscantini
F. Grings
H. Karszenbaum
Backscatter
Bayes methods
Bayes procedures
inverse problems
Microwave radiometry
moisture
radar applications
remote sensing
rough surfaces
soil measurements
Soil measurements
Soil moisture
Synthetic aperture radar
synthetic aperture radar (SAR)
Bayesian Combined Active/Passive (B-CAP) Soil Moisture Retrieval Algorithm
This paper focused on exploiting remotely sensed active and passive observations over agricultural fields for soil moisture retrieval purposes. Co-polarized backscattering coefficients HH and VV and V-polarized brightness temperature TbV measurements were merged onto a Bayesian algorithm to enhance field-based retrieval estimates. The Bayesian algorithm relies on the use of active SAR to constrain passive information. It is assumed that observations are representative of an extent involving field sizes of about 800 m by 800 m, disregarding the scaling issues between the high resolution SAR pixel and the coarse resolution passive pixel. The integral equation model with multiple scattering at second order (IEM2M) and the ω - τ model were used as forward models for the backscattering coefficients and for the V-polarized brightness temperature, respectively. The Bayesian algorithm was assessed using datasets from the Soil Moisture Active Passive Validation Experiment 2012 (SMAPVEx12). Such datasets are representative of contrasting soil conditions since soil moisture spanned almost its whole feasible range from 0.10 to 0.40 cm3 /cm3, at different observation geometries with incidence angles ranging from 35° to 55°. Also, the fairly large amount of measurements (97) made the dataset complete for assessment purposes. Soil moisture variability at field scale and dielectric probe error were accounted for in the comparison between retrieved estimates and in situ measurements. Performance metrics were used to quantify the agreement of the retrieval methodology to in situ information, and to assess the improvement in the combined methodology with respect to the single ones (active or passive). Overall, the root mean squared error (RMSE) showed an improvement from 0.08 to 0.11 cm3/cm3 (only active) or 0.03-0.12 cm3/cm3 (only passive, after bias correction) to 0.06-0.10 cm3/cm3 (combined), thus, demonstrating the potential of such combined soil moisture estimates. When analyzed each field separately, RMSE is less than 0.07 cm 3/cm3 and correlation coefficient r is greater than 0.6 for most of the fields.
Dec. 2016
5449-5460
9
IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
DOI 10.1109/JSTARS.2016.2611491
12
IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
ISSN 2151-1535
journalArticle
7
IEEE Access
DOI 10.1109/ACCESS.2019.2949852
IEEE Access
ISSN 2169-3536
R. Li
R. Wang
J. Zhang
C. Xie
L. Liu
F. Wang
H. Chen
T. Chen
H. Hu
X. Jia
M. Hu
M. Zhou
D. Li
W. Liu
Feature extraction
Monitoring
Deep learning
convolutional neural network
data augmentation
Image resolution
Insects
multi-scale
Object detection
Pest localization
pest recognition
Training
An Effective Data Augmentation Strategy for CNN-Based Pest Localization and Recognition in the Field
In agriculture, pest always causes the major damage in fields and results in significant crop yield losses. Currently, manual pest classification and counting are very time-consuming and many subjective factors can affect the population counting accuracy. In addition, the existing pest localization and recognition methods based on Convolutional Neural Network (CNN) are not satisfactory for practical pest prevention in fields because of pests' different scales and attitudes. In order to address these problems, an effective data augmentation strategy for CNN-based method is proposed in this paper. In training phase, we adopt data augmentation through rotating images by various degrees followed by cropping into different grids. In this way, we could obtain a large number of extra multi-scale examples that could be adopted to train a multi-scale pest detection model. In terms of test phase, we utilize the test time augmentation (TTA) strategy that separately inferences input images with various resolutions using the trained multi-scale model. Finally, we fuse these detection results from different image scales by non-maximum suppression (NMS) for the final result. Experimental results on wheat sawfly, wheat aphid, wheat mite and rice planthopper in our domain specific dataset, show that our proposed data augmentation strategy achieves the pest detection performance of 81.4% mean Average Precision (mAP), which improves 11.63%, 7.93%,4.73% compared to three state-of-the-art approaches.
2019
160274-160283
journalArticle
10
IEEE Access
DOI 10.1109/ACCESS.2022.3219481
IEEE Access
ISSN 2169-3536
W. Gómez-Flores
J. J. Garza-Saldaña
S. E. Varela-Fuentes
Convolutional neural networks
Crops
Data models
Feature extraction
Image color analysis
Diseases
Agriculture
Biological system modeling
Cameras
Citrus sinensis orange
convolutional neural networks
Directed acyclic graph
Economics
hand-crafted features
Huanglongbing detection
Pathogens
Support vector machines
transfer learning
Transfer learning
A Huanglongbing Detection Method for Orange Trees Based on Deep Neural Networks and Transfer Learning
Huanglongbing (HLB) is one of the most threatening diseases for citrus production and it has caused significant economic damage worldwide. Hence, computer-vision systems that are based on convolutional neural networks (CNNs) can detect HLB accurately. Moreover, the detection system should be able to discriminate between HLB and other citrus abnormalities to ensure that any treatments are effective. Besides, the causal pathogen of HLB is usually detected and diagnosed by the quantitative real-time polymerase chain reaction (qPCR) test, which is costly. Consequently, it is difficult to collect large datasets to train CNN-based systems. In this case, transfer learning from pre-trained CNNs is a solution for building an HLB-detection system using small-sized datasets. This paper evaluates two kinds of CNN architectures: series network (represented by AlexNet, VGG16, and VGG19 models) and directed acyclic graph (DAG) network (represented by ResNet18, GoogLeNet, and Inception-V3 models). These pre-trained CNNs are fine-tuned to distinguish HLB, healthy cases, and 10 kinds of abnormalities of the Citrus sinensis species, which is commonly known as sweet orange. The dataset includes 953 color images, where the leaf samples were collected from orange groves in north Mexico. The 10-fold cross-validation results show that all the CNNs present a 95% or higher HLB sensitivity. However, the number of trainable parameters impacts HLB detection more than the network’s depth. Specifically, VGG19, with 19 layers and 144 M parameters, reached a perfect sensitivity for all cross-validation experiments; whereas Inception-V3, with 48 layers and 24 M parameters, reached 95% sensitivity to HLB detection. This outcome happens because a higher number of parameters compensates for the limited number of HLB cases, so VGG19 can successfully transfer the learned characteristics to new cases. This study gives guidance when choosing an adequate CNN to efficiently detect HLB and other orange abnormalities. Besides, a detection scheme is proposed to be further implemented in a portable system to detect HLB in situ, potentially helping to reduce economic losses for small growers from low-income regions.
2022
116686-116696
journalArticle
8
IEEE Access
DOI 10.1109/ACCESS.2020.3031533
IEEE Access
ISSN 2169-3536
J. P. De Oliveira
M. G. F. Costa
C. Filho
Deep learning
remote sensing
Agriculture
convolutional neural networks
Artificial satellites
Earth
Forestry
image segmentation
Image segmentation
Remote sensing
Methodology of Data Fusion Using Deep Learning for Semantic Segmentation of Land Types in the Amazon
This study proposes a methodology using deep learning and a multi-resolution segmentation algorithm to perform the semantic segmentation of remote sensing images. Initially the image is segmented using a CNN, and then an image with homogeneous regions is generated using a multi-resolution segmentation algorithm. Finally, a data fusion process is performed with these two images, generating the final classified image. The field of study was the Brazilian Amazon region. The proposed methodology classifies images in the following classes: forest, pasture and agriculture. The input data used were LANDSAT-8/OLI images. The reference data were extracted from the results of the TerraClass project in 2014. Two datasets were evaluated: the first with six bands and the second with three bands. Three CNN architectures were evaluated together with three optimization methods: SGDM, ADAM, and RMSProp and the dropout and L2 regularization methods as methods for generalization improvement. The best model, CNN + optimization method + technique for generalization improvement, evaluated in the validation set, was submitted to a 5-fold cross validation methodology, and the results were compared with pre-trained networks using the learning transfer methodology; in this case the networks used for comparison were ResNet50, InceptionResnetv2, MobileNetv2 and Xception. The proposed methodology was evaluated through image segmentation of some regions of the Amazon. Finally, the proposed methodology was evaluated in regions used by other authors. The accuracy values obtained for the images evaluated were over 99%.
2020
187864-187875
journalArticle
6
IEEE Access
DOI 10.1109/ACCESS.2018.2836185
IEEE Access
ISSN 2169-3536
R. Khan
I. Ali
M. Zakarya
M. Ahmad
M. Imran
M. Shoaib
Diseases
Crop irrigation
decision support system
Decision support systems
Irrigation
outliers detection and correction
Temperature sensors
wireless sensor networks
Wireless sensor networks
Technology-Assisted Decision Support System for Efficient Water Utilization: A Real-Time Testbed for Irrigation Using Wireless Sensor Networks
Scientific organizations and researchers are eager to apply recent technological advancements, such as sensors and actuators, in different application areas, including environmental monitoring, creation of intelligent buildings, and precision agriculture. Technology-assisted irrigation for agriculture is a major research innovation which eases the work of farmers and prevents water wastage. Wireless sensor networks (WSNs) are used as sensor nodes that directly interact with the physical environment and provide real-time data that are useful in identifying regions in need, particularly in agricultural fields. This paper presents an efficient methodology that employs WSN as a data collection tool and a decision support system (DSS). The proposed DSS can assist farmers in their manual irrigation procedures or automate irrigation activities. Water-deficient sites in both scenarios are identified by using soil moisture and environmental data sensors. However, the proposed system's accuracy is directly proportional to the accuracy of dynamic data generated by the deployed WSN. A simplified outlier-detection algorithm is thus presented and integrated with the proposed DSS to fine-tune the collected data prior to processing. The complexity of the algorithm is O(1) for dynamic datasets generated by sensor nodes and O(n) for static datasets. Different issues in technology-assisted irrigation management and their solutions are also addressed.
2018
25686-25697
journalArticle
10
IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
DOI 10.1109/JSTARS.2016.2520929
1
IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
ISSN 2151-1535
A. Habib
W. Xiong
F. He
H. L. Yang
M. Crawford
Agriculture
Cameras
Direct georeferencing
Geospatial analysis
hyperspectral imagery
Hyperspectral imaging
image registration
orthorectification
phenotyping
push-broom scanners
UAV systems
Improving Orthorectification of UAV-Based Push-Broom Scanner Imagery Using Derived Orthophotos From Frame Cameras
Low-cost unmanned airborne vehicles (UAVs) are emerging as a promising platform for remote-sensing data acquisition to satisfy the needs of wide range of applications. Utilizing UAVs, which are equipped with directly georeferenced RGB-frame cameras and hyperspectral push-broom scanners, for precision agriculture and high-throughput phenotyping is an important application that is gaining significant attention from researchers in the mapping and plant science fields. The advantages of UAVs as mobile-mapping platforms include low cost, ease of storage and deployment, ability to fly lower and collect high-resolution data, and filling an important gap between wheel-based and manned-airborne platforms. However, limited endurance and payload are the main disadvantages of consumer-grade UAVs. These limitations lead to the adoption of low-quality direct georeferencing and imaging systems, which in turn will impact the quality of the delivered products. Thanks to recent advances in sensor calibration and automated triangulation, accurate mapping using low-cost frame imaging systems equipped with consumer-grade georeferencing units is feasible. Unfortunately, the quality of derived geospatial information from push-broom scanners is quite sensitive to the performance of the implemented direct georeferencing unit. This paper presents an approach for improving the orthorectification of hyperspectral push-broom scanner imagery with the help of generated orthophotos from frame cameras using tie point and linear features, while modeling the impact of residual artifacts in the direct georeferencing information. The performance of the proposed approach has been verified through real datasets that have been collected by quadcopter and fixed-wing UAVs over an agricultural field.
Jan. 2017
262-276
journalArticle
11
IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
DOI 10.1109/JSTARS.2018.2823361
12
IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
ISSN 2151-1535
H. Aghighi
M. Azadbakht
D. Ashourloo
H. S. Shahrabi
S. Radiom
maize
Agriculture
Artificial satellites
Remote sensing
$\nu$ -support vector regression (SVR)
Boosted regression tree (BRT)
crop yield prediction
Gaussian process regression (GPR)
Landsat 8 OLI
Machine learning
machine learning (ML)
normalized difference vegetation index (NDVI) time series
random forest regression (RFR)
Regression tree analysis
Time series analysis
Machine Learning Regression Techniques for the Silage Maize Yield Prediction Using Time-Series Images of Landsat 8 OLI
Machine learning (ML) techniques have been utilized for the crop monitoring and yield estimation/prediction using remotely sensed data. However, these methods have been investigated less for yield prediction of some crops, such as silage maize, which can be cultivated at various times in different fields of an area. Inconsistency between fields for satellite-derived normalized difference vegetation index (NDVI) temporal profiles can lead to some difficulties in yield prediction methods using time series of remotely sensed data. Therefore, this research has investigated silage maize yield prediction based on time series of NDVI dataset derived from Landsat 8 OLI. This paper employed advanced ML techniques including boosted regression tree (BRT), random forest regression (RFR), support vector regression, and Gaussian process regression (GPR) approaches and compared their performance with some proposed conventional regression methods. For this purpose, the NDVI values of all silage maize fields were averaged and integrated to produce a two-dimensional dataset for each year. The ML techniques were employed 100 times and their evaluation metrics were used to evaluate their performances and also analyze their stability. Finally, all the results of each ML technique were averaged to produce silage maize yields. The comparisons between the results of these methods indicate that the BRT technique, with the average $R$ value higher than 0.87, outperforms other ones for all years. It was followed by RFR with almost same performance as GPR technique. This research demonstrated that some advanced ML approaches can predict the silage maize yield and they are less sensitive to inconsistency of NDVI time series. The results also showed that RFR was the most stable method to predict the maize yield in 2015, while it was trained using 2013-2014 dataset.
Dec. 2018
4563-4577
journalArticle
10
IEEE Access
DOI 10.1109/ACCESS.2022.3215740
IEEE Access
ISSN 2169-3536
C. T. Urabe
T. Ikegami
K. Ogimoto
Time series analysis
100% renewable energy
Climate change
Energy management
Energy system integration
Fluctuations
Maximum power point trackers
maximum power point tracking
ramp rate limitation
Renewable energy sources
short-term fluctuations
smoothing effect
Smoothing methods
wind power
Wind power generation
Mitigation of Short-Term Fluctuations in Wind Power Output in a Balancing Area on the Road Toward 100% Renewable Energy
The rapid growth of the share of variable renewable energy (VRE) may make it difficult to operate power systems incorporating these sources, due to fluctuations in VRE output. In this paper, we focus on the short-term fluctuations (STFs) in wind power total outputs in several balancing areas (BAs) in Japan. We propose five methods to mitigate STFs, utilizing innate functions of wind turbines that use neither battery systems nor any other additional systems or equipment. In addition, the methods suggested do not require predictions of the wind power output. The efficiency of the method was measured based on the relationship between the mitigation of STFs and associated energy loss. Historical wind power output data from three BAs in Japan (the Hokkaido, Tohoku, and Kyushu BAs) were used to conduct numerical simulations. One of the proposed methods effectively mitigated STFs in the total wind power output. The proposed approach is applicable to solar power and will help overcome challenges on the road toward 100% renewable energy.
2022
111210-111220
journalArticle
9
IEEE Access
DOI 10.1109/ACCESS.2021.3134196
IEEE Access
ISSN 2169-3536
H. R. Bukhari
R. Mumtaz
S. Inayat
U. Shafi
I. U. Haq
S. M. H. Zaidi
M. Hafeez
Crops
deep learning
Deep learning
Image color analysis
Diseases
Biological system modeling
Image segmentation
Machine learning
classification
cropping
Production
segmentation
wheat stripe rust disease
Assessing the Impact of Segmentation on Wheat Stripe Rust Disease Classification Using Computer Vision and Deep Learning
Wheat is a staple crop that is grown across the world due to its substantial contribution to human nutrition. Its significance is evident as it provides almost 20% of calories and protein required for daily human consumption. However, wheat yield is affected by rust disease that can reduce 30% of wheat production which is a serious threat to food security. In order to minimize the loss, it is crucial to identify precisely and localize the wheat rust disease and its infection types. For this purpose, several classification and segmentation techniques are used which are based on machine/deep learning models. This paper provides a realistic analysis and evaluation of various segmentation techniques including Watershed, Grab Cut, and U2-Net. These techniques are applied to the wheat stripe rust data to generate multiple datasets such as Watershed segmented data, GrabCut segmented data, and U2-Net segmented data. Subsequently, a pre-trained deep learning model, ResNet-18 is applied to these datasets to assess the impact of segmentation on classification accuracy. The highest classification accuracy (96.196%) is achieved on the dataset segmented by U2-Net. This research collates several state-of-the-art segmentation techniques in terms of correctness and their direct impact on classification accuracy which gives a pragmatic analysis for researchers to choose optimal segmentation technique. The research primarily focuses on the direct impact of segmentation on classification accuracy of wheat stripe rust, which has not been given sufficient focus in earlier researches.
2021
164986-165004
journalArticle
S. Zheng
C. Shen
X. Chen
Collaborative work
communication design
Computational modeling
Convergence
convergence analysis
Downlink
Quantization (signal)
Uplink
Wireless communication
Wireless federated learning
Design and Analysis of Uplink and Downlink Communications for Federated Learning
Communication has been known to be one of the primary bottlenecks of federated learning (FL), and yet existing studies have not addressed the efficient communication design, particularly in wireless FL where both uplink and downlink communications have to be considered. In this paper, we focus on the design and analysis of physical layer quantization and transmission methods for wireless FL. We answer the question of what and how to communicate between clients and the parameter server and evaluate the impact of the various quantization and transmission options of the updated model on the learning performance. We provide new convergence analysis of the well-known FED AVG under non-i.i.d. dataset distributions, partial clients participation, and finite-precision quantization in uplink and downlink communications. These analyses reveal that, in order to achieve an O(1/T) convergence rate with quantization, transmitting the weight requires increasing the quantization level at a logarithmic rate, while transmitting the weight differential can keep a constant quantization level. Comprehensive numerical evaluation on various real-world datasets reveals that the benefit of a FL-tailored uplink and downlink communication design is enormous - a carefully designed quantization and transmission achieves more than 98% of the floating-point baseline accuracy with fewer than 10% of the baseline bandwidth, for majority of the experiments on both i.i.d. and non-i.i.d. datasets. In particular, 1-bit quantization (3.1% of the floating-point baseline bandwidth) achieves 99.8% of the floating-point baseline accuracy at almost the same convergence rate on MNIST, representing the best known bandwidth-accuracy tradeoff to the best of the authors' knowledge.
July 2021
2150-2167
39
IEEE Journal on Selected Areas in Communications
DOI 10.1109/JSAC.2020.3041388
7
IEEE Journal on Selected Areas in Communications
ISSN 1558-0008
journalArticle
8
IEEE Access
DOI 10.1109/ACCESS.2020.3025196
IEEE Access
ISSN 2169-3536
Q. Zeng
X. Ma
B. Cheng
E. Zhou
W. Pang
Data models
Feature extraction
deep learning
Diseases
generative adversarial networks
data augmentation
Training
Machine learning
Computational modeling
Citrus Huanglongbing
plant disease severity
Plants (biology)
GANs-Based Data Augmentation for Citrus Disease Severity Detection Using Deep Learning
Recently, many Deep Learning models have been employed to classify different kinds of plant diseases, but very little work has been done for disease severity detection. However, it is more important to master the severities of plant diseases accurately and timely, as it helps to make effective decisions to protect the plants from being further infected and reduce financial loss. In this paper, based on the Huanglongbing (HLB)-infected leaf images obtained from PlantVillage and crowdAI, we created a dataset with 5,406 citrus leaf images infected by HLB. Then six different kinds of popular models were trained to perform the severity detection of citrus HLB with the goal to find which types of models are more suitable to detect HLB severity with the same training circumstance. The experimental results show that the Inception_v3 model with epochs=60 can achieve higher accuracy than that of other models for severity detection with an accuracy of 74.38% due to its highly computational efficiency and small number of parameters. Additionally, aiming for evaluating whether GANs-based data augmentation can contribute to improve the model learning performance, we adopted DCGANs (Deep Convolutional Generative Adversarial Networks) to augment the original training dataset up to two times itself. Finally, a new training dataset with 14,056 leaf images composed by the original training images and the augmented ones were used to train the Inception_v3 model. As a result, we achieved an accuracy of 92.60%, about 20% higher than that of the Inception_v3 model trained by the original training dataset, which suggested that the GANs-based data augmentation is very useful to improve the model learning performance.
2020
172882-172891
journalArticle
8
IEEE Access
DOI 10.1109/ACCESS.2020.2969847
IEEE Access
ISSN 2169-3536
S. D. Fabiyi
H. Vu
C. Tachtatzis
P. Murray
D. Harle
T. K. Dao
I. Andonovic
J. Ren
S. Marshall
Feature extraction
Cameras
Hyperspectral imaging
Inspection
rice seed variety
Shape
Spatial resolution
spatio-temporal feature fusion
Task analysis
Varietal Classification of Rice Seeds Using RGB and Hyperspectral Images
Inspection of rice seeds is a crucial task for plant nurseries and farmers since it ensures seed quality when growing seedlings. Conventionally, this process is performed by expert inspectors who manually screen large samples of rice seeds to identify their species and assess the cleanness of the batch. In the quest to automate the screening process through machine vision, a variety of approaches utilise appearance-based features extracted from RGB images while others utilise the spectral information acquired using Hyperspectral Imaging (HSI) systems. Most of the literature on this topic benchmarks the performance of new discrimination models using only a small number of species. Hence, it is unclear whether or not model performance variance confirms the effectiveness of proposed algorithms and features, or if it can be simply attributed to the inter-class/intra-class variations of the dataset itself. In this paper, a novel method to automatically screen and classify rice seed samples is proposed using a combination of spatial and spectral features, extracted from high resolution RGB and hyperspectral images. The proposed system is evaluated using a large dataset of 8,640 rice seeds sampled from a variety of 90 different species. The dataset is made publicly available to facilitate robust comparison and benchmarking of other existing and newly proposed techniques going forward. The proposed algorithm is evaluated on this large dataset and the experimental results show the effectiveness of the algorithm to eliminate impure species by combining spatial features extracted from high spatial resolution images and spectral features from hyperspectral data cubes.
2020
22493-22505
journalArticle
10
IEEE Access
DOI 10.1109/ACCESS.2022.3171341
IEEE Access
ISSN 2169-3536
T. Yu
L. Wang
W. Zhang
G. Xing
J. Han
F. Li
C. Cao
Data models
Bayes methods
Computational modeling
Bioinformatics
ensemble learning
Genomic selection
Genomics
gradient boosted decision tree
phenotypic prediction
Predictive models
Random forests
wheat
Predicting Phenotypes From High-Dimensional Genomes Using Gradient Boosting Decision Trees
xsxsGenomic selection (GS) is an emerging technique for predicting unknown phenotypes using genome-wide marker coverage, allowing the use of efficient computational models to select individuals with high phenotypic values as candidate breeding populations. However, GS remains challenging inefficient crop breeding due to the limited size of training populations, the nature of genotype-environment interactions, and the complex interaction patterns between molecular markers. In this study, we use ensemble learning algorithms to construct gradient boosted decision tree (GBDT) models to achieve the prediction of phenotypic values from genotypic markers. We trained GBDT using the wheat GS dataset and compared the predictive performance with six other widely used GS models. The mean normalized discounted cumulative gain (MNDCG) method was used to evaluate the ability of each model to select individuals with high phenotypic values. The results of the study show that: (1) Bayesian models converge and reach a steady-state only when a sufficient number of iterations are set. As the number of iterations increases, the prediction accuracy of the Bayesian model increases, but the computational efficiency of the model decreases significantly. When 200,000 iterations are performed, the prediction performance of the five Bayesian models is similar and converges to a smooth state, and their prediction accuracy is 7.60% better than the GBDT model overall, and the computational efficiency of the GBDT model is 70 times that of the Bayesian model. (2) Overall, the overall prediction performance of the RRBLUP model was the best, but for some traits, the GBDT model still had a higher ability to select individuals with high phenotypic values than the RRBLUP and Bayesian models. (3) The prediction accuracy of GBDT and RRBLUP models was influenced by the subset of markers, and the higher the number of markers the higher the prediction accuracy of the models, so the reasonable selection of genetic marker data of appropriate size could improve the prediction performance of the models.
2022
48126-48140
journalArticle
9
IEEE Access
DOI 10.1109/ACCESS.2021.3120309
IEEE Access
ISSN 2169-3536
T. Ferdousi
L. W. Cohnstaedt
C. M. Scoglio
Data models
Time series analysis
Correlation
Dengue
feature selection
Land surface temperature
machine learning
Ocean temperature
recurrent neural networks
Temperature distribution
time series
Viruses (medical)
A Windowed Correlation-Based Feature Selection Method to Improve Time Series Prediction of Dengue Fever Cases
The performance of data-driven models depends on training samples. For accurately predicting dengue fever cases, historical incidence data are inadequate in many locations. This work aims to enhance temporally limited dengue case data by methodological addition of epidemically relevant case data from nearby locations as predictors (features). A novel framework is presented for windowing incidence data and computing time-shifted correlation-based metrics to quantify feature relevance. The framework ranks incidence data of adjacent locations around a target by combining metrics based on correlation, spatial distance, and local prevalence. Recurrent neural network models achieve up to 33.6% accuracy improvement on average using the proposed method. These models achieve mean absolute error (MAE) values as low as 0.128 on [0, 1] normalized incidence data for a municipality with the highest dengue prevalence in Brazil’s Espirito Santo. When predicting aggregate cases over geographical ecoregions, the models improve by 16.5%, using only 6.5% of ranked incidence data. This paper also presents two correlation window allocation methods: fixed-size and outbreak detection. Both perform comparably well, although the outbreak detection method uses less data for computations. The proposed framework is generalized, and it can be used to improve time-series predictions of many spatiotemporal datasets.
2021
141210-141222
journalArticle
Y. Shi
L. Han
L. Han
S. Chang
T. Hu
D. Dancey
Data models
Generative adversarial networks
Spatial resolution
Deep learning (DL)
Distortion
generative adversarial network (GAN)
Generators
hyperspectral image (HSI) super-resolution (SR)
Optimization
Superresolution
A Latent Encoder Coupled Generative Adversarial Network (LE-GAN) for Efficient Hyperspectral Image Super-Resolution
Realistic hyperspectral image (HSI) super-resolution (SR) techniques aim to generate a high-resolution (HR) HSI with higher spectral and spatial fidelity from its low-resolution (LR) counterpart. The generative adversarial network (GAN) has proven to be an effective deep learning framework for image SR. However, the optimization process of existing GAN-based models frequently suffers from the problem of mode collapse, leading to the limited capacity of spectral–spatial invariant reconstruction. This may cause the spectral–spatial distortion to the generated HSI, especially with a large upscaling factor. To alleviate the problem of mode collapse, this work has proposed a novel GAN model coupled with a latent encoder (LE-GAN), which can map the generated spectral–spatial features from the image space to the latent space and produce a coupling component to regularize the generated samples. Essentially, we treat an HSI as a high-dimensional manifold embedded in a latent space. Thus, the optimization of GAN models is converted to the problem of learning the distributions of HR HSI samples in the latent space, making the distributions of the generated SR HSIs closer to those of their original HR counterparts. We have conducted experimental evaluations on the model performance of SR and its capability in alleviating mode collapse. The proposed approach has been tested and validated based on two real HSI datasets with different sensors (i.e., AVIRIS and UHD-185) for various upscaling factors (i.e., $\times 2$ , $\times 4$ , and $\times 8$ ) and added noise levels (i.e., $\infty $ , 40, and 80 dB) and compared with the state-of-the-art SR models (i.e., hyperspectral coupled network (HyCoNet), low tensor-train rank (LTTR), band attention GAN (BAGAN), SR-GAN, and WGAN). Experimental results show that the proposed model outperforms the competitors on the SR quality, robustness, and alleviation of mode collapse. The proposed approach is able to capture spectral and spatial details and generate more faithful samples than its competitors. It has also been found that the proposed model is more robust to noise and less sensitive to the upscaling factor and has been proven to be effective in improving the convergence of the generator and the spectral–spatial fidelity of the SR HSIs.
2022
1-19
60
IEEE Transactions on Geoscience and Remote Sensing
DOI 10.1109/TGRS.2022.3193441
IEEE Transactions on Geoscience and Remote Sensing
ISSN 1558-0644
journalArticle
9
IEEE Access
DOI 10.1109/ACCESS.2021.3049191
IEEE Access
ISSN 2169-3536
M. K. I. Molla
S. K. Saha
S. Yasmin
M. R. Islam
J. Shin
Feature extraction
Support vector machines
Task analysis
Brain computer interface (BCI)
discrete wavelet transformation
Discrete wavelet transforms
Electroencephalography
electroencephalography (EEG)
motor imagery
narrowband signals
Signal resolution
subband decomposition
Transforms
Trial Regeneration With Subband Signals for Motor Imagery Classification in BCI Paradigm
Electroencephalography (EEG) captures the electrical activities of human brain. It is an easy and cost effective tool to characterize motor imager (MI) task used in brain computer interface (BCI) implementation. The MI task is represented by short time trial of multichannel EEG. In this paper, the raw EEG trial is regenerated using narrowband signals obtained from individual channel. Each channel of EEG trial is decomposed into a set of subband signals using multivariate discrete wavelet transform. The selected subbands are organized in two different ways namely vertical arrangement of subbands (VaS) and horizontal arrangement of subbands (HaS) to regenerate the trials. The features are extracted from each of the arrangements using common spatial pattern (CSP). An optimum number of features are used to classify the motor imagery tasks represented by EEG trials. The effectiveness of two classifiers– linear discriminant analysis (LDA) and support vector machine (SVM) are studied. The performances of the proposed methods are evaluated using publicly available benchmark datasets. The experimental results show that it performs better than the recently developed algorithms.
2021
7632-7642
journalArticle
10
IEEE Access
DOI 10.1109/ACCESS.2022.3174964
IEEE Access
ISSN 2169-3536
R. Singh
L. I. Izhar
I. Elamvazuthi
A. Ashok
S. Aole
N. Sharma
Discrete wavelet transforms
Transforms
Arnold transform
Color
Color watermarking
Discrete cosine transforms
Discrete wavelet transform
False positive problem
Frequency-domain analysis
Robustness
Singular value decomposition
Watermarking
Efficient Watermarking Method Based on Maximum Entropy Blocks Selection in Frequency Domain for Color Images
False-positive problem (FPP) is a one of the challenging tasks for the researchers. It authenticates the wrong owner to access the multimedia content. To overcome, the FPP problem, this paper introduces an efficient watermarking method based on the selection of highest entropy blocks. In this method, cover and watermark images are initially shuffled through Arnold transform. Then, the encrypted images are further processed by a 2-level discrete wavelet transform followed by singular value decomposition. The proposed method has been evaluated with geometrical, filtering, noise, and contrast adjustment attacks on the standard image datasets against five recently developed watermarking methods. The simulation results reveal that the proposed method outperforms the existing methods.
2022
52712-52723
journalArticle
10
IEEE Access
DOI 10.1109/ACCESS.2022.3163380
IEEE Access
ISSN 2169-3536
D. Ozdemir
M. S. Kunduraci
Deep learning
Insects
Training
Shape
Artificial intelligence
Classification algorithms
computers and information processing
Entomology
insect classification
Software
Comparison of Deep Learning Techniques for Classification of the Insects in Order Level With Mobile Software Application
Insects are a class of the arthropod branch and the most crowded animal group in terms of species and taxonomy. Due to destruction and forest fires, some insect species could go extinct without being detected. Identifying new insects and having knowledge about insects in terms of biodiversity will contribute positively to the studies carried out, especially in entomology, agriculture, the pharmaceutical industry, medicine, robotics, and other branches. In this study, we produced a mobile-based decision support software with a deep learning model to classify and detect insects at the order level. We also presented the comparative analysis results of SSD MobileNET, YoloV4, and Faster R-CNN InceptionV3 deep learning methods and adapting processes for order-level insect classification. Our approach studies the suitability of existing models towards such an objective, and we conclude that Faster R-CNN InceptionV3 performs the best at classifying and detecting insects at the order level. In addition, we shared 25820 training and 1500 test data in the kaggle database in order to contribute studies to be carried out in this area. As a result, we believe that this research will be beneficial to entomologists, naturalists, and other researchers in related fields.
2022
35675-35684
journalArticle
8
IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
DOI 10.1109/JSTARS.2015.2419225
4
IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
ISSN 2151-1535
S. Zhang
Q. Wang
Data models
Biological system modeling
\textit{Tamarix ramosissima}
Absorption
Accuracy
Calibration
chlorophyll
Ecosystems
inversion
Needles
PROSPECT
Tamarix ramosissima
Inverse Retrieval of Chlorophyll From Reflected Spectra for Assimilating Branches of Drought-Tolerant Tamarix ramosissima
Leaf chlorophyll content is a critical indicator for the better understanding of the featured carbon cycle and ecosystem functions in arid regions. The potential applicability of the inverse retrieval of chlorophyll via the radiative transfer model PROSPECT has been intensively examined in this study for a dominant species in desert ecosystems, Tamarix ramosissima, in central Asia, which has distinct structural features of xeromorphism and its young twig functioned as “assimilating organisms.” This study revealed that the performance of the inverse retrieval based on the original version of PROSPECT-4 was poor with very low accuracy. As a comparison, its calibrated version was capable of accurate retrieval of chlorophyll content, which recorded an R2 (coefficient of determination) of 0.47 with a root mean square error (RMSE) of 28.79 mg/m2, over the entire measured chlorophyll range, from 57.37 to 202.27 mg/m2. The model calibration is not considered to be overfitting since the tenfold cross-validation shows a close RMSE value of 26.19 mg/m2. The effects of the percentage of training dataset for calibration and the number of calibration repeats have also been intensively investigated in this study. Despite some inherent defects of applying broadleaforiented PROSPECT on assimilating branches, it remains a feasible selection to inversely retrieve the chlorophyll content from the reflectance and thus provides a base for investigating the chlorophyll content of desert plants using hyperspectral remote sensing.
April 2015
1498-1505
journalArticle
U. A. Bhatti
Z. Ming-Quan
H. Qing-Song
S. Ali
A. Hussain
Y. Yuhuan
Z. Yu
L. Yuan
S. A. Nawaz
Color
Algebra
clifford algebra
Fourier transforms
Image edge detection
Licenses
Prediction algorithms
QFT
Quaternions
remote sensing image
satellite image processing
Advanced Color Edge Detection Using Clifford Algebra in Satellite Images
Edge detection is widely used for image processing to improve the detection and classification of objects, segmentation, and extraction of other features. Satellite images are rich in information about objects with different color intensity and have a large amount of noise, so it is difficult to achieve recognition, classification, and feature extraction of small objects through traditional edge detection algorithms. The colors in satellite images suffer from a large amount of overlap due to areas or weather conditions that generate a lot of noise. Edge detection provides detailed information about objects in an image by reducing unnecessary feature information. Edge detection in color images is more challenging than edge detection in gray-level images. This paper proposes a method for the edge detection of color images using Clifford algebra and its sub-algebra, quaternions. Quaternion-based Fourier transform is used to process red, green and blue (RGB) images separately in the vector field. A 3×3 quaternion mask is developed to filter out frequencies of the image in multiple directions and only provides details about the edges. The algorithm works on three channels individually; the output is then processed through quaternion Fourier transform (QFT) and inverse QFT with a 3×3 mask to filter high frequencies. The proposed algorithm is compared with traditional edge detection algorithms using a satellite image dataset that has different types of objects and detailed information. Results are validated through entropy, structure similarity, and noise error to prove that our proposed algorithm provides satisfactory performance on different remote sensed images.
April 2021
1-20
13
IEEE Photonics Journal
DOI 10.1109/JPHOT.2021.3059703
2
IEEE Photonics Journal
ISSN 1943-0655
journalArticle
8
IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
DOI 10.1109/JSTARS.2014.2347299
6
IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
ISSN 2151-1535
X. Li
B. Huang
K. Zhao
hyperspectral imagery
Hyperspectral imaging
Automatic target generation process (ATGP)
CUDA
graphics processing unit (GPU)
Graphics processing units
Indexes
Instruction sets
Libraries
Runtime
Massively Parallel GPU Design of Automatic Target Generation Process in Hyperspectral Imagery
A popular algorithm for hyperspectral image interpretation is the automatic target generation process (ATGP). ATGP creates a set of targets from image data in an unsupervised fashion without prior knowledge. It can be used to search a specific target in unknown scenes and when a target's size is smaller than a single pixel. Its application has been demonstrated in many fields including geology, agriculture, and intelligence. However, the algorithm requires long time to process due to the massive amount of data. To expedite the process, the graphics processing units (GPUs) are an attractive alternative in comparison with traditional CPU architectures. In this paper, we propose a GPU-based massively parallel version of ATGP, which provides real-time performance for the first time in the literature. The HYDICE image data (307 * 307 pixels and 210 spectral bands) are used for benchmark. Our optimization efforts on the GPU-based ATGP algorithm using one NVIDIA Tesla K20 GPU with I/O transfer can achieve a speedup of 362× with respect to its single-threaded CPU counterpart. We also tested the algorithm on Airborne Visible/InfraRed Imaging Spectrometer (AVIRIS) WTC dataset (512 * 614 * 224 of 224 bands) and Cuprite dataset (35 * 350 * 188 of 188 bands), the speedup was 416× and 320×, respectively, when the target number was 15.
June 2015
2862-2869
journalArticle
8
IEEE Access
DOI 10.1109/ACCESS.2020.3014908
IEEE Access
ISSN 2169-3536
A. Mosavi
F. S. Hosseini
B. Choubin
M. Goodarzi
A. A. Dineva
Biological system modeling
Irrigation
Machine learning
Predictive models
Bayesian generalized linear model
Groundwater salinity
hazard
Lakes
Numerical models
recursive feature elimination
rotation forest
Salinity (geophysical)
stochastic gradient boosting
Groundwater Salinity Susceptibility Mapping Using Classifier Ensemble and Bayesian Machine Learning Models
Risk and susceptibility mapping of groundwater salinity (GWS) are challenging tasks for groundwater quality monitoring and management. Advancement of accurate prediction systems is essential for the identification of vulnerable areas in order to raise awareness about the potential salinity susceptibility and protect the groundwater and top-soil in due time. In this study, three machine learning models of Stochastic Gradient Boosting (StoGB), Rotation Forest (RotFor), and Bayesian Generalized Linear Model (Bayesglm) are developed for building prediction models and their performance evaluated in the delineation of salinity susceptibility maps. Both natural and human effective factors (16 features) were used as predictors for groundwater salinity modeling and were randomly divided into the training (80%) and testing (20%) datasets. The models were evaluated using testing datasets after calibration using the selected features by recursive feature elimination (RFE) method. The RFE indicated that modeling with 8 features had better performance among 1 to 16 features (Accuracy = 0.87). Results of the groundwater salinity prediction highlighted that StoGB had a good performance, whereas the RotFor and Bayesglm had an excellent performance based on the Kappa values (>0.85). Although spatial prediction of the models was different, all of the models indicated that central parts of the region have a very high susceptibility which matches with agricultural areas, lithology map, the locations with low depth to groundwater, low slope, and elevation. Additionally, areas near to the Maharlu lake and locations with a high decline in groundwater are also located in the very high susceptibility zone, which can confirm the effects of saltwater intrusion. The susceptibility maps produced in this study are of utmost importance for water security and sustainable agriculture.
2020
145564-145576
journalArticle
9
IEEE Access
DOI 10.1109/ACCESS.2021.3100816
IEEE Access
ISSN 2169-3536
C. L. Christensen
A. Vartakavi
Feature extraction
Agriculture
convolutional neural networks
Task analysis
Predictive models
Automatic image cropping
Benchmark testing
image enhancement
image processing
Tuning
Visualization
An Experience-Based Direct Generation Approach to Automatic Image Cropping
Automatic Image Cropping is a challenging task with many practical downstream applications. The task is often divided into sub-problems - generating cropping candidates, finding the visually important regions, and determining aesthetics to select the most appealing candidate. Prior approaches model one or more of these sub-problems separately, and often combine them sequentially. We propose a novel convolutional neural network (CNN) based method to crop images directly, without explicitly modeling image aesthetics, evaluating multiple crop candidates, or detecting visually salient regions. Our model is trained on a large dataset of images cropped by experienced editors and can simultaneously predict bounding boxes for multiple fixed aspect ratios. We consider the aspect ratio of the cropped image to be a critical factor that influences aesthetics. Prior approaches for automatic image cropping, did not enforce the aspect ratio of the outputs, likely due to a lack of datasets for this task. We, therefore, benchmark our method on public datasets for two related tasks - first, aesthetic image cropping without regard to aspect ratio, and second, thumbnail generation that requires fixed aspect ratio outputs, but where aesthetics are not crucial. We show that our strategy is competitive with or performs better than existing methods in both these tasks. Furthermore, our one-stage model is easier to train and significantly faster than existing two-stage or end-to-end methods for inference. We present a qualitative evaluation study, and find that our model is able to generalize to diverse images from unseen datasets and often retains compositional properties of the original images after cropping. We also find that the model can generate crops with better aesthetics than the ground truth in the MIRThumb dataset for image thumbnail generation with no fine tuning. Our results demonstrate that explicitly modeling image aesthetics or visual attention regions is not necessarily required to build a competitive image cropping algorithm.
2021
107600-107610
journalArticle
8
IEEE Access
DOI 10.1109/ACCESS.2020.3016824
IEEE Access
ISSN 2169-3536
W. -Y. Shih
Y. -S. Lu
H. -P. Tsai
J. -L. Huang
Predictive models
Adaptation models
Advertising
bidding strategy
branding campaign
Computer science
demand side platform
Learning (artificial intelligence)
Logistics
online advertising
Real time bidding
Real-time systems
reinforcement learning
An Expected Win Rate-Based Real Time Bidding Strategy for Branding Campaign by the Model-Free Reinforcement Learning Model
The bidding strategy plays the most important role to help the Demand Side Platforms (DSPs) making bidding decisions on a large number of bid requests in Real Time Bidding (RTB) to satisfy the different objectives of campaigns under the lifetime and budget constraints. In this paper, we focus on branding campaign whose objective is to obtain as many impressions as possible under the lifetime and budget constraints. To achieve the objectives of branding campaigns, we propose a novel expected win rate-based bidding strategy for branding campaign under the lifetime and budget constraints by utilizing a model-free reinforcement learning model. Specifically, to prevent missing good opportunities resulting from submitting extremely low bid prices, the concept of the base winning price is introduced to determine the lower bound of expected winning price. In addition, to obtain more impressions, the concept of the DSP-specified budget spending plan is proposed to determine the proper winning prices. The base expected win rate is then calculated based on the base winning price and the winning price determined by the DSP-specified budget spending plan. Since RTB is a dynamic environment, we propose a novel expected win rate-based bidding strategy named EWDQN which utilizes Deep Q Network (DQN) to dynamically determine the expected win rate according to the base expected win rate and the current status of the RTB market, and then determines the bid price according to the expected win rate. To the best of our knowledge, this is the first research applying the reinforcement learning technique on the bidding strategies for branding campaign. To measure the performance of EWDQN, several experiments are conducted on two real datasets. Experimental results show that EWDQN outperforms the-state-of-the-art bidding strategies for branding campaign in terms of the number of obtained impressions and CPM (cost per thousand impressions).
2020
151952-151967
journalArticle
10
IEEE Access
DOI 10.1109/ACCESS.2022.3200603
IEEE Access
ISSN 2169-3536
A. H. Al-Badri
N. A. Ismail
K. Al-Dulaimi
A. Rehman
I. Abunadi
S. A. Bahaj
Convolutional neural networks
Crops
Feature extraction
Agriculture
Economics
Computational modeling
Classification algorithms
Visualization
Chemicals
CNN networks
economic growth
ensemble models
Lighting
real-world data
weed classification
Hybrid CNN Model for Classification of Rumex Obtusifolius in Grassland
Rumex obtusifolius Linnaeus (R. obtu. L.) is one of the vital broad-leaved weeds in grassland that needs removal. It affects dairy products and reduces their quality. Hand-removal methods are costly and time-consuming. Chemical treatment using herbicides has a negative impact on crops and causes environmental pollution. In smart farming, weeding is performed by using computer vision to recognize the weeds efficiently and effectively. Conventional machine learning (ML)-based algorithms face challenges, especially in identifying the weeds in real-world data due to a lack of features. Deep learning (DL) approaches use self-learning to extract all potential features that assist in classifying malignant weed species accurately. Recently, single deep learning methods achieved high performance in identifying well-separated and illumination but suffered from misclassification in more sophisticated cases such as overlapping and partial occlusion leaves. This paper presents a hybrid Convolutional Neural Network (CNN) model of three state-of-the-art CNNs to classify Rumex obtusifolius. The proposed model utilizes convolutional neural networks to extract features and classify images. The framework of the proposed method comprises three paramount stages to accomplish the classification key idea, including the data preparation phase, pre-processing phase, and classification phase. A hybrid model of three CNN extractor networks is used as the backbone in the classification stage. Our tested data is real-world data that includes multi-circumstances (overlap, occlusion, various illuminations, etc.) acquired from nature. The first extractor is the Visual Graphics Group-16 (VGG-16) for well-separated leaves and non-complicated issues. The second extractor is Residential Energy Services Network-50 (ResNet-50), to overcome complex real-world issues. The third extractor is Inception-v3 to solve the illumination problem. Therefore, combining three networks into one model improves the discriminatory ability to extract additional useful features. The proposed model has been tested using two benchmark datasets for Rumex weed plants. Both of these datasets were captured in real-world environments. The first dataset consists of 900 samples, while the second dataset consists of 677 samples. Each dataset is individually tested in the proposed model to evaluate the classification accuracy using a set of standard evaluation metrics including accuracy, precession, recall, True-Positive Rate (TPR), False-Positive Rate (FPR), and F1-score. The total averages of the proposed model on both datasets are 97.51%, 97.4%, 94.45%, and 95.9% on the accuracy, recall, precision, and F1-score, respectively.
2022
90940-90957
journalArticle
7
IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
DOI 10.1109/JSTARS.2013.2295513
4
IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
ISSN 2151-1535
A. Merentitis
C. Debes
R. Heremans
Feature extraction
Training
Image segmentation
Hyperspectral imaging
classification
segmentation
Bagging
bias-variance
Complexity theory
ensemble methods
hyperspectral image (HIS)
Noise
random forest
Ensemble Learning in Hyperspectral Image Classification: Toward Selecting a Favorable Bias-Variance Tradeoff
Automated classification of hyperspectral images is a fast growing field with numerous applications in the areas of security and surveillance, agriculture, urban management, and environmental monitoring. Although significant progress has been achieved in various aspects of hyperspectral classification (e.g., feature extraction, feature selection, classification, and post-classification processing), the problem has not been addressed so far from a bias-variance decomposition point of view. In this work, we introduce a consistent unified framework that jointly considers all steps in the hyperspectral image classification chain from a bias-variance decomposition perspective. Additionally, we show how state-of-the-art techniques in feature extraction, ensemble-based classification, and post-classification segmentation are related to the bias-variance tradeoff and how this relation can be used to improve classification accuracy. An important outcome of our analysis is that all the steps of the classification chain should be optimized jointly as this unified optimization can guide toward a more favorable bias-variance tradeoff. Experimental results of the proposed framework in the case of four hyperspectral datasets prove the effectiveness of our approach.
April 2014
1089-1102
journalArticle
R. Dwivedi
T. Dutta
Y. -C. Hu
Feature extraction
Image color analysis
Diseases
Training
Biological system modeling
Classification
disease detection
extreme learning machine (ELM)
Extreme learning machines
leaf disease
Minimization
precision agriculture
A Leaf Disease Detection Mechanism Based on L1-Norm Minimization Extreme Learning Machine
The disease-free growth of a plant is highly influential for both environment and human life, as numerous microorganisms/viruses/fungus may affect the growth and agricultural production of a plant. Early detection and treatment thus becomes necessary and must be treated on time. The existing vision techniques either involve image segmentation or feature classification/regression applied over aerial images. This results in an increase in time and cost consumption due to various challenges, such as generalization ability and learning cost. Therefore, a feature-based disease detection approach with minimal learning time and generalization ability could be fairly befitting such as an extreme learning machine (ELM). In this letter, we demonstrate an algorithm, L1-ELM, after employing Kuan filtering for preprocessing and different feature computations. At the evaluation stage, the experimentation performed over benchmark plant datasets confirms that L1-ELM outperforms all existing one-class classification algorithms, preserving optimal learning and better generalization.
2022
1-5
19
IEEE Geoscience and Remote Sensing Letters
DOI 10.1109/LGRS.2021.3110287
IEEE Geoscience and Remote Sensing Letters
ISSN 1558-0571
journalArticle
8
IEEE Access
DOI 10.1109/ACCESS.2020.3012701
IEEE Access
ISSN 2169-3536
Y. Zhang
M. Chi
Feature extraction
remote sensing
Object detection
Image segmentation
Remote sensing
Convolution
Deep fusion
deep semantic segmentation
fully convolutional network
Neural networks
object detection
Semantics
Mask-R-FCN: A Deep Fusion Network for Semantic Segmentation
Remote sensing image classification plays a significant role in urban applications, precision agriculture, water resource management. The task of classification in the field of remote sensing is to map raw images to semantic maps. Typically, fully convolutional network (FCN) is one of the most effective deep neural networks for semantic segmentation. However, small objects in remote sensing images can be easily overlooked and misclassified as the majority label, which is often the background of the image. Although many works have attempted to deal with this problem, making a trade-off between background semantics and edge details is still a problem. This is mainly because they are based on a single neural network model. To deal with this problem, a convolutional deep network with regions (R-CNN), which is highly effective for object detection is leveraged as a complementary component in our work. A learning-based and decision-level strategy is applied to fuse both semantic maps from a semantic model and an object detection model. The proposed network is referred to as Mask-R-FCN. Experimental results on real remote sensing images from the Zurich dataset, Gaofen Image Dataset (GID), and DataFountain2017 show that the proposed network can obtain higher accuracy than single deep neural networks and other machine learning algorithms. The proposed network achieved better average accuracies, which are approximately 2% higher than those of any other single deep neural networks on the Zurich, GID, and DataFoundation2017 datasets.
2020
155753-155765
journalArticle
19
IEEE Geoscience and Remote Sensing Letters
DOI 10.1109/LGRS.2022.3218608
IEEE Geoscience and Remote Sensing Letters
ISSN 1558-0571
X. -M. Zhu
X. -N. Song
P. Leng
X. -T. Li
L. Gao
L. -R. Ding
H. Guo
Microwave radiometry
Earth
Advanced Microwave Scanning Radiometer for Earth Observing System (AMSR-E)
atmospheric correction
Atmospheric modeling
clear sky
Land surface
Maximum likelihood estimation
Microwave imaging
surface emissivity
Surface treatment
A Simplified Approach to Retrieve the K-Band Microwave Surface Emissivity Under Clear Skies
Microwave land surface emissivity (MLSE) at the K-band plays a key role in driving geophysical parameters, such as land surface temperature (LST). However, satellite-based MLSE currently is hard to be quickly retrieved in clear skies since the time cost is high in removing atmospheric contributions. In this letter, one clear-sky atmospheric profile dataset, including a wide range of precipitable water vapor (PWV) values, was constructed using the thermodynamic initial guess retrieval database for analyzing numerical relationships between PWV and atmospheric parameters. Then, a simplified algorithm was developed for accurately retrieving instantaneous K-band MLSEs (18.7 and 23.8 GHz) under clear skies, which can significantly save the time of atmospheric correction. The sensitivity analysis shows that PWV is a key factor affecting MLSE estimation at 23.8 GHz, and the brightness temperature (BT) uncertainty has a greater impact on MLSE estimation than LST. In addition, with LST derived from the moderate-resolution imaging spectroradiometer, BT from the Advanced Microwave Scanning Radiometer Earth Observing System (AMSR-E), and the ERA5 reanalysis PWV in 2008, the proposed algorithm was, respectively, applied in Europe and the United States for presenting its applicability at a station scale and regional scale. The actual sounding profile and global AMSR-E MLSE product were used as validation datasets. Results indicate that the simplified approach has a good performance with root-mean-square errors (RMSEs) less than 0.02 in the site and regional validations, whereas there are some apparent overestimations in estimating clear-sky MLSEs, especially for 23.8 GHz. We believe that the proposed approach is promising for retrieving other parameters.
2022
1-5
journalArticle
9
IEEE Access
DOI 10.1109/ACCESS.2021.3073086
IEEE Access
ISSN 2169-3536
M. A. Awal
M. S. Hossain
K. Debjit
N. Ahmed
R. D. Nath
G. M. M. Habib
M. S. Khan
M. A. Islam
M. A. P. Mahmud
Diseases
Machine learning
Classification
ADASYN
ANOVA
asthma
clinical and non-clinical data
Detectors
Machine learning algorithms
Radio frequency
Respiratory system
Static VAr compensators
An Early Detection of Asthma Using BOMLA Detector
Asthma is a chronic and airway-induced disease, causing the incidence of bronchus inflammation, breathlessness, wheezing, is drastically becoming life-threatening. Even in the worst cases, it may destroy the quality to lead. Therefore, early detection of asthma is urgently needed, and machine learning can help identify asthma accurately. In this paper, a novel machine learning framework, namely BOMLA (Bayesian Optimisation-based Machine Learning framework for Asthma) detector has been proposed to detect asthma. Ten classifiers have been utilized in the BOMLA detector, where Support Vector Classifier (SVC), Random Forest (RF), Gradient Boosting Classifier (GBC), eXtreme Gradient Boosting (XGB), and Artificial Neural Network (ANN) are state-of-the-art classifiers. In contrast, Linear Discriminant Analysis (LDA), Quadratic Discriminant Analysis (QLDA), Naive Bayes (NB), Decision Tree (DT), and K-Nearest Neighbor (KNN) are conventional popular classifiers. ADASYN algorithm has also been employed in the BOMLA detector to eradicate the issues created due to the imbalanced dataset. It has even been attempted to delineate how the ADASYN algorithm affects the classification performance. The highest accuracy (ACC) and Matthews’s correlation coefficient (MCC) for an Asthma dataset provide 94.35% and 88.97%, respectively, using BOMLA detector when SVC is adapted, and it has been increased to 96.52% and 93.04%, respectively, when ensemble technique is adapted. The one-way analysis of variance (ANOVA) has also been performed in the 10-fold cross-validation to measure the statistical significance. A decision support system has been built as a potential application of the proposed system to visualize the probable outcome of the patient. Finally, it is expected that the BOMLA detector will help patients in their early diagnosis of asthma.
2021
58403-58420
journalArticle
19
IEEE Geoscience and Remote Sensing Letters
DOI 10.1109/LGRS.2022.3195809
IEEE Geoscience and Remote Sensing Letters
ISSN 1558-0571
J. Ye
C. Wang
H. Gao
H. Fan
T. Song
L. Ding
Crops
remote sensing
Synthetic aperture radar
Change detection matrix
Covariance matrices
crop rotation
Entropy
Light rail systems
Matrix decomposition
Probabilistic logic
superpixel
time-series dual-polarization synthetic aperture radar~(SAR) images
A Novel Unsupervised Object-Level Crop Rotation Detection With Time-Series Dual-Polarimetric SAR Data
Crop rotation is subsidized by the government because of its many advantages, monitoring whether crop rotation is beneficial to agricultural management and can also provide a reference for government subsidy policies for crop rotation. In this letter, we propose an unsupervised object-oriented crop rotation detection method using time-series polarimetric synthetic aperture radar (PolSAR) data. On the one hand, we construct the change detection matrix based on the likelihood ratio test (LRT) distance to perform temporal filtering. Then, the pixel-level temporal change image is generated using Shannon entropy and maximum between-class variance (OTSU). On the other hand, we perform temporal segmentation on time-series PolSAR images to obtain superpixel results. Finally, the object-level crop rotation results are obtained with the probabilistic label relaxation (PLR) model; 42 Sentinel-1 dual-polarization SAR datasets during 2018 and 2019 are selected for detecting crop rotation changes on farms within Jinchang, China. Experimental results show that the crop rotation detection accuracy and Kappa coefficients of this method can reach 96.21% and 0.8989, respectively.
2022
1-5
journalArticle
10
IEEE Access
DOI 10.1109/ACCESS.2022.3194925
IEEE Access
ISSN 2169-3536
S. Li
H. Wang
C. Zhang
J. Liu
Convolutional neural networks
Feature extraction
computer vision
deep learning
Biological system modeling
Shape
Convolution
object detection
Semantics
Pest detection
SAFFPest model
Standards
A Self-Attention Feature Fusion Model for Rice Pest Detection
To address the problem that existing deep learning methods are not sufficiently accurate to detect rice pests with changeable shapes or similar appearances, a self-attention feature fusion model for rice pest detection (SAFFPest) was proposed. The model was based on VarifocalNet. First, a deformable convolution module was added to the feature extraction network, to improve the feature extraction ability of pests with changeable shapes. Second, by obtaining the balance features of multiple feature maps, the self-attention mechanism was introduced to refine the balance feature, in order to better restore the semantic information of some pests with similar appearances. Subsequently, the group normalization method was used to replace the batch normalization method in the original model, to reduce the impact of batch size on model training. The IP102 rice pest dataset was used to train and verify this model. The experimental results showed that the model can accurately detect nine kinds of rice pests, such as rice leaf rollers and rice leaf caterpillars. Compared with FasterRCNN, RetinaNet, CP-FCOS, VFNet and BiFA-YOLO, the mean average precision of the model improved by 33.7%, 6.5%, 4.5%, 2.9% and 2% respectively.
2022
84063-84077
journalArticle
9
IEEE Access
DOI 10.1109/ACCESS.2021.3110816
IEEE Access
ISSN 2169-3536
S. Kocaaslan
N. Musaoğlu
S. Karamzadeh
Monitoring
Temperature sensors
Land surface temperature
Indexes
Drought
drought monitoring
Meteorology
SPEI
TCI
Time-frequency analysis
VCI
Vegetation mapping
VHI
Evaluating Drought Events by Time-Frequency Analysis: A Case Study in Aegean Region of Turkey
Drought is a slowly progressing and complex natural phenomenon, so the nature of drought events remains unclear. Remote sensing is preferred as an effective tool for finding, evaluating, and monitoring drought especially for large areas throughout long-term periods by providing near real-time and accurate data. Besides, Google Earth Engine (GEE) is a cloud-based service to provide analysis and visualization of geospatial datasets. The ability of GEE as a remote sensing platform to analyze high-impact societal issues, including water management diseases, disaster, deforestation, and climate monitoring environmental protection, offers it as the best option for drought monitoring. Here, Vegetation Health Index (VHI) index that combines Vegetation Condition Index (VCI) and Temperature Condition Index (TCI) has been chosen for agricultural drought assessment in a case study (Aegean Region of Turkey) from 2000 to 2018 (19 years). Thence, the land surface temperature (LST) data and the Normalized Difference Vegetation Index (NDVI) data from the Moderate Resolution Imaging Spectroradiometer (MODIS) sensor have been used and analyzed as remotely sensed data. The major data processing steps have been efficiently done on the GEE platform. Also, the time series and periodic behavior of these satellite-based indices have been examined. Besides, as the meteorological drought index, Standardized Precipitation Evapotranspiration Index (SPEI) time series were calculated for the region in question at different time scales (SPEI3, SPEI6, SPEI12, etc.) from 1980 to 2018 (39 years). Also, the frequency analysis of both satellite-based and meteorological station-based indices has been done. Fast Fourier Transform (FFT) for satellite-based indices frequency analyzing and Wavelet Transform (WT) for time-frequency analyzing of SPEI sequence have been used. Cross Wavelet (XWT), and Coherence Wavelet (CWT) were used to evaluate the time-frequency relationship of the satellite-based and the meteorological station-based time series.
2021
125032-125041
journalArticle
J. Valente
L. Kooistra
S. Mücher
Image color analysis
Agriculture
Cameras
Image segmentation
Indexes
Vegetation mapping
agro-food robotics
crop emergence
field assessment
machine vision
Object segmentation
plants breeding
Unmanned aerial vehicles
Fast Classification of Large Germinated Fields Via High-Resolution UAV Imagery
Crop breeding consists of the process of editing crop genetic profile for increasing many crop qualities. In order to achieve optimal results, crop breeders have to plant thousands of plants and keep a track of their growth almost daily. This process requires increased man-hour inspection over large fields, which results in poor accuracy due to human fatigue and a time-inefficient strategy. In this letter, two machine vision approaches were compared for classifying three crop germination classes (good, average, and bad). A naive approach using a classical segmentation and an unsupervised learning approach using k-means segmentation were compared within a high-resolution unmanned aerial vehicles imagery dataset. Experimental results demonstrate the classification of germinated patches up to 0.05 m2/patch of resolution with a minimum F1-score of 76% and 80%, and AUC of 95% and 91% for high and low spatial image resolutions, respectively.
Oct. 2019
3216-3223
4
IEEE Robotics and Automation Letters
DOI 10.1109/LRA.2019.2926957
4
IEEE Robotics and Automation Letters
ISSN 2377-3766
journalArticle
19
IEEE Geoscience and Remote Sensing Letters
DOI 10.1109/LGRS.2021.3095505
IEEE Geoscience and Remote Sensing Letters
ISSN 1558-0571
P. Tang
P. Du
J. Xia
P. Zhang
W. Zhang
Training
Agriculture
Remote sensing
Time series analysis
Task analysis
Radio frequency
Crop type mapping
Satellites
self-attention
temporal convolutional networks (TCNs)
time series classification
Channel Attention-Based Temporal Convolutional Network for Satellite Image Time Series Classification
Satellite image time series classification has become a research focus with the launch of new remote sensing sensors capable of capturing images with high spatial, spectral, and temporal resolutions. In particular, in the field of crop classification, time dimension information is particularly important. Although some advanced machine learning algorithms, such as random forests (RFs), can achieve good results, they often ignore the time series information. To make full use of temporal and spectral information in multitemporal remote sensing images, a channel attention-based temporal convolutional network (CA-TCN) is proposed in this letter. Specifically, the proposed method is composed of two main modules: temporal convolutional network and attention block. The temporal convolutional network can capture long-range dependence by using a hierarchy of temporal convolutional filters. To capture relevant information inside the sequence and enhance the important information, the attention block is used to enhance the important features in the channel dimension since not all bands contain equal information in crop type classification. The proposed CA-TCN can excavate deeper phenological characteristics. Compared to the temporal attention-based temporal convolutional network and other deep learning-based models, the proposed CA-TCN has achieved state-of-the-art performance in the Breizhcrops dataset with fewer parameters.
2022
1-5
journalArticle
19
IEEE Geoscience and Remote Sensing Letters
DOI 10.1109/LGRS.2022.3202186
IEEE Geoscience and Remote Sensing Letters
ISSN 1558-0571
W. Zhou
J. Shen
N. Liu
S. Xia
H. Sun
Feature extraction
Object detection
Semantics
Anchor-free
attention mechanism
dynamic activation function (DAF)
Heuristic algorithms
transformer
Transformers
vehicle detection
Vehicle detection
Vehicle dynamics
An Anchor-Free Vehicle Detection Algorithm in Aerial Image Based on Context Information and Transformer
Vehicle detection in the aerial image is an essential and challenging task widely used in industry and agriculture. Deep learning technology has recently achieved rapid development and good object detection results. However, the background of aerial images is complex; targets are densely distributed, and some of them are occluded. For densely distributed targets, we need to predict at each feature point. In the case of complex background and target occlusion, it is often difficult to determine whether a location contains a target if the model only focuses on the local information. Therefore, we need a global perspective and contextual information to help train the model. This letter proposes a new anchor-free small object detection algorithm, which improves feature extraction by fusing contextual semantic information. In addition, a dynamic activation function (DAF) is also used in our network, which helps us calculate the activation function value for each point from a global perspective. Moreover, we also use the channel attention module and the transformer as the spatial attention module to help the network efficiently obtain global information. We evaluate the effectiveness of our method on the public dataset DLR-3K and vehicle detection in aerial imagery dataset (VEDAI), and the average precision (AP) achieves 0.896 and 0.875.
2022
1-5
journalArticle
8
IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
DOI 10.1109/JSTARS.2015.2440274
5
IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
ISSN 2151-1535
Y. Zhou
B. Xing
W. Ju
Data models
Agriculture
Earth
Remote sensing
Accuracy
Ecosystems
Boreal ecosystem productivity simulator (BEPS) model
land-cover change
land-use change
net primary production (NPP)
Soil
urban sprawl
Assessing the Impact of Urban Sprawl on Net Primary Productivity of Terrestrial Ecosystems Using a Process-Based Model—A Case Study in Nanjing, China
Urban sprawl/urbanization has large impacts on the structure and function of terrestrial ecosystems. Net primary production (NPP) is an important indicator for estimating the earth's ability to support life and aids the evaluation of sustainable development of the terrestrial ecosystem. In this study, the process-based boreal ecosystem productivity simulator (BEPS) model was used in conjunction with leaf area index (LAI) dataset, land cover, and meteorological and soil data to simulate daily NPP at spatial resolution 250 m in Nanjing, a representative region within the Yangtze Delta, for the period 2001-2010. Effects of urbanization on land-cover change and regional NPP are quantitatively evaluated. The results show that during this period, urbanization caused significant land-cover change. Compared with 2001, urbanized area and area covered by water bodies increased significantly, while vegetated area declined greatly. The greatest loss was cropland, followed by evergreen coniferous and closed deciduous forests. There were obvious spatial differences in NPP variations. The reduction rate of annual NPP in the major city of Nanjing, Jiangning District, and Gaochun County was much higher than that in Pukou and Luhe district, and Lishui County. These results indicate that a process-based model driven by remote sensing is useful in assessing the impact of urban sprawl on NPP, and urbanization, not climate factors, is a main factor for NPP reduction for an urbanizing region.
May 2015
2318-2331
journalArticle
7
IEEE Access
DOI 10.1109/ACCESS.2019.2949866
IEEE Access
ISSN 2169-3536
Z. Peng
L. Guan
Y. Liao
S. Lian
Data models
Vegetation
Agriculture
Hyperspectral imaging
Predictive models
Calibration
Artificial neural networks
Chlorophyll
hyperspectral data
navel oranges
partial least squares
Estimating Total Leaf Chlorophyll Content of Gannan Navel Orange Leaves Using Hyperspectral Data Based on Partial Least Squares Regression
The goal of this study was to model the total leaf chlorophyll content (LCCtot) of Gannan navel orange leaves using a field imaging spectroscopy system in the visible and near-infrared domain. The spectral range from 400 to 1000 nm with 176 wavebands (a wavelength interval of 3.41 nm) or 360 wavebands (a wavelength interval of 1.67 nm), labeled as “Datasets_1.67” and “Datasets_3.41”, respectively, were used. Although different spectral data types were used, better prediction results for LCCtot were based on Datasets_1.67 for LCCtot prediction. Several prediction models of LCCtot were built based on partial least squares regression (PLSR), artificial neural networks (ANN), ordinary least squares regression (OLSR), and stepwise linear regression (SLR) using full spectral and effective wavelength (EW) data (raw spectral (RS), first derivative spectral (FDS) and second derivative spectral (SDS) data). The determination coefficient (R2), the root mean square error (RMSE) and the residual predictive deviation (RPD) were used to evaluate the reliability and accuracy of the predicted LCCtot values. As a result, 14 (7 obtained from Datasets_1.67, 7 obtained from Datasets_3.41), 39 (21 obtained from Datasets_1.67, 18 obtained from Datasets_3.41) and 50 (27 obtained from Datasets_1.67, 23 obtained from Datasets_3.41) wavebands were selected from the RS data, FDS data and SDS data, respectively, as the EWs for LCCtot prediction of navel orange leaves. After that, PLSR and ANN predictive models were established using full spectra, and OLSR and SLR predictive models were built using the selected EWs. The experimental results demonstrated that these various regression methods were useful for estimating LCCtot in the order of PLSR models established using full spectra from RS data (F-RS-PLSR) > PLSR models established using full spectra from SDS data (F-SDS-PLSR) > PLSR models established using full spectra from FDS data (F-FDS-PLSR) > SLR models established using EWs by RS data (EWs-RS-SLR). However, models built with ANN and OLSR, where the RPD values were less than 3, cause the models to be inaccurate. Finally, in comparison, the F-RS-PLSR model exhibited the best performance of LCCtot estimation; with the number of principal components (Pcs) = 5, this model provided high values of the R2 of calibration (C-R2) = 0.92 and the R2 of validation (V-R2) = 0.96, small values of the RMSE of calibration (C-RMSE)=0.05 mg/g and the RMSE of validation (V-RMSE) = 0.19 mg/g, and sufficient the RPD of calibration (C-RPD)=17.00 and the RPD of validation (V-RPD)=3.63 values. Overall, the best modeling method was PLSR. Hence, the PLSR applicability for assessing chlorophyll content in navel orange leaves was demonstrated.
2019
155540-155551
journalArticle
D. Huang
C. -D. Wang
J. -H. Lai
C. -K. Kwoh
Clustering algorithms
Consensus clustering
diversified metrics
ensemble clustering
high-dimensional data
Partitioning algorithms
random subspaces
Toward Multidiversified Ensemble Clustering of High-Dimensional Data: From Subspaces to Metrics and Beyond
The rapid emergence of high-dimensional data in various areas has brought new challenges to current ensemble clustering research. To deal with the curse of dimensionality, recently considerable efforts in ensemble clustering have been made by means of different subspace-based techniques. However, besides the emphasis on subspaces, rather limited attention has been paid to the potential diversity in similarity/dissimilarity metrics. It remains a surprisingly open problem in ensemble clustering how to create and aggregate a large population of diversified metrics, and furthermore, how to jointly investigate the multilevel diversity in the large populations of metrics, subspaces, and clusters in a unified framework. To tackle this problem, this article proposes a novel multidiversified ensemble clustering approach. In particular, we create a large number of diversified metrics by randomizing a scaled exponential similarity kernel, which are then coupled with random subspaces to form a large set of metric-subspace pairs. Based on the similarity matrices derived from these metric-subspace pairs, an ensemble of diversified base clusterings can be thereby constructed. Furthermore, an entropy-based criterion is utilized to explore the cluster wise diversity in ensembles, based on which three specific ensemble clustering algorithms are presented by incorporating three types of consensus functions. Extensive experiments are conducted on 30 high-dimensional datasets, including 18 cancer gene expression datasets and 12 image/speech datasets, which demonstrate the superiority of our algorithms over the state of the art. The source code is available at https://github.com/huangdonghere/MDEC.
Nov. 2022
12231-12244
52
IEEE Transactions on Cybernetics
DOI 10.1109/TCYB.2021.3049633
11
IEEE Transactions on Cybernetics
ISSN 2168-2275
journalArticle
10
IEEE Access
DOI 10.1109/ACCESS.2022.3166479
IEEE Access
ISSN 2169-3536
K. Hu
W. Zhang
Fuzzy adaptive PID
hydraulic interconnected suspension
Hydraulic systems
load impact
Load modeling
Mathematical models
position control
Position control
sliding mode control
Synchronization
Transfer functions
Valves
Position Control Algorithm of Fuzzy Adaptive PID of Hydraulic Interconnected Suspension Under Load Impact Disturbance
Position control accuracy of hydraulic interconnected suspension (HIS) for agricultural vehicle is unsatisfied under load impact conditions. In order to address this problem, advanced control methods were studied in this paper. The technical scheme of HIS was developed firstly. The transfer function from proportional valve spool displacement to hydraulic cylinder piston displacement was derived and then the parameters of the transfer function were also identified. The PID, sliding mode control (SMC) and fuzzy adaptive PID (FAPID) control algorithms were designed. The co-simulation of AMESim and SIMULINK was adopted to compare and analyze the control characteristics of the three algorithms. An experimental platform was also built to verify the improvement effect. The research conclusions show that when the HIS operates under load impact condition, for FAPID algorithm, the rise time is reduced by 0.27s, the maximum overshoot is reduced by 9.83mm, and the absolute value of average error is decreased by 62.62% compared with PID control algorithm. The response speed of SMC is the fastest, but there is a large chattering in the steady-state displacement. The designed FAPID control algorithm balances the advantages of fast response, high control precision and good stability, and the control performance is better than that of SMC and PID control algorithms. The research methods in this paper can provide reference value for position control accuracy improvement of hydraulic suspension.
2022
39665-39673
journalArticle
8
IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
DOI 10.1109/JSTARS.2015.2459754
10
IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
ISSN 2151-1535
M. Chellasamy
T. P. A. Ferré
M. H. Greve
Agriculture
Remote sensing
Accuracy
Vegetation mapping
Agricultural parcels
crop discrimination
ensemble
neural classifier
training data
Training data
WorldView-2
An Ensemble-Based Training Data Refinement for Automatic Crop Discrimination Using WorldView-2 Imagery
This paper presents a new approach for refining and selecting training data for satellite imagery-based crop discrimination. The goal of this approach is to automate the pixel-based “multievidence crop classification approach,” proposed by the authors in their previous research. The present study is used to feed this classification approach with automatically selected training samples based on available vector data (agricultural parcels representing crop boundaries with crop codes). The vector data are created by farmers to support subsidy claims and are, therefore, prone to errors such as boundary digitization mismatch and mislabeling of crop codes. The proposed approach, ensemble-based cluster refinement approach (ECRA), refines the declared crop clusters in an iterative training-classification scheme and provides potential training samples that give correct class descriptions. ECRA operates based on two assumptions: 1) mislabels in each class will be far from their cluster centroid and 2) each crop class based on the available vector data has more correctly labeled samples than mislabeled samples. Three datasets, derived from bitemporal WorldView-2 multispectral imagery, are used in an ensemble framework to iteratively refine the samples from crop clusters declared by the farmers: spectral, texture, and vegetation indices. Once the refinement of clusters is complete, final training samples are identified. They are used for learning and the satellite imagery is classified using the multievidence classification approach. The study is implemented with WorldView-2 imagery acquired for a study area in Denmark containing 15 crop classes. The multievidence classification approach with ECRA-based refinement is compared with the classification based on common training sample selection methods (manual and random). It is also compared with the winner-takes-all-based classification approach. ECRA achieves an overall classification accuracy of 92.8%, which is higher than existing common approaches.
Oct. 2015
4882-4894
journalArticle
10
IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
DOI 10.1109/JSTARS.2016.2637927
2
IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
ISSN 2151-1535
S. Chakrabarti
J. Judge
A. Rangarajan
S. Ranka
Microwave radiometry
remote sensing
Soil moisture
Remote sensing
Atmospheric modeling
Clustering algorithms
Cotton
Kernel
soil moisture
Utilizing Self-Regularized Regressive Models to Downscale Microwave Brightness Temperatures for Agricultural Land Covers in the SMAPVEX-12 Region
A novel algorithm is developed to downscale microwave brightness temperatures (TB), obtained at satellite scales of 10-40 to ≤1km, meaningful for agricultural applications. Downscaling TB directly bypasses the errors induced by inverse modeling encountered while downscaling satellite-based soil moisture products. This algorithm is based upon self-regularized regressive models (SRRM) and uses higher order correlations between auxiliary variables, such as precipitation (PPT), land cover, leaf area index, and land surface temperature, and horizontally polarized TB observations. It includes information-theoretic clustering based on auxiliary variables to identify areas of similarity, followed by kernel regression that produces downscaled TB. The algorithm was evaluated using a multiscale synthetic dataset over North Central Florida for one year, including two growing seasons of corn and one growing season of cotton. Compared to the true TB, the downscaled TB had a root-mean-square error (RMSE) of 5.76 K with standard deviation (SD) of 2.8 K during the growing seasons and an RMSE of 1.2 K with an SD of 0.9 K during nonvegetated. The SRRM algorithm effectively captured the variability in TB at 1 km through the auxiliary variables. This algorithm was implemented to downscale SMOS observations available for five days during the SMAPVEX-12 experiment. Spatially averaged rootmean-square difference (RMSD) between the downscaled TB and the airborne TB observations from the airborne passive-active Lband sensor was 6.2 K, with Kullback-Leibler divergences of up to 0.91. For the SMAPVEX-12 dataset, better downscaling results are obtained for days when there was no PPT due to regional biases in the remotely sensed PPT from the NASA Tropical Measurement Mission. The RMSDs were lower when in-situ PPT data were used.
Feb. 2017
478-488
journalArticle
8
IEEE Access
DOI 10.1109/ACCESS.2020.3014631
IEEE Access
ISSN 2169-3536
F. Tang
D. Zhang
T. Cai
Q. Li
Data models
Feature extraction
Task analysis
Transforms
Clustering algorithms
Clustering methods
Decoding
image clustering
regression based clustering
Unsupervised learning
Regression Based Clustering by Deep Adversarial Learning
Despite the great success, existing regression clustering methods based on shallow models are vulnerable due to: (1) They often pay no attention to the combination between learning representations and clustering, thus resulting in unsatisfactory clustering performance. (2) They ignore the relationship of data distribution and target distribution such that those methods are noise and illumination-change sensitive. (3) These nonlinear regression methods usually impose the hard constraint to minimize the mismatch between the discrete cluster assignment matrix and latent representations, which leads to over-fitting. In this paper, we utilize deep adversarial regression to tackle these problems and formulate regression based clustering by deep adversarial learning (RCDA). By seamlessly combining with the stacked autoencoder, the proposed model integrates learning deep nonlinear latent representation and clustering in a unified framework. Specifically, RCDA uses a kind of relax constraint between latent representations and continuous cluster assignment matrix to avoid over-fitting, and simultaneously utilizes the t-SNE algorithm and adversarial learning to analyze data distribution and target distribution so that improve representations learning. Experimental results on public benchmark datasets demonstrate that the proposed architecture achieves better performance than state-of-the-art clustering models in image clustering task.
2020
146744-146753
journalArticle
10
IEEE Access
DOI 10.1109/ACCESS.2022.3201338
IEEE Access
ISSN 2169-3536
M. Hassam
M. A. Khan
A. Armghan
S. A. Althubiti
M. Alhaisoni
A. Alqahtani
S. Kadry
Y. Kim
Convolutional neural networks
Feature extraction
deep learning
Deep learning
Diseases
Agriculture
Transfer learning
classification
feature selection
Optimization
augmentation
Citrus diseases
Green products
Plants
A Single Stream Modified MobileNet V2 and Whale Controlled Entropy Based Optimization Framework for Citrus Fruit Diseases Recognition
Fruit disease recognition is quickly becoming a hot topic in the field of computer vision. The presence of plant diseases not only reduces fruit production but also causes a significant loss to the national economy. Citrus fruits help to strengthen the immune system, allowing it to fight off diseases such as COVID-19. Manual inspection of fruit diseases with the naked eye takes time and is difficult; therefore, a computer based method is always required for accurate recognition of plant diseases. Several deep learning techniques for recognizing citrus fruit diseases have been introduced in the literature. Existing techniques had several issues, including redundant features, convolutional neural network (CNN) model selection, low contrast images, and long computational times. In this paper, single stream convolutional neural network architecture is proposed for recognizing citrus fruit diseases. In the first step, data augmentation is performed using four contrast enhancement operations: shadow removal, adjusting pixel intensity, improving brightness, and improving local contrast. The MobileNet-V2 CNN model is selected and fine-tuned in the second step. Using the transfer learning process, the fine-tuned model is trained on the augmented citrus dataset. The newly trained model is used for deep feature extraction; however, analysis shows that the extracted deep features contain little redundant information. As a result, an improved Whale Optimization Algorithm (IWOA) is used in the third step. The best features are then classified using machine learning classifiers in the final step. The augmented citrus fruits, leaves, and hybrid dataset were used in the experimental process and achieved an accuracy of 99.4, 99.5, and 99.7%. When compared to existing techniques, the proposed architecture outperformed them in terms of accuracy and time.
2022
91828-91839
journalArticle
10
IEEE Access
DOI 10.1109/ACCESS.2022.3156569
IEEE Access
ISSN 2169-3536
X. Y. Kek
C. S. Chin
Y. Li
Feature extraction
convolutional neural network
feature selection
Acoustic scene classification
Acoustics
Filtering theory
genetic algorithm
Genetic algorithms
Information filters
Scattering
wavelet scattering
Wavelet transforms
Multi-Timescale Wavelet Scattering With Genetic Algorithm Feature Selection for Acoustic Scene Classification
In this paper, we apply a genetic algorithm (GA) for feature selection, wrapper approach, on wavelet scattering (WS) second-order coefficients to reduce the large frequency dimension (>500). The evaluation demonstrates the capability of GA to reduce the dimension space by approximately 30% while ensuring a minimum performance drop. Furthermore, the reduced WS directly impacts the training time of the convolutional neural network, by reducing the computational time by 20% to 32%. The paper extends its scopes to explore GA for feature selection on multiple timescales of WS: 46ms, 92ms, 185ms, and 371ms. Incorporating multiple timescales has improved classification performance (by ~ around 2.5%) as an acoustic representation usually contains information at different time scales. However, it can increase computational cost due to the larger frequency dimension of 1851. With the application of GA for feature selection, the frequency dimension is reduced by 50%, saving around 40% computational time, thus increasing the classification performance by 3% compared to a vanilla WS. Lastly, the entire implementations are evaluated using the Detection and Classification of Acoustic Scenes and Events (DCASE) 2020 dataset, and the proposed multiple timescales model achieves 73.32% of classification accuracy.
2022
25987-26001
journalArticle
19
IEEE Geoscience and Remote Sensing Letters
DOI 10.1109/LGRS.2022.3225215
IEEE Geoscience and Remote Sensing Letters
ISSN 1558-0571
W. Zhang
Z. Li
H. -H. Sun
Q. Zhang
P. Zhuang
C. Li
Feature extraction
Hyperspectral imaging
Convolution
Kernel
Corn variety
Electronic mail
hyperspectral image
Seeds (agriculture)
spatial features
spectral features
texture features
Three-dimensional displays
SSTNet: Spatial, Spectral, and Texture Aware Attention Network Using Hyperspectral Image for Corn Variety Identification
Currently, most existing methods using hyperspectral images to assist seed identification only consider the spectral information but ignore the spatial information resulting in unsatisfactory classification results. To cope with this issue, we propose a spatial, spectral, and texture-aware attention network to identify corn varieties, called SSTNet. Specifically, we first employ 3-D convolution to extract the spatial and inter-spectral features. Subsequently, we utilize 2-D convolution to extract the spatial and texture features. Meanwhile, we embed an attention mechanism into the 2-D convolution module to further refine the spatial and texture features. The advantageous complementary properties of 3-D and 2-D convolutions allow the spatial and textural features of hyperspectral images to be fully exploited. Besides, we construct a hyperspectral image dataset including 1200 samples of ten corn varieties. Experiments on our proposed dataset demonstrate that our SSTNet outperforms the state-of-the-art methods for identifying corn varieties.
2022
1-5
journalArticle
60
IEEE Transactions on Geoscience and Remote Sensing
DOI 10.1109/TGRS.2022.3196127
IEEE Transactions on Geoscience and Remote Sensing
ISSN 1558-0644
X. -M. Zhu
X. -N. Song
P. Leng
Z. -L. Li
X. -T. Li
L. Gao
D. Guo
Microwave radiometry
Cloud computing
Atmospheric modeling
Land surface
Maximum likelihood estimation
Microwave imaging
Advanced Microwave Scanning Radiometer for Earth Observing System (AMSR-E) product
all-weather
Clouds
error analysis
microwave land surface emissivity (MLSE)
random forest (RF)
Estimate of Cloudy-Sky Surface Emissivity From Passive Microwave Satellite Data Using Machine Learning
The derivation of microwave land surface emissivity (MLSE) under various weather conditions from the microwave radiometer plays a crucial role in acquiring land surface and atmospheric parameters. Nevertheless, currently, most existing studies mainly focus on the clear-sky scenarios due to a lack of cloudy-sky land surface temperature (LST) and uncertainties in simulating the scattering and emission properties of atmospheric hydrometeors. Under this background, with satellite observations and the random forest (RF) model, this study proposes a method to estimate the MLSE under cloudy skies. First, clear-sky MLSEs with satisfactory accuracy are retrieved by using the brightness temperatures (BTs) from the Advanced Microwave Scanning Radiometer-Earth sensor, LSTs from the Moderate Resolution Imaging Spectroradiometer (MODIS), and atmospheric profiles from the ERA5 reanalysis. Then, the relation among the clear-sky MLSE and related impact factors is built with the RF and extended to the cloudy-sky environment for generating all-weather MLSEs with a 0.25°. The results show that the input datasets present a considerable impact on the calculation of instantaneous MLSE, and a 5.73 K bias of ERA5 LST may generate a 0.014–0.021 error in the MLSE from 6.9- to 89-GHz horizontal polarization, while the impacts of BT and profile uncertainties on the MLSE are smaller. The retrieved clear-sky MLSE is coincident with the existing MLSE for the spatiotemporal variations, and there is an average difference range from −0.035 to 0.035 in January 2008. Meanwhile, the constructed RF model can successfully apply to cloudy-sky status and recover the MLSE image gaps affected by cloud contamination.
2022
1-20
journalArticle
15
IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
DOI 10.1109/JSTARS.2021.3136565
IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
ISSN 2151-1535
Z. Wu
J. Qiu
W. T. Crow
D. Wang
Z. Wang
X. Zhang
Monitoring
Microwave radiometry
Spatial resolution
Indexes
Vegetation mapping
Soil
Agricultural drought
high spatial resolution
Microwave theory and techniques
mutual information (MI)
soil moisture (SM)
soil moisture active passive (SMAP)
Investigating the Efficacy of the SMAP Downscaled Soil Moisture Product for Drought Monitoring Based on Information Theory
Soil moisture (SM) information can be routinely obtained from high-quality microwave retrievals at a global scale—such as datasets generated by the Soil Moisture Active Passive (SMAP) mission. In this article, using mutual information (MI) theory, we investigate the efficacy of the downscaled SMAP/Sentinel-1 L2 3-km EASE-Grid SM product (SPL2) for the detection of agricultural drought over northwestern China. The SPL2 is generated by merging SMAP enhanced radiometer data with Sentinel-1 radar observations. To evaluate the efficiency of the SPL2 downscaled algorithm, the SMAP Enhanced L3 Radiometer 9-km EASE-Grid SM product (SPL3) is also utilized as a non-downscaled baseline. Over croplands, comparing normalized MI (NMI) values sampled between the NDVI time series and 3-km Sentinel-1 C-band backscatter coefficient (σ) from SPL2 with NMI values between NDVI and SPL3 radiometer brightness temperature (Tb; resampled to 3-km resolution), we find that the Sentinel-1 σ explains more (3-km) NDVI information than the SPL3 Tb, as the NMI between σvh (σvv) and NDVI is 15% (8%), larger than that between SPL3 Tb and NDVI (5%). However, compared to the SPL3 Tb baseline, the information from downscaled SPL2 Tb on NDVI is reduced by approximately 3%, and the SPL2 algorithm extracts only 7% (10%) of the total information available from both enhanced SPL3 Tb and Sentinel-1 σvh (σvv). Overall, the C-band σ signal provides valuable information for vegetation monitoring due to its frequency advantage. However, additional efforts should be focused on SPL2 merging algorithms to improve the value of the downscaled SPL2 product for agricultural applications.
2022
1604-1616
journalArticle
8
IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
DOI 10.1109/JSTARS.2015.2461453
10
IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
ISSN 2151-1535
B. Zhong
A. Yang
A. Nie
Y. Yao
H. Zhang
S. Wu
Q. Liu
Agriculture
Remote sensing
Time series analysis
Accuracy
Vegetation mapping
Satellites
Charge coupled devices
Crop classification
HJ-1/CCD
land cover
multiple classifiers
multiple scales
multisource remotely sensed data
phenology
river basin
time-series analysis
Finer Resolution Land-Cover Mapping Using Multiple Classifiers and Multisource Remotely Sensed Data in the Heihe River Basin
Land-cover datasets are crucial for research on eco-hydrological processes and earth system modeling. Many land-cover datasets have been derived from remote-sensing data. However, their spatial resolutions are usually low and their classification accuracy is not high enough, which are not well suited to the needs of land surface modeling. Consequently, a comprehensive method for monthly land-cover classification in the Heihe river basin (HRB) with high spatial resolution is developed. Moreover, the major crops in the HRB are also distinguished. The proposed method integrates multiple classifiers and multisource data. Three types of data including MODIS, HJ-1/CCD, and Landsat/TM and Google Earth images are used. Compared to single classifier, multiple classifiers including thresholding, support vector machine (SVM), object-based method, and time-series analysis are integrated to improve the accuracy of classification. All the data and classifiers are organized using a decision tree. Monthly land-cover maps of the HRB in 2013 with 30-m spatial resolution are made. A comprehensive validation shows great improvement in the accuracy. First, a visual comparison of the land-cover maps using the proposed method and standard SVM method shows the classification differences and the advantages of the proposed method. The confusion matrix is used to evaluate the classification accuracy, showing an overall classification accuracy of over 90% in the HRB, which is quite higher than previous approaches. Furthermore, a ground campaign was performed to evaluate the accuracy of crop classification and an overall accuracy of 84.09% for the crop classification was achieved.
Oct. 2015
4973-4992
journalArticle
8
IEEE Access
DOI 10.1109/ACCESS.2020.2978283
IEEE Access
ISSN 2169-3536
A. Deliège
A. Cioppa
M. Van Droogenbroeck
computer vision
deep learning
Training
Machine learning
Classification
Training data
Computer network reliability
mislabeled data
noisy labels
Reliability engineering
Tools
Ghost Loss to Question the Reliability of Training Data
Supervised image classification problems rely on training data assumed to have been correctly annotated; this assumption underpins most works in the field of deep learning. In consequence, during its training, a network is forced to match the label provided by the annotator and is not given the flexibility to choose an alternative to inconsistencies that it might be able to detect. Therefore, erroneously labeled training images may end up “correctly” classified in classes which they do not actually belong to. This may reduce the performances of the network and thus incite to build more complex networks without even checking the quality of the training data. In this work, we question the reliability of the annotated datasets. For that purpose, we introduce the notion of ghost loss, which can be seen as a regular loss that is zeroed out for some predicted values in a deterministic way and that allows the network to choose an alternative to the given label without being penalized. After a proof of concept experiment, we use the ghost loss principle to detect confusing images and erroneously labeled images in well-known training datasets (MNIST, Fashion-MNIST, SVHN, CIFAR10) and we provide a new tool, called sanity matrix, for summarizing these confusions.
2020
44774-44782
journalArticle
11
IEEE Access
DOI 10.1109/ACCESS.2022.3232917
IEEE Access
ISSN 2169-3536
V. K. Vishnoi
K. Kumar
B. Kumar
S. Mohan
A. A. Khan
Convolutional neural networks
Crops
deep learning
Image color analysis
convolutional neural network
Diseases
Support vector machines
classification
Computational modeling
machine learning
image processing
disease detection
Apple diseases
Lesions
Detection of Apple Plant Diseases Using Leaf Images Through Convolutional Neural Network
Plant diseases are a severe cause of crop losses in the agriculture globally. Detection of diseases in plants is difficult and challenging due to the lack of expert knowledge. Deep learning-based models provide promising ways to identify plant diseases using leaf images. However, need of larger training sets, computational complexity, and overfitting, etc. are the major issues with these techniques that still need to be addressed. In this work, a convolutional neural network (CNN) is developed that consists of smaller number of layers leading to lower computational burden. Some augmentation techniques such as shift, shear, scaling, zoom, and flipping are applied to generate additional samples increasing the training set without actually capturing more images. The CNN model is trained for apple crop using a publicly available dataset PlantVillage to identify Scab, Black rot, and Cedar rust diseases in apple leaves. The rigorous experimental results revealed that the proposed model is well fit to identify apple leaf diseases and achieves 98% classification accuracy. It is also evident from the results that it needs lesser amount of storage and takes smaller execution time than several existing deep CNN models. Although, there exist several CNN models for crop disease detection with comparable accuracy, but the proposed model needs lower storage and computational resources. Therefore, it is highly suitable for deploying in handheld devices.
2023
6594-6609
journalArticle
10
IEEE Access
DOI 10.1109/ACCESS.2022.3150306
IEEE Access
ISSN 2169-3536
Q. Luo
R. Liao
J. Li
X. Ye
S. Chen
Blockchain
Blockchains
Business
Data privacy
Electronic commerce
information credibility
Pipelines
Smart contracts
supply chain
Supply chains
Blockchain Enabled Credibility Applications: Extant Issues, Frameworks and Cases
The credibility of information is known as a major cause of a wide range of issues, such as: altered product information in food supply chains; fake transactions on E-commerce platforms; lengthy claim settlement time in agricultural insurance; and costly borrowings in agricultural financing. For a more specific example in food supply chains, end customers want to check the product information, but either doubt the authenticity of information, or simply do not have access to the information. The reason is that upstream suppliers and downstream retailers are often reluctant to share data, fearing privacy loss or business secret leakage. The consequence is that regulatory departments may face enormous challenges to identify accurate contamination sources, if there is scarce information or falsely recorded information at any stage of the food supply chain. In this paper, we focus on four common scenarios demanding information credibility in the agricultural supply chain: product traceability, E-commerce platforms, agricultural insurance, and agricultural financing. We review some high-profile smart credibility applications with emphasis on how blockchain related technologies can provide the information credibility by examining extant issues and relevant frameworks.
2022
45759-45771
journalArticle
7
IEEE Access
DOI 10.1109/ACCESS.2019.2936536
IEEE Access
ISSN 2169-3536
H. Altaheri
M. Alsulaiman
G. Muhammad
deep learning
Deep learning
Image color analysis
Robots
Computer architecture
convolutional neural networks
Task analysis
Real-time systems
automated harvesting
Dates classification
Machine vision
maturity analysis
Date Fruit Classification for Robotic Harvesting in a Natural Environment Using Deep Learning
An accurate vision system to classify and analyze fruits in real time is critical for harvesting robots to be cost-effective and efficient. However, practical success in this area is still limited, and to the best of our knowledge, there is no research in the area of machine vision for date fruits in an orchard environment. In this work, we propose an efficient machine vision framework for date fruit harvesting robots. The framework consists of three classification models used to classify date fruit images in real time according to their type, maturity, and harvesting decision. In the classification models, deep convolutional neural networks are utilized with transfer learning and fine-tuning on pre-trained models. To build a robust vision system, we create a rich image dataset of date fruit bunches in an orchard that consists of more than 8000 images of five date types in different pre-maturity and maturity stages. The dataset has a large degree of variations that reflects the challenges in the date orchard environment including variations in angles, scales, illumination conditions, and date bunches covered by bags. The proposed date fruit classification models achieve accuracies of 99.01%, 97.25%, and 98.59% with classification times of 20.6, 20.7, and 35.9 msec for the type, maturity, and harvesting decision classification tasks, respectively.
2019
117115-117133
journalArticle
7
IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
DOI 10.1109/JSTARS.2013.2258659
1
IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
ISSN 2151-1535
A. Pérez-Hoyos
F. J. García-Haro
N. Valcárcel
Agriculture
Earth
Remote sensing
Spatial resolution
Accuracy
Vegetation mapping
CORINE
Databases
fuzzy validation
GLC2000
GlobCover
land cover classification
MODISLC
SIOSE
Incorporating Sub-Dominant Classes in the Accuracy Assessment of Large-Area Land Cover Products: Application to GlobCover, MODISLC, GLC2000 and CORINE in Spain
Various global land cover (LC) datasets have been produced from remote sensing data in response to the need for information about LC. Nevertheless, the potential use of global LC products is often very limited by the lack of detailed accuracy information at regional to national level. This paper proposes a methodology for performing accuracy assessment of large-area LC products, which takes into account a number of factors arising from intrinsic characteristics of LC, such as thematic uncertainty that results from the partial overlap in legend definitions and lack of homogeneity within reference and classification data. The approach compares the LC pixel label not only with the dominant reference label but also with sub-dominant LC types within the extent of the sampling unit. The methodology was illustrated in Spain using four LC datasets (GlobCover, MODIS land cover (MODISLC), GLC2000 and CORINE). The variety of reference label data offered by a detailed national database, namely SIOSE, supported several different fuzzy agreement definitions in order to derive unbiased estimates of accuracy measures. CORINE followed by GLC2000 showed the highest accuracy scores, whereas GlobCover and MODISLC showed the lowest scores. Nevertheless, the fuzzy approach revealed that a great amount of disagreement in GlobCover and MODISLC datasets does not actually correspond to classification errors, but it can be associated to legend ambiguity and mixed coverage pixels.
Jan. 2014
187-205
journalArticle
W. Liu
G. Wu
F. Ren
X. Kang
Deep learning
Insects
Task analysis
Optimization
Adaptation models
Convolution
deep feature fusion
image classification
insect pest recognition
residual network
Residual neural networks
DFF-ResNet: An insect pest recognition model based on residual networks
Insect pest control is considered as a significant factor in the yield of commercial crops. Thus, to avoid economic losses, we need a valid method for insect pest recognition. In this paper, we proposed a feature fusion residual block to perform the insect pest recognition task. Based on the original residual block, we fused the feature from a previous layer between two 1×1 convolution layers in a residual signal branch to improve the capacity of the block. Furthermore, we explored the contribution of each residual group to the model performance. We found that adding the residual blocks of earlier residual groups promotes the model performance significantly, which improves the capacity of generalization of the model. By stacking the feature fusion residual block, we constructed the Deep Feature Fusion Residual Network (DFF-ResNet). To prove the validity and adaptivity of our approach, we constructed it with two common residual networks (Pre-ResNet and Wide Residual Network (WRN)) and validated these models on the Canadian Institute For Advanced Research (CIFAR) and Street View House Number (SVHN) benchmark datasets. The experimental results indicate that our models have a lower test error than those of baseline models. Then, we applied our models to recognize insect pests and obtained validity on the IP102 benchmark dataset. The experimental results show that our models outperform the original ResNet and other state-of-the-art methods.
Dec. 2020
300-310
3
Big Data Mining and Analytics
DOI 10.26599/BDMA.2020.9020021
4
Big Data Mining and Analytics
ISSN 2096-0654
journalArticle
Y. Lu
Y. Wang
D. Parikh
A. Khan
G. Lu
Estimation
Cameras
Shape
Three-dimensional displays
cross-view synthesis
Image reconstruction
Periodic structures
Root reconstruction
single image depth estimation
Solid modeling
Simultaneous Direct Depth Estimation and Synthesis Stereo for Single Image Plant Root Reconstruction
Plant roots are the main conduit to its interaction with the physical and biological environment. A 3D root system architecture can provide fundamental and applied knowledge of a plant's ability to thrive, but the construction of 3D structures for thin and complicated plant roots is challenging. Existing methods such as structure-from-motion and shape-from-silhouette require multiple images, as input, under a complicated optimization process, which is usually not convenient in fieldwork. Little effort has been put into investigating the applications of deep neural network methods to reconstruct thin objects, like plant root systems, from a single image. We propose an unsupervised learning scheme to estimate the root depth from only one image as input, which is further applied to reconstruct the complete root system. The boundaries of the reconstructed object usually contain large errors, which is a significant problem for roots with many thin branches. To reduce reconstruction errors, we integrate a cross-view GAN-based network into the reconstruction process, which predicts the root image from a different perspective. Based on the predicted view, we reconstruct the root system using stereo reconstruction, which helps to identify the accurately reconstructed points by enforcing their consistency. The results on both the real plant root dataset and the synthetic dataset demonstrate the effectiveness of the proposed algorithm compared with state-of-the-art single image 3D reconstruction models on plant roots.
2021
4883-4893
30
IEEE Transactions on Image Processing
DOI 10.1109/TIP.2021.3069578
IEEE Transactions on Image Processing
ISSN 1941-0042
journalArticle
A. Biglari
W. Tang
Monitoring
computer vision
Training
machine learning
object detection
agriculture
Animals
Cows
Object recognition
sensor applications
Sensor systems
TensorFlow
Testing
water management
Water resources
A Vision-Based Cattle Recognition System Using TensorFlow for Livestock Water Intake Monitoring
This letter presents a new method for identifying individual cattle for the purpose of tracking and efficiently measuring their daily water intake using a vision-based machine learning system. In addition to the current solution of using radio frequency identification (RFID), the proposed system uses TensorFlow Object Detection to detect labels on the RFID tag. The proposed system can be integrated into the current water intake monitoring system and alleviates the errors introduced by the unreliable RFID readers. The system allows users to train an object recognition model that can recognize and differentiate the labels on the ear tags of individual farm animals, so the drinking events can be recorded by the water intake monitoring system. The models are trained using custom datasets of manually annotated tag images with pretrained model architectures from TensorFlow 2 Model Zoo. The system is tested using images from event-triggered weather-proof cameras deployed in the grazing site. Experimental results of the system showed an accuracy of around 90%. In comparison to other present methods, this newly proposed system provides scalability and flexibility, making it an attractive vision-based solution for machine learning systems in agriculture.
Nov. 2022
1-4
6
IEEE Sensors Letters
DOI 10.1109/LSENS.2022.3215699
11
IEEE Sensors Letters
ISSN 2475-1472
journalArticle
60
IEEE Transactions on Geoscience and Remote Sensing
DOI 10.1109/TGRS.2022.3224221
IEEE Transactions on Geoscience and Remote Sensing
ISSN 1558-0644
K. Xue
R. Ma
Z. Cao
M. Shen
M. Hu
J. Xiong
Lakes
Sensors
Satellites
Algae
Equivalent bloom area (EBA)
eutrophic lakes
fractional floating algae cover (FAC)
MODIS
multisensor
Oceans
pixel un-mixing
Reflectivity
Monitoring Fractional Floating Algae Cover Over Eutrophic Lakes Using Multisensor Satellite Images: MODIS, VIIRS, GOCI, and OLCI
Coarse-resolution sensors have been used operationally to monitor floating algal blooms with a near daily revisit in coastal and inland waters. Most of the current methods in estimating fractional floating algae cover (FAC) were based on the linear pixel un-mixing assumption. In this study, a new FAC model following a logistic curve was developed and applied to multisensor satellite data in two large shallow eutrophic lakes, Lake Taihu and Lake Chaohu, in China. The results indicated that after resampling to 250 m, match-up pairs of Moderate Resolution Imaging Spectroradiometer (MODIS), The Visible and Infrared Imager/Radiometer Suite (VIIRS), Geostationary Ocean Color Imager (GOCI), and Ocean and Land Color Instrument (OLCI) possessed consistent Rayleigh corrected reflectance ( $R_{\mathrm {rc}}$ ) and floating algae index (FAI) or AFAI (alternative FAI). The FAC model was developed based on the simulated AFAI data of GOCI using point spread function (PSF) and bloom percent derived from Operational Land Imager (OLI) and then was applied to MODIS, VIIRS, and OLCI. Compared with the linear pixel un-mixing method, the FAC model reflects the asymptotic reflectance saturation in the near-infrared (NIR) band with the accumulation of blooms. Besides, the equivalent bloom area (EBA) of GOCI was validated using OLI-matched pairs with UPD 37.6% ( $N=39$ , $R^{2}=0.96$ ). The spatial-temporal dataset of FAC (2002–2020) shows that Lake Taihu and Lake Chaohu experienced severe algal blooms after 2010, partly resulting from the higher frequency of multisensor data. This study provides a method for building a lasting and comparable FAC dataset using multisensors.
2022
1-15
journalArticle
8
IEEE Access
DOI 10.1109/ACCESS.2019.2961142
IEEE Access
ISSN 2169-3536
W. I. Gabr
H. T. Dorrah
Irrigation
Crossing the boundaries between sciences
ecology and hydrology
engineering and technology
evolutionary systems
feet/head aggregation networks
head/feet disaggregation networks
life sciences
Mathematical model
medicine and biology
Morphology
multi-step modular modeling
Network topology
Oils
real-life natural and man-made operational networks
Roads
symbolic-based mathematical modeling
the science of botany
the tree of life
Topology
tree-shaped morphology
water and energy
A New Symbolic-Based Flow Aggregation and Disaggregation Modular Approach for Tree-shaped Networks
This paper presents the representation and modeling of real-life tree-shaped natural and man-made networks. It is shown that the tree-shaped networks could be composed of two entities of different functionalities that can operate separately or jointly. The first entity is the feet/head aggregation networks, while the second entity is the head/feet disaggregation networks. Each entity is represented with the same symbolic-based modular model expressions. Moreover, it is illustrated that the aggregation entity network can be mapped through a mirroring type process to an analogous disaggregation entity network and vice versa. The suggested technique is demonstrated by an application of the modeling of 20-nodes real-life tree-shaped irrigation network. The paper also addresses simultaneously the analogy between natural plant tree morphology and natural/man-made operational network of both the aggregation or disaggregation types. It is highlighted that such analogy with the natural tree system could help in future schematizing of stages of operational networks expansion in the most efficient way as learnt from nature and in building advanced generations of operational networks. Furthermore, it is pointed out that the new approach has unlimited scope of real-life applications in engineering/technology such as electric generation, water basins, sewage, agriculture drainage, highway transportation..etc. networks for the aggregation entity, and electric distribution, irrigation, oil, gas, potable water, roads transport,..etc. networks for the disaggregation entity. In all respects, the paper has succeeded within the area of tree-shaped networks in crossing the boundaries between the Science of Botany and Engineering/technology (and vice versa) and to create new common areas of important shared interests of great benefits to these disciplines and the science world as a whole. Finally, the new notion of crossing boundaries between sciences can also be extended to and among many other sciences themselves dealing with tree-shaped systems.
2020
325-337
journalArticle
10
IEEE Access
DOI 10.1109/ACCESS.2022.3204114
IEEE Access
ISSN 2169-3536
A. Pal
A. Chowdhury
Satakshi
H. S. Narman
A. Chowdhury
M. Kumar
Data models
Support vector machines
classification
Optimization
Classification algorithms
Training data
Big Data
Distributed databases
Distributed learning
distributed processing
Distributed processing
distributed storage
large datasets
Learning systems
Storage management
SVM
Random Partition Based Adaptive Distributed Kernelized SVM for Big Data
In this paper, we present a distributed classification technique for big data by efficiently using distributed storage architecture and data processing units of a cluster. While handling such large data, the existing approaches consider specific data partitioning techniques which demand complete data be processed before partitioning. This leads to an excessive overhead of high computation and data communication. The proposed method does not require any pre-structured data partitioning technique and is also adaptive to big data mining tools. We hypothesize that an effective aggregation of the information generated from data partitions by subprocesses of the complete learning process can lead to accurate prediction results while reducing the overall time complexity. We build three SVM based classifiers, namely one phase voting SVM (1PVSVM), two phase voting SVM (2PVSVM), and similarity based SVM (SIMSVM). Each of these classifiers utilizes the support vectors as the local information to construct the synthesized learner for efficiently reducing the training time and ensuring minimal communication between processing units. In this context, an extensive empirical analysis demonstrates the effectiveness of our classifiers when compared to other existing approaches on several benchmark datasets. However, among existing methods and three of our proposed (1PVSVM, 2PVSIM, and SIMSVM) methods, SIMSVM is the most efficient. Considering MNIST dataset, SIMSVM achieves an average speedup ratio of 0.78 and minimum scalability of 73% when the data size is scaled up to 10 times. It also retains high accuracy (99%) similar to centralized approaches.
2022
95623-95637
journalArticle
14
IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
DOI 10.1109/JSTARS.2020.3042887
IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
ISSN 2151-1535
N. Bengana
J. Heikkilä
Image resolution
Earth
image segmentation
Image segmentation
Remote sensing
Semantics
Satellites
Domain adaptation (DA)
land cover segmentation
Satellite broadcasting
Improving Land Cover Segmentation Across Satellites Using Domain Adaptation
Land use and land cover mapping is essential to various fields of study, such as forestry, agriculture, and urban management. Generally, earth observation satellites facilitate and accelerate the mapping process. Subsequently, deep learning methods have been proven to be excellent in automating the mapping via semantic image segmentation. However, because deep neural networks require large amounts of labeled data, it is not easy to exploit the full potential of satellite imagery. Additionally, land cover tends to differ in appearance from one region to another; therefore, having labeled data from one location does not necessarily help map others. Furthermore, satellite images come in various multispectral bands, which range from RGB to over 12 bands. In this study, our aim is to use domain adaptation (DA) to solve the aforementioned problems. We applied a well-performing DA approach on the DeepGlobe land cover dataset as well as datasets that we built using RGB images from Sentinel-2, WorldView-2, and Pleiades-1B satellites with CORINE Land Cover as ground truth (GT) labels. The experiments revealed significant improvements over the results obtained without using DA. In some cases, an improvement of over 20% mean intersection over union was obtained. Sometimes, our model manages to correct errors in the GT labels.
2021
1399-1410
journalArticle
60
IEEE Transactions on Geoscience and Remote Sensing
DOI 10.1109/TGRS.2022.3202609
IEEE Transactions on Geoscience and Remote Sensing
ISSN 1558-0644
P. L. Bykov
V. A. Gordin
L. L. Tarasova
E. V. Vasilenko
neural networks
remote sensing
Soil measurements
Soil moisture
Satellites
Soil
soil moisture
Data assimilation
Extraterrestrial measurements
Moisture
Moisture measurement
Inhomogeneous Anisotropic Analysis of the Available Water Content of the Upper Soil Layer According to Ground-Based and Remote Sensing on the Territory of Russia
The Hydrometeorological Center of Russia receives agrometeorological information from about 950 stations one time per ten days and the remote sensing Advanced Scatterometer (ASCAT) data from three Meteorological Operational (MetOp) satellites. We suggest a combined objective analysis (OA) of the available water content based on the available water content measurements at agrometeorological stations and on remote sensing data. The new version of OA is constructed using two neural networks and the backpropagation of error to learn it simultaneously. The first neural network is used to convert the ASCAT data into the available water content values, and the second network is used to estimate the inhomogeneities of soil moisture fields. We use the optimal interpolation (OI) method for assimilation of the ground-based data. In the new version, we evaluate the correlation functions (CFs) of inhomogeneous non-Gaussian fields, not from sample statistics but from machine learning methods. The method takes into account the combining of various datasets: ASCAT data, Food and Agriculture Organization (FAO) soil types, European Space Agency (ESA) GlobCover, and National Center for Atmospheric Research (NCAR) climate data.
2022
1-9
journalArticle
H. Chopra
H. Singh
M. S. Bamrah
F. Mahbubani
A. Verma
N. Hooda
P. S. Rana
R. K. Singla
A. K. Singh
computer vision
Computer vision
Training
Cameras
Machine learning
Sensors
driverlessAI
fruit grading
Python
spectroscopy
Spectroscopy
Efficient Fruit Grading System Using Spectrophotometry and Machine Learning Approaches
Physical Classification of ripe fruits is an expensive affair in the agriculture industry and human error can lead to inaccurate results. This paper introduces the concept of an intelligent AI-based system using spectrophotometry and computer vision for automated fruit segregation based on their grade. When the fruit is fed into the proposed system, the fruit is identified with 95% accuracy, using a cloud-computing platform provided by Microsoft Azure. After that, using spectroscopy and ensemble machine learning approaches, fruit grade is predicted. This ensemble model is trained using 1366 apple readings taken from Unitec's Apple Sorting and Grading Machine from an industrial plant. With the help of H2O's Driverless.AI, the proposed ensemble provides an overall approximate validation accuracy of 82%. The model is also tested on an unseen test dataset containing real-life spectral values and the accuracy of fruit segregation into different classes peaked at 72%.
15 July15, 2021
16162-16169
21
IEEE Sensors Journal
DOI 10.1109/JSEN.2021.3075465
14
IEEE Sensors Journal
ISSN 1558-1748
journalArticle
8
IEEE Access
DOI 10.1109/ACCESS.2020.3022842
IEEE Access
ISSN 2169-3536
P. Anand
Y. Singh
A. Selwal
M. Alazab
S. Tanwar
N. Kumar
Computer architecture
Temperature sensors
machine learning
Security
Internet of Things
security
cyberattacks
IoT
privacy
Protocols
sustainability
vulnerabilities
IoT Vulnerability Assessment for Sustainable Computing: Threats, Current Solutions, and Open Challenges
Over the last few decades, sustainable computing has been widely used in areas like social computing, artificial intelligence-based agent systems, mobile computing, and Internet of Things (IoT). There are social, economic, and commercial impacts of IoT on human lives. However, IoT nodes are generally power-constrained with data transmission using an open channel, i.e., Internet which opens the gates for various types of attacks on them. In this context, several efforts are initiated to deal with the evolving security issues in IoT systems and make them self-sufficient to harvest energy for smooth functioning. Motivated by these facts, in this paper, we explore the evolving vulnerabilities in IoT devices. We provide a state-of-the-art survey that addresses multiple dimensions of the IoT realm. Moreover, we provide a general overview of IoT, Sustainable IoT, its architecture, and the Internet Engineering Task Force (IETF) protocol suite. Subsequently, we explore the open-source tools and datasets for the proliferation in research and growth of IoT. A detailed taxonomy of attacks associated with various vulnerabilities is also presented in the text. Then we have specifically focused on the IoT Vulnerability Assessment techniques followed by a case study on sustainability of Smart Agriculture. Finally, this paper outlines the emerging challenges related to IoT and its sustainability, and opening the doors for the beginners to start research in this promising area.
2020
168825-168853
journalArticle
10
IEEE Access
DOI 10.1109/ACCESS.2022.3228160
IEEE Access
ISSN 2169-3536
A. A. Khan
M. Faheem
R. N. Bashir
C. Wechtaisong
M. Z. Abbas
Crops
Bayes methods
Agriculture
Machine learning
machine learning
Internet of Things
Vegetation mapping
Soil
fertilizer recommendation
Fertilizers
Gaussian Naïve Bayes (GNB)
Internet of Things (IoT)
k-nearest neighbor (KNN)
logistic regression (LR)
Nearest neighbor methods
Recommender systems
soil fertility mapping
support vector machine (SVM)
Internet of Things (IoT) Assisted Context Aware Fertilizer Recommendation
An accurate amount of fertilizer according to the real-time context is the basis of precision agriculture in terms of sustainability and profitability. Many fertilizers recommendation systems are proposed without considering the real-time context in terms of soil fertility level, crop type, and soil type. The major obstacle in developing the real-time context-aware fertilizer recommendation system is related to the complexity associated with the real-time mapping of soil fertility. Furthermore, the existing methods of determining the real-time soil fertility levels for the recommendation of fertilizer are costly, time-consuming, and laborious. Therefore, to tackle this issue, we propose a machine learning-based fertilizer recommendation methodology according to the real-time soil fertility context captured through the Internet of Things (IoT) assisted soil fertility mapping to improve the accuracy of the fertilizer recommendation system. For real-time soil fertility mapping, an IoT architecture is also proposed to support context-aware fertilizer recommendations. The proposed solution is practically implemented in real crop fields to assess the accuracies of IoT-assisted fertility mapping. The accuracy of IoT-assisted fertility mapping is assessed by comparing the proposed solution with the standard soil chemical analysis method in terms of observing Nitrogen (N), Phosphorous (P), and Potassium (K). The results reveal that the observations by both methods are in line with a mean difference of 0.34, 0.36, and −0.13 for N, P, and K observations, respectively. The context-aware fertilizer recommendation is implemented with the Logistic Regression (LR), Support Vector Machine (SVM), Gaussian Naïve Bayes (GNB), and K-Nearest Neighbor (KNN) machine learning models to assess the performance of these machine learning models. The evaluation of the proposed solution reveals that the GNB model is more accurate as compared to the machine learning models evaluated, with accuracies of 96% and 94% from training and testing datasets, respectively.
2022
129505-129519
journalArticle
60
IEEE Transactions on Geoscience and Remote Sensing
DOI 10.1109/TGRS.2021.3134564
IEEE Transactions on Geoscience and Remote Sensing
ISSN 1558-0644
A. Hassanzadeh
F. Zhang
S. P. Murphy
S. J. Pethybridge
J. van Aardt
Crops
Feature extraction
Hyperspectral imaging
feature selection
machine learning
Indexes
Classification
precision agriculture
Vegetation mapping
Data collection
hyperspectral imaging
maturity assessment
Noise reduction
pod size
snap bean
unmanned aerial system (UAS)
Toward Crop Maturity Assessment via UAS-Based Imaging Spectroscopy—A Snap Bean Pod Size Classification Field Study
Timely assessment of crop maturity contributes to optimized harvesting schedules while limiting food loss/waste at the farm level. Maturity assessments are typically performed via costly and time-consuming in situ methods. This study aimed to evaluate pod size crop maturity using imaging spectroscopy via unmanned aerial systems (UASs), as well as identifying discriminating wavelengths, using snap bean as a proxy crop. The research utilized a UAS-mounted hyperspectral imager in the visible-to-near-infrared region. Two years’ worth of data were collected at two different geographical locations for six different snap bean cultivars. Our approach consisted of calibration to reflectance, vegetation detection, noise reduction, creating classification bins, and feature selection. We used our previously published feature selection library, Jostar, and utilized ant colony optimization and simulated annealing to detect five spectral features and Plus-L Minus-R to identify one to ten features. We utilized decision trees and random forest classifiers for the classification task. Our findings show that, given the proper wavelengths, accurate pod maturity assessment is feasible for large-sieve cultivars (F1 score = 0.79–0.91), separating sieve sizes between ready-to-harvest and not ready-to-harvest pods. These spectral features were in the ~450, ~530, ~660, 700–720, ~740, and ~760 nm regions. This bodes well for the potential extension of results to an operational, multispectral sensor, tuned with the identified bands, thereby negating the need for a costly hyperspectral system. However, this proposition mandates further investigation, including data acquisition from geographical locations with variable climates, and quantifying noise for the hyperspectral imager to compare results with noisier datasets.
2022
1-17
journalArticle
F. Deng
W. Mao
Z. Zeng
H. Zeng
B. Wei
Data models
Feature extraction
Diseases
Training
Convergence
Neural networks
object detection
Disease and pest detection
faster region convolutional neural network (R-CNN)
federated learning (FL)
multiscale integration
Servers
Multiple Diseases and Pests Detection Based on Federated Learning and Improved Faster R-CNN
Traditional disease and pest detection technology employ cloud-based deep learning, which facing the pressures, such as high data storage and communication costs, unbalanced and insufficient data from orchards, diversity of pests and diseases, and complex detection environments. In this article, we propose a multiple pest detection technique based on federated learning (FL) and improved faster region convolutional neural network (R-CNN). As the new distributed computing model, FL can derive a shared model integrating the advantages of data from all parties without uploading local data and also reduces the communication cost. A restriction $M$ is added to the FL algorithm to ensure the convergence of the model and improve the training speed. According to the original faster R-CNN network, ResNet-101 is used instead of VGG-16 to construct the base convolutional layer to maintain the original structure of small-sized targets and improve the detection speed. Then, the multisize fusion of feature maps from different convolutional layers is performed to improve the detection accuracy of multisize multiple pests and diseases. Finally, a soft-nonmaximum suppression (NMS) algorithm is proposed to solve the apple obscured problem after the region proposal network (RPN). The experimental results show that the improved faster R-CNN can achieve an average accuracy of 90.27% on multiple pest detection, and the detection time is only 0.05 s per image. After using FL, the mean average precision (mAP) of the model reached 89.34% and the model training speed was improved by 59%.
2022
1-11
71
IEEE Transactions on Instrumentation and Measurement
DOI 10.1109/TIM.2022.3201937
IEEE Transactions on Instrumentation and Measurement
ISSN 1557-9662
journalArticle
12
IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
DOI 10.1109/JSTARS.2019.2898727
4
IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
ISSN 2151-1535
L. Mascolo
G. Forino
F. Nunziata
G. Pugliano
M. Migliaccio
Feature extraction
Monitoring
Backscatter
Synthetic aperture radar
synthetic aperture radar (SAR)
Training
Agriculture
Time series analysis
rice mapping
A New Methodology for Rice Area Monitoring With COSMO-SkyMed HH–VV PingPong Mode SAR Data
In this paper, a novel approach is proposed to exploit a time series of COSMO-SkyMed (CSK) HH-VV SAR images to map rice fields and to estimate the sowing dates. The approach relies on multi-polarization features, i.e., the squared modulus of the HH and VV channels and the polarization ratio, extracted from CSK SAR scenes. The key step consists of extracting a rice training signature related to the multipolarization features. This signature allows estimating the sowing date that, at once, is used to refine the rice map obtained by the conventional interpretation of the CSK time series in terms of the scattering mechanisms of the different growing cycles. Experiments, carried out on a time series of 32 CSK images, collected from the Mekong Delta region, South Vietnam, confirm the soundness of the proposed methodology which is shown to provide results comparable to the ones obtained by a literature approach that exploits a similar dataset.
April 2019
1076-1084
journalArticle
5
IEEE Robotics and Automation Letters
DOI 10.1109/LRA.2020.2966398
2
IEEE Robotics and Automation Letters
ISSN 2377-3766
E. Bellocchio
G. Costante
S. Cascianelli
M. L. Fravolini
P. Valigi
Robots
Training
Agriculture
Biological system modeling
Task analysis
Agricultural automation
Picture archiving and communication systems
robotics in agriculture and forestry
visual learning
Yield estimation
Combining Domain Adaptation and Spatial Consistency for Unseen Fruits Counting: A Quasi-Unsupervised Approach
Autonomous robotic platforms can be effectively used to perform automatic fruits yield estimation. To this aim, robots need data-driven models that process image streams and count, even approximately, the number of fruits in an orchard. However, training such models following a supervised paradigm is expensive and unpractical. Extending pre-trained models to perform yield estimation for a completely new type of fruit is even more challenging, but interesting since this situation is typical in practice. In this work, we combine a State-of-the-Art weakly-supervised fruit counting model with an unsupervised style transfer method for addressing the task above. In this sense, our proposed approach is quasi-unsupervised. In particular, we use a Cycle-Generative Adversarial Network (C-GAN) to perform unsupervised domain adaptation and train it alongside with a Presence-Absence Classifier (PAC) that discriminates images containing fruits or not. The PAC produces the weak-supervision signal for the counting network, that can then be used on the target orchard directly. Experiments on datasets collected in four different orchards show that the proposed approach is more accurate than the supervised baseline methods.
April 2020
1079-1086
journalArticle
7
IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
DOI 10.1109/JSTARS.2014.2308273
9
IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
ISSN 2151-1535
L. Zhao
J. Yang
P. Li
L. Zhang
Monitoring
Image color analysis
Synthetic aperture radar
Agriculture
Remote sensing
classification
Scattering
crop harvest patterns
Decision trees
high frequency
radar polarimetry
Characteristics Analysis and Classification of Crop Harvest Patterns by Exploiting High-Frequency MultiPolarization SAR Data
At harvest season, crops are often harvested using various methods at different times. Mapping and monitoring of the patterns of croplands during the harvest period provide information for farmers to help guide the harvest practices that are time critical and to support early warning of threats to food security. This study discusses the feasibility of high-frequency (C/X) polarimetric synthetic aperture radar (PolSAR) for the discrimination of crop patterns during harvest. The polarimetric signals gathered from a farmland area during harvest in Inner Mongolia, China, have been evaluated to investigate the properties of different harvest patterns by using the fully polarimetric Radarsat-2 and dual-pol TerraSAR-X images. A set of polarimetric parameters were derived from the datasets to interpret the radar signatures. The statistics show the sensitivity of the polarimetric parameters to the properties of the harvest patterns. The crop type, biomass, water content held by plants, crop swath direction, and crop state make a large contribution to the fluctuation of the polarimetric scattering characteristics. By exploring the polarimetric characteristics across different harvest patterns, a new method of mapping the harvest state is proposed by utilizing the decision tree algorithm. In the proposed method, GIS data are exploited to avoid the confusion of similar harvest patterns for different species. The harvest pattern mapping results by using the multipolarimetric data acquired over the study area in different years, demonstrate the feasibility and potential of polarimetric data of short wavelength for harvest pattern monitoring during harvest.
Sept. 2014
3773-3783
journalArticle
3
IEEE Robotics and Automation Letters
DOI 10.1109/LRA.2018.2855052
4
IEEE Robotics and Automation Letters
ISSN 2377-3766
M. Imperoli
C. Potena
D. Nardi
G. Grisetti
A. Pretto
Agriculture
Optimization
Robustness
Global Positioning System
localization and sensor fusion
Pose estimation
Robot sensing systems
Robotics in agriculture and forestry
An Effective Multi-Cue Positioning System for Agricultural Robotics
The self-localization capability is a crucial component for Unmanned Ground Vehicles in farming applications. Approaches based solely on visual cues or on a low-cost Global Positioning System (GPS) are easily prone to fail in such scenarios. In this letter, we present a robust and accurate three-dimensional (3-D) global pose estimation framework, designed to take full advantage of heterogeneous sensory data. By modeling the pose estimation problem as a pose graph optimization, our approach simultaneously mitigates the cumulative drift introduced by motion estimation systems (wheel odometry, visual odometry, etc) and the noise introduced by raw GPS readings. Along with a suitable motion model, our system also integrates two additional types of constraints, namely, a Digital Elevation Model and a Markov Random Field assumption. We demonstrate how using these additional cues substantially reduces the error along the altitude axis and, moreover, how this benefit spreads to the other components of the state. We report exhaustive experiments combining several sensor setups, showing accuracy improvements ranging from 37% to 76% with respect to the exclusive use of a GPS sensor. We show that our approach provides accurate results even if the GPS unexpectedly changes positioning mode. The code of our system along with the acquired datasets is released with this letter.
Oct. 2018
3685-3692
journalArticle
D. Gao
L. Wang
B. Hu
Wireless communication
Bluetooth
cross-technology communication
Cyber-physical systems
heterogeneous IoT networks.
Heterogeneous networks
IEEE 802.15 Standard
Logic gates
Radio spectrum management
Resource management
Social factors
Spectrum allocation
Wireless fidelity
Zigbee
Spectrum Efficient Communication for Heterogeneous IoT Networks
Spectrum sharing for coexistence between heterogenous IoT (Internet of Things) networks degrades data communication effectiveness severely. Cross-Technology Communication(CTC) enables that heterogeneous devices can talk to each other directly, which sheds light on spectrum allocation of heterogeneous IoT networks for efficient communication based on CTC, such as, a WiFi device, as a sophisticated leader, coordinates the spectrum allocation for achieving efficient communication on off-the-shelf devices. In this work, we propose a simple spectrum allocation strategy, which is suitable for any duty-cycles of WiFi and ZigBee devices. Depending on the scheme, heterogeneous devices arrange their working schedules and each device monopolizes its time slots to evade data collisions and reduce wireless interference for achieving efficient communication. We implement a network-layer spectrum allocation technique, called CoWBee, that can be easily deployed in existing WiFi infrastructure without modifying the firmware or hardware of both WiFi and ZigBee devices. CoWBee is evaluated based on our platform and the results show our scheme based on CTC is feasible, which provides valuable insights about the spectrum allocation on achieving desirable performance.
1 Nov.-Dec. 2022
3945-3955
9
IEEE Transactions on Network Science and Engineering
DOI 10.1109/TNSE.2022.3150575
6
IEEE Transactions on Network Science and Engineering
ISSN 2327-4697
journalArticle
10
IEEE Access
DOI 10.1109/ACCESS.2022.3213354
IEEE Access
ISSN 2169-3536
J. Liu
W. Hou
X. Luo
J. Su
Y. Hou
Z. Wang
Feature extraction
Generative adversarial networks
Agriculture
Remote sensing
Spatial resolution
self-attention
GAN
Optical sensors
spatial multi-directional perception
thin cloud removal
SI-SA GAN: A Generative Adversarial Network Combined With Spatial Information and Self-Attention for Removing Thin Cloud in Optical Remote Sensing Images
In agricultural remote sensing monitoring, climate often affects the quality of optical remote sensing image data acquisition. The acquired satellite imagery results usually contain cloud information, leading to a lack of ground data information. Unlike thick clouds, the semi-transparent nature of thin clouds prevents thin clouds from completely obscuring the ground scene. In order to remove thin clouds in the cultivated land and restore the actual ground information as much as possible, we proposed a cloud removal method of spatial information fusion self-attention generative adversarial network (SI-SA GAN) based on multi-directional perceptual attention and self-attention mechanism. The proposed method identifies and focuses on cloud regions using spatial attention, channel attention, and self-attention mechanism, which can enhance image information. The modules of the discriminator utilize residual networks and self-attention non-local neural networks to guide image information output. The generative adversarial network (GAN) is applied to remove clouds and restore the corresponding irregular occlusion area according to the depth characteristics of the input information. A gradient penalty is applied to improve the robustness of the generative network. In this paper, we compared the evaluation indexes of other advanced models. The qualitative and quantitative results of Sentinel-2A and public RICE datasets confirmed that the proposed method could enhance image quality effectively after cloud removal. The model has excellent thin cloud removal performance with small-scale training data.
2022
114318-114330
journalArticle
8
IEEE Access
DOI 10.1109/ACCESS.2019.2963590
IEEE Access
ISSN 2169-3536
R. M. A. Latif
S. B. Belhaouari
S. Saeed
L. B. Imran
M. Sadiq
M. Farhan
Agriculture
Temperature sensors
Production
Temperature distribution
Meteorology
ensemble
analysis
CNN
frost event
Google
Google Play store
measurement
prediction
scraping
Integration of Google Play Content and Frost Prediction Using CNN: Scalable IoT Framework for Big Data
The forecast of frost occurrence requires complex decision analysis that uses conditional probabilities. Due to frost events, the production of crops and flowers gets reduced, and we must predict this event to minimize the damages. If the frost prediction results are accurate, then the damage caused by frost can be reduced. In this paper, an ensemble learning approach is used to detect frost events with Convolutional Neural Network (CNN). We have used this to get more efficient and accurate results. Frost events need to be predicted earlier so that the farmer can take on-time precautionary measures. So, for measurement and analysis of Google Play, we have scrapped a dataset of the Agricultural category from different genres and collected the top 550 application of each category of Agricultural applications with 70 attributes for each category. The prediction of frost events prior few days of an actual frost event with an accuracy of 98.86%.
2020
6890-6900
journalArticle
7
IEEE Access
DOI 10.1109/ACCESS.2019.2903830
IEEE Access
ISSN 2169-3536
Y. Fujimoto
S. Murakami
N. Kaneko
H. Fuchikami
T. Hattori
Y. Hayashi
Agriculture
Machine learning
Mathematical model
Additives
Analysis of plant data
Analytical models
directed graphical model
energy-aware plant growth control
Graphical models
identification of linearity/nonlinearity
overlap group lasso
plant factory
Production facilities
sparse partially linear model
Machine Learning Approach for Graphical Model-Based Analysis of Energy-Aware Growth Control in Plant Factories
In recent decades, there has been a gradual penetration of plant factories achieving semiautomated crop cultivation. However, efficient energy utilization, as well as quality control of crops, are very important factors with regard to sustainable operation. Operating parameters, such as room temperature, affect not only the quality of crops but also the electric power required to realize the target operation while being influenced by the environment outside the plant. Therefore, a methodology is needed to analyze and interpret the relationships among these manipulated variables, exogenous variables, crop quality, and the amount of required electric power. Constructing a directed acyclic graph composed of regression models is an attractive approach for such analysis; however, the relationships can possibly be nonlinear, so the direct application of existing analytic approaches will not be appropriate. In this paper, we propose a methodology for relationship analysis among variables based on the directed acyclic graphs while identifying the linearity/nonlinearity in their relationships. In general, the construction of such a graphical model has computational issues, especially when the number of variables is large, and the risk of overfitting. The proposed method utilizes the idea of sparse regularization, which has been actively discussed in the field of machine learning, for realizing the automatic identification of linearity/nonlinearity between variables and screening redundant candidate structures; this approach relaxes the computational complexity issue and controls the risk of overfitting. As a case study, the proposed method is applied to a dataset collected from a real-world cultivation system in a plant factory to discuss its usefulness.
2019
32183-32196
journalArticle
8
IEEE Access
DOI 10.1109/ACCESS.2020.2991552
IEEE Access
ISSN 2169-3536
Q. Dai
X. Cheng
Y. Qiao
Y. Zhang
deep learning
Deep learning
Diseases
Generative adversarial networks
Insects
Agriculture
Image segmentation
classification
Agricultural pests
object instance segmentation
quadra-attention
residual and dense fusion
super-resolution
Agricultural Pest Super-Resolution and Identification With Attention Enhanced Residual and Dense Fusion Generative and Adversarial Network
The growth of the most significant field crops such as rice, wheat, maize, and soybean are influenced because of various pests. And crop production is decreased due to various categories of insects. Deep learning technologies significantly increased the efficiency of identifying and controlling agricultural pests attack. However, agricultural pests images obtained are often obscure and unclear because of the sparse density of cameras deployed in the real farmland. This always makes pests difficult to recognize and monitor. Additionally, the existing classification and segmentation methods are not satisfying for the identification of low-resolution images because they are pre-trained on the clear and high-resolution datasets. Therefore, it is crucial to restore and upscale the obtained low-resolution pest images in order to improve classification accuracy and the recall rate of the instance segmentation. In this paper, we propose a generative adversarial network (GAN) with quadra-attention and residual and dense fusion mechanisms to transform low-resolution pest images. Compared with previous state-of-the-art PSNR-oriented super-resolution methods, our proposed method is more powerful in image reconstruction and achieves the state of the art performance. The experiment results show that after reconstructing with our proposed gan, the recall rate increased by 182.89% and classification accuracy also improved a lot. Besides, our proposed method could decrease the density of the camera layout in the agricultural Internet of Things (IOT) monitor systems and the cost of infrastructure, which is practical for real-world applications.
2020
81943-81959
journalArticle
7
IEEE Access
DOI 10.1109/ACCESS.2019.2954587
IEEE Access
ISSN 2169-3536
K. Zou
L. Ge
C. Zhang
T. Yuan
W. Li
Feature extraction
Image color analysis
Training
Agriculture
Support vector machines
Image segmentation
Soil
broccoli seedling
multiple features
Pattern recognition
support vector machine
weed
Broccoli Seedling Segmentation Based on Support Vector Machine Combined With Color Texture Features
The segmentation of broccoli seedlings in the crops and weeds co-exist field environment is of great significance for weeding and herbicide spraying. This paper constructed a crop segmentation algorithm with a small training set for discriminating broccoli seedlings from weeds and soil. This algorithm was based on a support vector machine (SVM) combined with color-texture features. Correlation analysis and chi-square tests were used to select 6 features from the 21 color features. Gray-level co-occurrence matrix (GLCM) was used to extract 5 texture features. And each parameter of GLCM had been assessed and optimized by the chi-square test. Linear Discriminant Analysis (LDA) was used to decompose the original dataset in a set of 3 successive orthogonal components. This method selected features more reasonable and gained higher plant segmentation accuracy. When the training sample is greater than 50, the accuracy of the test set could reach 90%. The coefficient of determination (R2) between the ground truth broccoli seedling area and the segmentation broccoli area was 0.91, and the root-mean-square error (σ) was 0.10. Results demonstrated that the color-texture features were able to effectively segment broccoli seedlings even when there was a significant amount of weeds.
2019
168565-168574
journalArticle
8
IEEE Access
DOI 10.1109/ACCESS.2020.2989052
IEEE Access
ISSN 2169-3536
A. S. Aguiar
F. N. D. Santos
A. J. M. De Sousa
P. M. Oliveira
L. C. Santos
Feature extraction
Deep learning
Robots
Diseases
Agriculture
convolutional neural networks
transfer learning
Image segmentation
Task analysis
Performance evaluation
tensor processing unit
Visual Trunk Detection Using Transfer Learning and a Deep Learning-Based Coprocessor
Agricultural robotics is nowadays a complex, challenging, and exciting research topic. Some agricultural environments present harsh conditions to robotics operability. In the case of steep slope vineyards, there are several challenges: terrain irregularities, characteristics of illumination, and inaccuracy/unavailability of signals emitted by the Global Navigation Satellite System (GNSS). Under these conditions, robotics navigation becomes a challenging task. To perform these tasks safely and accurately, the extraction of reliable features or landmarks from the surrounding environment is crucial. This work intends to solve this issue, performing accurate, cheap, and fast landmark extraction in steep slope vineyard context. To do so, we used a single camera and an Edge Tensor Processing Unit (TPU) provided by Google's USB Accelerator as a small, high-performance, and low power unit suitable for image classification, object detection, and semantic segmentation. The proposed approach performs object detection using Deep Learning (DL)-based Neural Network (NN) models on this device to detect vine trunks. To train the models, Transfer Learning (TL) is used on several pre-trained versions of MobileNet V1 and MobileNet V2. A benchmark between the two models and the different pre-trained versions is performed. The models are pre-trained in a built in-house dataset, that is publicly available containing 336 different images with approximately 1,600 annotated vine trunks. There are considered two vineyards, one using camera images with the conventional infrared filter and others with an infrablue filter. Results show that this configuration allows a fast vine trunk detection, with MobileNet V2 being the most accurate retrained detector, achieving an overall Average Precision of 52.98%. We briefly compare the proposed approach with the state-of-the-art Tiny YOLO-V3 running on Jetson TX2, showing the outperformance of the adopted system in this work. Additionally, it is also shown that the proposed detectors are suitable for the Localization and Mapping problems.
2020
77308-77320
journalArticle
6
IEEE Access
DOI 10.1109/ACCESS.2018.2884199
IEEE Access
ISSN 2169-3536
A. Khan
U. Khan
M. Waleed
A. Khan
T. Kamal
S. N. K. Marwat
M. Maqsood
F. Aadil
Vegetation
Agriculture
Image segmentation
Remote sensing
Satellites
Tools
Blob detection
crop estimation
Hough transform
multi-spectral imagery
olive
satellite imagery
Remote Sensing: An Automated Methodology for Olive Tree Detection and Counting in Satellite Images
Cultivation of olive trees for the past few years has been widely spread across Mediterranean countries, including Spain, Greece, Italy, France, and Turkey. Among these countries, Spain is listed as the largest olive producing country with almost 45% of olive oil production per year. Dedicating land of over 2.4 million hectares for the olive cultivation, Spain is among the leading distributors of olives throughout the world. Due to its high significance in the country's economy, the crop yield must be recorded. Manual collection of data over such expanded fields is humanly infeasible. Remote collection of such information can be made possible through the utilization of satellite imagery. This paper presents an automated olive tree counting method based on image processing of satellite imagery. The images are pre-processed using the unsharp masking followed by improved multi-level thresholding-based segmentation. Resulting circular blobs are detected through the circular Hough transform for identification. Validation has been performed by evaluating the proposed scheme for the dataset formed by acquiring images through the “El Sistema de Información Geográfica de Parcelas Agrícolas”viewer over the region of Spain. The proposed algorithm achieves an accuracy of 96% in detection. Computation time was recorded as 24 ms for an image size of 300 × 300 pixels. The less spectral information is used in our proposed methodology resulting in a competitive accuracy with low computational cost in comparison to the state-of-the-art technique.
2018
77816-77828
journalArticle
13
IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
DOI 10.1109/JSTARS.2020.3019046
IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
ISSN 2151-1535
J. Sun
Z. Lai
L. Di
Z. Sun
J. Tao
Y. Shen
Agriculture
Earth
Remote sensing
Machine learning
Meteorology
MODIS
Satellite broadcasting
prediction
Convolutional neural network (CNN)
county-level
long short-term memory (LSTM)
yield
Multilevel Deep Learning Network for County-Level Corn Yield Estimation in the U.S. Corn Belt
Accurate and timely estimation of crop yield at a small scale is of great significance to food security and harvest management. Recent studies have proven remote sensing is an efficient method for yield estimation and machine learning, especially deep learning, can infer a good prediction by integrating multisource datasets such as satellite data, climate data, soil data, and so on. However, there are some bottleneck challenges to improve accuracy. First, the popular remote sensing data used for yield prediction fall into two major groups-time-series data and constant data. Surprisingly little attention has been devoted to deep learning networks which can integrate the two kinds of data effectively; second, both temporal and spatial features play a role in affecting the yields. But most of the existing approaches employed either convolutional neural network (CNN) or recurrent neural network (RNN). CNN cannot learn temporal patterns, while RNN barely can learn spatial characteristics. This work proposed a novel multilevel deep learning model coupling RNN and CNN to extract both spatial and temporal features. The inputs include both time-series remote sensing data, soil property data, and the model outputs yield. We experimented with the model in U.S. Corn Belt states, and used it to predict corn yield from 2013 to 2016 at the county-level. The results approve the effectiveness and advantages of the proposed approach over the other methods. In the future, the model will be used on other crops such as soybean and winter wheat to assist agricultural decision-making.
2020
5048-5060
journalArticle
9
IEEE Access
DOI 10.1109/ACCESS.2021.3059431
IEEE Access
ISSN 2169-3536
P. Xi
P. Lin
Y. Lin
H. Zhou
S. Cheng
Z. Chen
L. Wu
Data models
Feature extraction
Machine learning
machine learning
Circuit faults
fault diagnosis
Fault diagnosis
fisher discrimination criterion
fisher discrimination dictionary learning
Photovoltaic array
Photovoltaic systems
sparse representation
Transient analysis
Online Fault Diagnosis for Photovoltaic Arrays Based on Fisher Discrimination Dictionary Learning for Sparse Representation
The nonlinear output characteristics of PV arrays and maximum power point tracking (MPPT) techniques bring more difficulties to fault diagnosis. The fault diagnosis model based on electrical transient time-domain analysis is an effective method for solving the above problems. However, existing studies using transient processes usually train their models by extensive labeled datasets, and some approaches apply normalization methods with environmental condition sensors or reference PV panels. Therefore, Fisher discrimination dictionary learning (FDDL) for sparse representation is explored for diagnosing PV array faults, including line-to-line faults (LLF), open-circuit faults (OCF), and partial shading faults (PSF), with a small labeled dataset, and a dynamic normalization method without additional sensors is proposed to process transient data. Moreover, LLF and PSF that have similar characteristics under low mismatch should be further distinguished. The proposed model is designed with two stages. In the first stage, a multiple classifier trained using small labeled datasets with all fault types is applied to diagnose all kinds of studied PV array faults. Then, a dictionary only for PSF and LLF is learned in the second stage to further identify LLF and PSF. Finally, a 1.8 kW rooftop grid-connected PV system with $6\times3$ PV arrays is applied to validate the performance of the proposed model. The comparison result shows the superiority of the proposed model.
2021
30180-30192
journalArticle
8
IEEE Access
DOI 10.1109/ACCESS.2020.3026452
IEEE Access
ISSN 2169-3536
G. Hassan
K. M. Hosny
R. M. Farouk
A. M. Alzohairy
Feature extraction
Computed tomography
Image retrieval
Image retrieval systems
Laguerre moments
Magnetic resonance imaging
Medical diagnostic imaging
medical imaging
Noise measurement
An Efficient Retrieval System for Biomedical Images Based on Radial Associated Laguerre Moments
The ability of any retrieval system to extract features by using its feature descriptor is the primary criterion to measure its efficiency. In this paper a novel technique for feature extraction of biomedical images is presented. The mooted system uses the Radial Associated Laguerre Moments (RALMs) as a feature descriptor to obtain features from two types of medical images: computer tomography (CT) and magnetic resonance images (MRI). RALMs represent one sort of discrete orthogonal moments. RALMs extract the features from images using orthogonal moments to retrieve images from a database. Our approach is extensively assessed with noise-free and noisy images from three different benchmark databases: Emphysema-CT, NEMA CT, and NEMA MRI. The first two databases are used for CT image retrieval, while the third is for MR image retrieval. The proposed approach was tested against the state-of-the art local feature descriptors: Local Binary Pattern (LBP), and local diagonal extrema pattern (LDEP). It was also evaluated against orthogonal Fourier-Mellin moments (OFMMs) as a global descriptor. The comparison shows a significant improvement in favor of the proposed approach in terms of three different performance metrics: ARP, ARR, and F_score. The proposed approach was also compared against the convolutional neural network (CNN) as a deep learning based method over the NEMA-MRI dataset. The RALMs based approach showed a significant improvement when compared against two state-of-the-art medical image retrieval approaches: Histogram of Compressed Scattering Coefficients (HCSCs) and a local bit-plane decoding-based AlexNet descriptor (LBpDAD), the study has done over the TCIA-CT dataset. The proposed approach was also tested with big well-known dataset from the international skin imaging collaboration (ISIC) 2018.
2020
175669-175687
journalArticle
7
IEEE Access
DOI 10.1109/ACCESS.2019.2911709
IEEE Access
ISSN 2169-3536
C. Lammie
A. Olsen
T. Carrick
M. Rahimi Azghadi
Training
Graphics processing units
weed classification
Internet of Things (IoT)
Acceleration
binarized neural networks (BNNs)
convolutional neural networks (CNNs)
deep neural networks (DNNs)
Engines
Field programmable gate arrays
field programmable gate arrays (FPGAs)
high-level synthesis (HLS)
Machine learning (ML)
Robot kinematics
Low-Power and High-Speed Deep FPGA Inference Engines for Weed Classification at the Edge
Deep neural networks (DNNs) have recently achieved remarkable performance in a myriad of applications, ranging from image recognition to language processing. Training such networks on graphics processing units (GPUs) currently offers unmatched levels of performance; however, GPUs are subject to large-power requirements. With recent advancements in high-level synthesis (HLS) techniques, new methods for accelerating deep networks using field programmable gate arrays (FPGAs) are emerging. FPGA-based DNNs present substantial advantages in energy efficiency over conventional CPU- and GPU-accelerated networks. Using the Intel FPGA software development kit (SDK) for OpenCL development environment, networks described using the high-level OpenCL framework can be accelerated targeting heterogeneous platforms including CPUs, GPUs, and FPGAs. These networks, if properly customized on GPUs and FPGAs, can be ideal candidates for learning and inference in resource-constrained portable devices such as robots and the Internet of Things (IoT) edge devices, where power is limited and performance is critical. Here, we introduce GPU- and FPGA-accelerated deterministically binarized DNNs, tailored toward weed species classification for robotic weed control. Our developed networks are trained and benchmarked using a publicly available weed species dataset, named DeepWeeds, which include close to 18 000 weed images. We demonstrate that our FPGA-accelerated binarized networks significantly outperform their GPU-accelerated counterparts, achieving a>7-fold decrease in power consumption, while performing inference on weed images 2.86 times faster compared to our best performing baseline full-precision GPU implementation. These significant benefits are gained whilst losing only 1.17% of validation accuracy. In this paper, this is a significant step toward enabling deep inference and learning on IoT edge devices, and smart portable machines such as agricultural robots, which is the target application.
2019
51171-51184
journalArticle
10
IEEE Access
DOI 10.1109/ACCESS.2022.3228957
IEEE Access
ISSN 2169-3536
D. Yao
X. Deng
X. Qing
Correlation
Prediction algorithms
Recommender systems
Bipartite graph
Collaborative filtering
Education
Psychology
PTACK
recommendation model
slope one
Teaching quality
teaching style
weighted bipartite graph
A Course Teacher Recommendation Method Based on an Improved Weighted Bipartite Graph and Slope One
The quality of course teaching is directly related to education quality. Many scholars have attempted to identify the associations between course-teaching quality and teachers’ characteristics, such as educational background, degree, professional title, age, teaching age, job burnout, and academic research. However, because these characteristics are mostly evolvable, research findings are inconsistent. Therefore, we attempted to identify the association between teaching styles that reflect teachers’ stable psychological quality, Technological Pedagogical Content Knowledge (TPACK), and teaching quality. To this end, we first collected data from three different disciplines at a university using the constructed teaching quality, TPACK, and course difficulty questionnaires, together with the TSTI scale proposed by Grigorenko and Sternberg. We constructed three matrices with different sparsities as experimental datasets using teachers with the teaching style and PTACK attributes, courses with the course difficulty attribute, and teaching quality. We then constructed a weighted bipartite graph with the teachers and courses in the matrix as nodes and the teaching quality divided by course difficulty as the weights of the edges. We proposed an improved Slope One algorithm based on a weighted bipartite graph to scientifically predict teachers’ teaching quality in untaught courses. Finally, we constructed a TOP-N recommendation model for course teachers that combined teaching style and TPACK features to achieve accurate recommendations for course teachers. The experiments show that our proposed solution is feasible and that the algorithmic model is effective. Therefore, we developed a scientific method to improve the quality of university course teaching.
2022
129763-129780
journalArticle
8
IEEE Access
DOI 10.1109/ACCESS.2019.2961767
IEEE Access
ISSN 2169-3536
Y. Peng
M. Liao
Y. Song
Z. Liu
H. He
H. Deng
Y. Wang
Feature extraction
Deep learning
Training
Computational modeling
Classification algorithms
Convolution
Neural networks
image classification
convolution neural network
feature fusion
Fruit fly images
FB-CNN: Feature Fusion-Based Bilinear CNN for Classification of Fruit Fly Image
The high-resolution devices for image capturing and the high professional requirement for users, are very complex to extract features of the fruit fly image for classification. Therefore, a bilinear CNN model based on the mid-level and high-level feature fusion (FB-CNN) is proposed for classifying the fruit fly image. At the first step, the images of fruit fly are blurred by the Gaussian algorithm, and then the features of the fruit fly images are extracted automatically by using CNN. Afterward, the mid- and high-level features are selected to represent the local and global features, respectively. Then, they are jointly represented. When finished, the FB-CNN model was constructed to complete the task of image classification of the fruit fly. Finally, experiments data show that the FB-CNN model can effectively classify four kinds of fruit fly images. The accuracy, precision, recall, and F1 score in testing dataset are 95.00%, respectively.
2020
3987-3995
journalArticle
P. Zhu
L. Wen
D. Du
X. Bian
H. Fan
Q. Hu
H. Ling
Computer vision
Object detection
Benchmark testing
benchmark
Conferences
Drone
Drones
image object detection
multi-object tracking
single object tracking
Surveillance
Target tracking
video object detection
Detection and Tracking Meet Drones Challenge
Drones, or general UAVs, equipped with cameras have been fast deployed with a wide range of applications, including agriculture, aerial photography, and surveillance. Consequently, automatic understanding of visual data collected from drones becomes highly demanding, bringing computer vision and drones more and more closely. To promote and track the developments of object detection and tracking algorithms, we have organized three challenge workshops in conjunction with ECCV 2018, ICCV 2019 and ECCV 2020, attracting more than 100 teams around the world. We provide a large-scale drone captured dataset, VisDrone, which includes four tracks, i.e., (1) image object detection, (2) video object detection, (3) single object tracking, and (4) multi-object tracking. In this paper, we first present a thorough review of object detection and tracking datasets and benchmarks, and discuss the challenges of collecting large-scale drone-based object detection and tracking datasets with fully manual annotations. After that, we describe our VisDrone dataset, which is captured over various urban/suburban areas of 14 different cities across China from North to South. Being the largest such dataset ever published, VisDrone enables extensive evaluation and investigation of visual analysis algorithms for the drone platform. We provide a detailed analysis of the current state of the field of large-scale object detection and tracking on drones, and conclude the challenge as well as propose future directions. We expect the benchmark largely boost the research and development in video analysis on drone platforms. All the datasets and experimental results can be downloaded from https://github.com/VisDrone/VisDrone-Dataset.
1 Nov. 2022
7380-7399
44
IEEE Transactions on Pattern Analysis and Machine Intelligence
DOI 10.1109/TPAMI.2021.3119563
11
IEEE Transactions on Pattern Analysis and Machine Intelligence
ISSN 1939-3539
journalArticle
9
IEEE Access
DOI 10.1109/ACCESS.2021.3086269
IEEE Access
ISSN 2169-3536
A. Bakhshipour
Feature extraction
Image color analysis
Training
Agriculture
Shape
feature selection
Classification algorithms
image processing
precision agriculture
Boosting
Ensemble learning
plant identification
Cascading Feature Filtering and Boosting Algorithm for Plant Type Classification Based on Image Features
Crop and weeds identification is of important steps towards the development of efficient automotive weed control systems. The higher the accuracy of plant detection and classification, the higher the performance of the weeding machine. In this study, the capability of two popular boosting methods including Adaboost.M1 and LogitBoost algorithms was evaluated to enhance the plant classification performance of four classifiers, namely Multi-Layer Perceptron (MLP), k-Nearest Neighbors (kNN), Random Forest (RF), and Support Vector Machine (SVM). Four feature filtering techniques including Correlation-based Feature Selection (CFS), Information Gain (IG), Gain Ratio (GR), and OneR were applied to the image-extracted features and 10 of the most significant features were selected and fed into single and boosted classifiers. The RF model trained by IG selected features (IG-RF) was the most appropriate classifier among the evaluated models whether in single or boosted modes. It was also found that boosting of IG-RF by using Adaboost.M1 and LogitBoost algorithms improved the classification accuracy. Regarding the performance values, the LogitBoost-IG-RF structure, which provided a classification accuracy of 99.58%, a kappa ( k) of 0.9948, and a Root Mean Squared Error (RMSE) of 0.0688 on training dataset, was selected as the most appropriate classifier for plant discrimination in peanut fields. The accuracy, k, and RMSE criteria of this combination on test dataset were 95.00%, 0.9375, and 0.1591, respectively. It was concluded that combination of boosting algorithms and feature selection methods can promote plant type discrimination accuracy, which is a crucial factor in the development of precision weed control systems.
2021
82021-82030
journalArticle
7
IEEE Access
DOI 10.1109/ACCESS.2019.2908040
IEEE Access
ISSN 2169-3536
M. A. Khan
M. I. U. Lali
M. Sharif
K. Javed
K. Aurangzeb
S. I. Haider
A. S. Altamrah
T. Akram
Feature extraction
Image color analysis
Diseases
Support vector machines
Image segmentation
Genetic algorithms
Lesions
feature extraction
optimal features
recognition
Symptoms enhancement
symptoms segmentation
An Optimized Method for Segmentation and Classification of Apple Diseases Based on Strong Correlation and Genetic Algorithm Based Feature Selection
Agriculture is a major part of the world economy as it provides food safety. However, in recent years, it has been noted that plants are extensively infected by different diseases. This causes enormous economic losses in agriculture industry around the world. The manual inspection of fruit diseases is a difficult process which can be minimized by using automated methods for detection of plant diseases at the earlier stage. In this paper, a new method is implemented for apple diseases identification and recognition. Three pipeline procedures are followed by preprocessing, spot segmentation, and features extraction, and classification. In the first step, the apple leaf spots are enhanced by a hybrid method which is the conjunction of 3D box filtering, de-correlation, 3D-Gaussian filter, and 3D-median filter. After that, the lesion spots are segmented by the strong correlation-based method and optimized their results by fusion of expectation maximization (EM) segmentation. Finally, the color, color histogram, and local binary pattern (LBP) features are fused by comparison-based parallel fusion. The extracted features are optimized by genetic algorithm and classified by One-vs-All M-SVM. The experimental results are performed on plant village dataset. The proposed methodology is tested for four types of apple disease classes including healthy leaves, Blackrot, Rust, and Scab. The classification accuracy shows the improvement of our method on selected apple diseases. Moreover, the good preprocessing step always produced prominent features which later achieved significant classification accuracy.
2019
46261-46277
journalArticle
4
IEEE Access
DOI 10.1109/ACCESS.2016.2592418
IEEE Access
ISSN 2169-3536
S. L. Rovere
M. J. North
G. P. Podestá
F. E. Bert
Agriculture
Biological system modeling
Software
Adaptation models
agent-based modeling
Complex adaptive systems
coupled human and natural systems
model design and implementation
Object oriented modeling
software engineering
Software engineering
Unified modeling language
Practical Points for the Software Development of an Agent-Based Model of a Coupled Human-Natural System
Modeling complex natural and human systems to support policy or management decision making is becoming increasingly common. The resulting models are often designed and implemented by researchers or domain experts with limited software engineering expertise. To help this important audience, we present our experience and share lessons learned from the design and implementation of an agent-based model of agricultural production systems in the Argentine Pampas, emphasizing the software engineering perspective. We discuss the model's design including the model classes; the activity diagram, and data flow; the package and folder layout; the use of design patterns; performance optimization; initialization approaches; the analysis of results; and model measurement, validation, and verification.
2016
4282-4298
journalArticle
70
IEEE Transactions on Instrumentation and Measurement
DOI 10.1109/TIM.2021.3111994
IEEE Transactions on Instrumentation and Measurement
ISSN 1557-9662
S. Azimi
R. Wadhawan
T. K. Gandhi
Convolutional neural networks
Crops
Computer vision
Visualization
Pipelines
long short-term memory (LSTM)
convolutional neural network (CNN)
deep learning (DL)
Long short term memory
monitoring
neural network
plant phenotyping
spatiotemporal analysis
Stress
water stress
Intelligent Monitoring of Stress Induced by Water Deficiency in Plants Using Deep Learning
In the recent decade, high-throughput plant phenotyping techniques, which combine noninvasive image analysis and machine learning, have been successfully applied to identify and quantify plant health and diseases. However, these techniques usually do not consider the progressive nature of plant stress and often require images showing severe signs of stress to ensure high confidence detection, thereby reducing the feasibility for early detection and recovery of plants under stress. To overcome the problem mentioned above, we propose a deep learning pipeline for the temporal analysis of the visual changes induced in the plant due to stress and apply it to the specific water stress identification case in Chickpea plant shoot images. For this, we have considered an image dataset of two chickpea varieties JG-62 and Pusa-372, under three water stress conditions: control, young seedling, and before flowering, captured over five months. We have employed a variant of convolutional neural network-long short-term memory (CNN-LSTM) network to learn spatiotemporal patterns from the chickpea plant dataset and use them for water stress classification. Our model has achieved ceiling level classification performance of 98.52% on JG-62 and 97.78% on Pusa-372 chickpea plant data and has outperformed the best reported time-invariant technique by at least 14% for both JG-62 and Pusa-372 species to the best of our knowledge. Furthermore, our CNN-LSTM model has demonstrated robustness to noisy input, with a less than 2.5% dip in average model accuracy and a small standard deviation about the mean for both species. Finally, we have performed an ablation study to analyze the performance of the CNN-LSTM model by decreasing the number of temporal session data used for training.
2021
1-13
journalArticle
8
IEEE Access
DOI 10.1109/ACCESS.2020.2998079
IEEE Access
ISSN 2169-3536
W. Khan
N. Minallah
I. U. Khan
Z. Wadud
M. Zeeshan
S. Yousaf
A. B. Qazi
Estimation
Monitoring
remote sensing
Agriculture
Remote sensing
Vegetation mapping
Satellites
artificial neural networks
Geosurvey
illicit tobacco
layer stacking
NDI45
NDVI
Pakistan tobacco board
producer accuracy
Sentinel 2
Stacking
temporal stacking
user accuracy
On the Performance of Temporal Stacking and Vegetation Indices for Detection and Estimation of Tobacco Crop
Machine learning in association with remote sensing has assisted agricultural specialists in monitoring, classification and yield estimation of crops. Tobacco is a major taxable crop of Pakistan, however the existing traditional methods for its monitoring and yield estimation are not only expensive and time consuming but also have limitations in terms of accuracy of collected data by a large number of diverse human surveyors. Due to the existence of such loopholes in the employed mechanism for tobacco crop monitoring and yield estimation, its illicit growth and distribution is on the rise. In this paper we have established a sophisticated machine learning mechanism for tobacco crop estimation using temporally stacked sentinel-2 satellite's data of Pakistan. Instead of the conventional approach of using single remotely sensed imagery for the target crop classification, we propose a machine learning based classification algorithm while keeping in view the phonological cycle of the target tobacco crop. Using the proposed mechanism, the temporal variations within the tobacco crop and its association with the variations of other vegetation is considered to improve the classification performance of the employed machine learning algorithm. Furthermore, the impact of stacking the vegetation indices derived from near infrared and vegetation red edge bands of sentinel-2 with the original sentinel-2 datasets, including Normalized Difference Vegetation Index (NDVI) and Normalized Difference Index 45 (NDI45), on the classification performance of the machine learning mechanism is investigated. Ground Truth data for training of our Artificial Neural Networks classifier, was obtained using indigenously developed survey application “GEOSurvey”. Experiments were conducted using our proposed mechanism while considering various input data setups - including single date imagery, temporally stacked datasets based on phonological cycle of tobacco crop and different combinations of NDVI and NDI45 stacking. Our proposed experimental setup consisting of temporally stacked imagery along with NDVI stacking results in the best classification performance of 95.81% with reference to the single date imagery stacked with NDVI and NDI45, with performance gain of 07.32%.
2020
103020-103033
journalArticle
15
IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
DOI 10.1109/JSTARS.2022.3144339
IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
ISSN 2151-1535
W. Chen
S. Ouyang
J. Yang
X. Li
G. Zhou
L. Wang
Feature extraction
Generative adversarial networks
Training
Hyperspectral imaging
Land surface
land cover classification
Roads
Attention mechanism
Gaofen-5 (GF-5)
generative adversarial network
hyperspectral remote sensing
Image classification
JAGAN: A Framework for Complex Land Cover Classification Using Gaofen-5 AHSI Images
Owing to their powerful feature extraction capabilities, deep learning-based methods have achieved significant progress in hyperspectral remote sensing classification. However, several issues still exist in these methods, including a lack of hyperspectral datasets for specific complicated scenarios and the need to improve the classification accuracy of land cover with limited samples. Thus, to highlight and distinguish effective features, we propose a hyperspectral classification framework based on a joint channel-space attention mechanism and generative adversarial network (JAGAN). To relearn feature-based weights, a higher priority was assigned to important features, which was developed by integrating a two-joint channel-space attention model to obtain the most valuable feature via the attention weight map. Additionally, two classifiers were designed in JAGAN: sigmoid was used to determine whether the input data were real or fake samples produced by the generator, while Softmax was adopted as a land cover classifier to yield the prediction type labels of the input samples. To test the classification performance of the JAGAN model, we used a self-constructed complex land cover dataset based on GaoFen-5 AHSI images, which consists of mixed landscapes of mining and agricultural areas from the urban-rural fringe. Compared with other methods, the proposed model achieved the highest overall classification accuracy of 86.09%, the highest kappa amount of 79.41%, the highest F1 score of 85.86%, and the highest average accuracy of 82.30%, indicating the JAGAN can effectively improve the classification accuracy for limited samples in complex regional environments using GF-5 AHSI images.
2022
1591-1603
journalArticle
115
Computers and Electronics in Agriculture
DOI 10.1016/j.compag.2015.05.011
Fountas
S.
Carli
G.
Sørensen
C.G.
Tsiropoulos
Z.
Cavalaris
C.
Vatsanidou
A.
Liakos
B.
Canavari
M.
Wiebensohn
J.
Tisserye
B.
Farm management information systems: Current situation and future perspectives
2015
Scopus
https://www.scopus.com/inward/record.uri?eid=2-s2.0-84930193398&doi=10.1016%2fj.compag.2015.05.011&partnerID=40&md5=ffa915e779dd5eb655b26f3d9d8cc4ca
40-50
journalArticle
4
Global Ecology and Conservation
DOI 10.1016/j.gecco.2015.10.004
Ridding
L.E.
Redhead
J.W.
Pywell
R.F.
Fate of semi-natural grassland in England between 1960 and 2013: A test of national conservation policy
2015
Scopus
https://www.scopus.com/inward/record.uri?eid=2-s2.0-84945122054&doi=10.1016%2fj.gecco.2015.10.004&partnerID=40&md5=82ce83d29e2d37166c1cd1014bd1578f
516-525
journalArticle
62
Applied Geography
DOI 10.1016/j.apgeog.2015.05.010
Haney
N.
Cohen
S.
Predicting 21st century global agricultural land use with a spatially and temporally explicit regression-based model
2015
Scopus
https://www.scopus.com/inward/record.uri?eid=2-s2.0-84930643846&doi=10.1016%2fj.apgeog.2015.05.010&partnerID=40&md5=8bf37d937d7f8dea85ae06a2c896e4f5
366-376
journalArticle
95
Canadian Journal of Soil Science
DOI 10.4141/CJSS-2014-017
3
Du
Y.
Huffman
T.
Daneshfar
B.
Green
M.
Feng
F.
Liu
J.
Liu
T.
Liu
H.
Improving the spatial resolution and ecostratification of crop yield estimates in Canada
2015
Amélioration de la résolution spatiale et de l’écostratification des estimations du rendement agricole au Canada
Scopus
https://www.scopus.com/inward/record.uri?eid=2-s2.0-84938524736&doi=10.4141%2fCJSS-2014-017&partnerID=40&md5=54aea19d04af1966585f566152541da4
287-297
journalArticle
166
Remote Sensing of Environment
DOI 10.1016/j.rse.2015.06.001
Duveiller
G.
Lopez-Lozano
R.
Cescatti
A.
Exploiting the multi-angularity of the MODIS temporal signal to identify spatially homogeneous vegetation cover: A demonstration for agricultural monitoring applications
2015
Scopus
https://www.scopus.com/inward/record.uri?eid=2-s2.0-84931271950&doi=10.1016%2fj.rse.2015.06.001&partnerID=40&md5=a59cfbbf91af612452dade3a26f14e0d
61-77
journalArticle
117
Computers and Electronics in Agriculture
DOI 10.1016/j.compag.2015.07.009
Zhong
B.
Yang
F.
Chen
Y.-L.
Information empowers vegetable supply chain: A study of information needs and sharing strategies among farmers and vendors
2015
Scopus
https://www.scopus.com/inward/record.uri?eid=2-s2.0-84952061580&doi=10.1016%2fj.compag.2015.07.009&partnerID=40&md5=95781f8b19c6624ee4c43c6538a7dd87
81-90
journalArticle
30
Ecological Research
DOI 10.1007/s11284-015-1290-2
5
Osawa
T.
Kadoya
T.
Kohyama
K.
5- and 10-km mesh datasets of agricultural land use based on governmental statistics for 1970–2005
2015
Scopus
https://www.scopus.com/inward/record.uri?eid=2-s2.0-84940449566&doi=10.1007%2fs11284-015-1290-2&partnerID=40&md5=8ab422f8431e35b7fee828e4fde31949
757
journalArticle
81
Biomass and Bioenergy
DOI 10.1016/j.biombioe.2015.07.022
Warren Raffa
D.
Bogdanski
A.
Tittonell
P.
How does crop residue removal affect soil organic carbon and yield? A hierarchical analysis of management and environmental factors
2015
Scopus
https://www.scopus.com/inward/record.uri?eid=2-s2.0-84938217338&doi=10.1016%2fj.biombioe.2015.07.022&partnerID=40&md5=a54ad4846b93c84d46220f183d801af5
345-355
journalArticle
118
Computers and Electronics in Agriculture
DOI 10.1016/j.compag.2015.09.016
Zolekar
R.B.
Bhagat
V.S.
Multi-criteria land suitability analysis for agriculture in hilly zone: Remote sensing and GIS approach
2015
Scopus
https://www.scopus.com/inward/record.uri?eid=2-s2.0-84942566740&doi=10.1016%2fj.compag.2015.09.016&partnerID=40&md5=12dff2a7f4488b7e522a371cec8a4d7f
300-321
journalArticle
2
Information Processing in Agriculture
DOI 10.1016/j.inpa.2015.10.002
3-4
L'Abate
G.
Caracciolo
C.
Pesce
V.
Geser
G.
Protonotarios
V.
Costantini
E.A.C.
Exposing vocabularies for soil as Linked Open Data
2015
Scopus
https://www.scopus.com/inward/record.uri?eid=2-s2.0-85000415404&doi=10.1016%2fj.inpa.2015.10.002&partnerID=40&md5=60d135a6ceafdba43f2e09d2a7c03dee
208-216
journalArticle
2
Information Processing in Agriculture
DOI 10.1016/j.inpa.2015.10.001
3-4
Bartzas
G.
Zaharaki
D.
Komnitsas
K.
Life cycle assessment of open field and greenhouse cultivation of lettuce and barley
2015
Scopus
https://www.scopus.com/inward/record.uri?eid=2-s2.0-85016995208&doi=10.1016%2fj.inpa.2015.10.001&partnerID=40&md5=a2673e86c49d792dd8294f23c5a83cb8
191-207
journalArticle
140
Biosystems Engineering
DOI 10.1016/j.biosystemseng.2015.08.006
Kässi
P.
Känkänen
H.
Niskanen
O.
Lehtonen
H.
Höglind
M.
Farm level approach to manage grass yield variation under climate change in Finland and north-western Russia
2015
Scopus
https://www.scopus.com/inward/record.uri?eid=2-s2.0-84943571473&doi=10.1016%2fj.biosystemseng.2015.08.006&partnerID=40&md5=cc01263c03242a41dd79e0bfc8a0c211
11-22
journalArticle
9
Ecohydrology
DOI 10.1002/eco.1618
1
Christensen
J.
Nash
M.
Chaloud
D.
Pitchford
A.
Spatial distributions of small water body types in modified landscapes: Lessons from Indiana, USA
2016
Scopus
https://www.scopus.com/inward/record.uri?eid=2-s2.0-84955713777&doi=10.1002%2feco.1618&partnerID=40&md5=4be9ca394b5104f9aff9d1afbe6cbcd0
122-137
journalArticle
54
Soil Research
DOI 10.1071/SR14245
1
Basak
N.
Datta
A.
Mitran
T.
Roy
S.S.
Saha
B.
Biswas
S.
Mandal
B.
Assessing soil-quality indices for subtropical rice-based cropping systems in India
2016
Scopus
https://www.scopus.com/inward/record.uri?eid=2-s2.0-84957683522&doi=10.1071%2fSR14245&partnerID=40&md5=5a8fc02721deae8d018b14a2c3d4822b
20-29
journalArticle
54
Soil Research
DOI 10.1071/SR15046
2
López De Herrera
J.
Tejedor
T.H.
Saa-Requejo
A.
Tarquis
A.M.
Effects of tillage on variability in soil penetration resistance in an olive orchard
2016
Scopus
https://www.scopus.com/inward/record.uri?eid=2-s2.0-84961878255&doi=10.1071%2fSR15046&partnerID=40&md5=2adff881b0edc52eee4233d54e5b46d1
134-143
journalArticle
59
Transactions of the ASABE
DOI 10.13031/trans.59.11208
2
Lee
D.-H.
Choi
C.-H.
Chung
S.-O.
Kim
Y.-J.
Lee
K.-H.
Shin
B.-S.
Development of a plow tillage cycle for an agricultural tractor
2016
Scopus
https://www.scopus.com/inward/record.uri?eid=2-s2.0-84964714782&doi=10.13031%2ftrans.59.11208&partnerID=40&md5=e55e253db4d6713f2846827a1d6e48e2
445-454
journalArticle
59
Transactions of the ASABE
DOI 10.13031/trans.59.11489
3
Sharma
V.
Irmak
S.
Kilic
A.
Sharma
V.
Gilley
J.E.
Meyer
G.E.
Knezevic
S.Z.
Marx
D.
Quantification and mapping of surface residue cover for maize and soybean fields in south central Nebraska
2016
Scopus
https://www.scopus.com/inward/record.uri?eid=2-s2.0-84975747917&doi=10.13031%2ftrans.59.11489&partnerID=40&md5=c696d49597a2e4948e717c7a6ae1351c
925-939
journalArticle
59
Transactions of the ASABE
DOI 10.13031/trans.59.11547
4
Antille
D.L.
Huth
N.I.
Eberhard
J.
Marinoni
O.
Cocks
B.
Poulton
P.L.
Macdonald
B.C.T.
Schmidt
E.J.
The effects of coal seam gas infrastructure development on arable land in Southern Queensland, Australia: Field investigations and modeling
2016
Scopus
https://www.scopus.com/inward/record.uri?eid=2-s2.0-84983740605&doi=10.13031%2ftrans.59.11547&partnerID=40&md5=ba0cfc4652ff46ab914142c4b6baeb56
879-901
journalArticle
8
Agris On-line Papers in Economics and Informatics
DOI 10.7160/aol.2016.080306
3
Jarolímek
J.
Martinec
R.
Analysis of open data availability in Czech republic agrarian sector
2016
Scopus
https://www.scopus.com/inward/record.uri?eid=2-s2.0-84992111867&doi=10.7160%2faol.2016.080306&partnerID=40&md5=1cf41ff4b8185fc5bce9b1669b63c6ed
57-67
journalArticle
59
Transactions of the ASABE
DOI 10.13031/trans.59.11584
6
Kim
S.H.
Myoung
B.
Stack
D.H.
Kim
J.
Kafatos
M.C.
Sensitivity of maize yield potential to regional climate in the South Western U.S.
2016
Scopus
https://www.scopus.com/inward/record.uri?eid=2-s2.0-85007373687&doi=10.13031%2ftrans.59.11584&partnerID=40&md5=900761b26d3a768f2ea75f671a06856e
1745-1757
journalArticle
155
Soil and Tillage Research
DOI 10.1016/j.still.2015.08.010
Rojas
J.M.
Prause
J.
Sanzano
G.A.
Arce
O.E.A.
Sánchez
M.C.
Soil quality indicators selection by mixed models and multivariate techniques in deforested areas for agricultural use in NW of Chaco, Argentina
2016
Scopus
https://www.scopus.com/inward/record.uri?eid=2-s2.0-84940950924&doi=10.1016%2fj.still.2015.08.010&partnerID=40&md5=0f8bdd5729758a97612535b3b6cac56e
250-262
journalArticle
15
Vadose Zone Journal
DOI 10.2136/vzj2015.07.0107
1
Hohenbrink
T.L.
Lischeid
G.
Schindler
U.
Hufnagel
J.
Disentangling the effects of land management and soil heterogeneity on soil moisture dynamics
2016
Scopus
https://www.scopus.com/inward/record.uri?eid=2-s2.0-84961318419&doi=10.2136%2fvzj2015.07.0107&partnerID=40&md5=60ebd946371c85c445b889c8bfe2571b
journalArticle
61
Ecological Indicators
DOI 10.1016/j.ecolind.2015.09.032
Weissteiner
C.J.
García-Feced
C.
Paracchini
M.L.
A new view on EU agricultural landscapes: Quantifying patchiness to assess farmland heterogeneity
2016
Scopus
https://www.scopus.com/inward/record.uri?eid=2-s2.0-84949681233&doi=10.1016%2fj.ecolind.2015.09.032&partnerID=40&md5=4961fd7dfeb462cdd2e6863e667921ca
317-327
journalArticle
124
Plant Cell, Tissue and Organ Culture
DOI 10.1007/s11240-015-0894-0
2
Elhiti
M.
Wang
H.
Austin
R.S.
Chen
B.
Brown
D.
Wang
A.
Generation of chemically induced mutations using in vitro propagated shoot tip tissues for genetic improvement of fruit trees
2016
Scopus
https://www.scopus.com/inward/record.uri?eid=2-s2.0-84955337197&doi=10.1007%2fs11240-015-0894-0&partnerID=40&md5=06d08fc45c2198bba4be10087e9eca96
447-452
journalArticle
75
Environmental Earth Sciences
DOI 10.1007/s12665-015-5142-8
4
Barranquero
R.S.
Varni
M.R.
Pardo
R.
Vega
M.
Zabala
M.E.
de Galarreta
V.A.R.
Joint interpretation of the hydrochemistry of two neighbouring basins by N-way multivariate methods
2016
Scopus
https://www.scopus.com/inward/record.uri?eid=2-s2.0-84958060031&doi=10.1007%2fs12665-015-5142-8&partnerID=40&md5=8a1a76a5fd4f11dbead691b61b97dd11
1-14
journalArticle
61
Journal of the Faculty of Agriculture, Kyushu University
1
Wang
X.
Han
G.
Maeda
K.
Zhou
Y.
China's agricultural trade costs: Measurement and determinants
2016
Scopus
https://www.scopus.com/inward/record.uri?eid=2-s2.0-84978105458&partnerID=40&md5=4d2d816874119c7c816698367ad17dde
215-223
journalArticle
27
Land Degradation and Development
DOI 10.1002/ldr.2414
3
Galdino
S.
Sano
E.E.
Andrade
R.G.
Grego
C.R.
Nogueira
S.F.
Bragantini
C.
Flosi
A.H.G.
Large-scale Modeling of Soil Erosion with RUSLE for Conservationist Planning of Degraded Cultivated Brazilian Pastures
2016
Scopus
https://www.scopus.com/inward/record.uri?eid=2-s2.0-84939234927&doi=10.1002%2fldr.2414&partnerID=40&md5=12413ecd818d4fd18662ca23b2a48502
773-784
journalArticle
267
Geoderma
DOI 10.1016/j.geoderma.2016.01.004
Cherubin
M.R.
Karlen
D.L.
Franco
A.L.C.
Tormena
C.A.
Cerri
C.E.P.
Davies
C.A.
Cerri
C.C.
Soil physical quality response to sugarcane expansion in Brazil
2016
Scopus
https://www.scopus.com/inward/record.uri?eid=2-s2.0-84954306524&doi=10.1016%2fj.geoderma.2016.01.004&partnerID=40&md5=e575be129f0a9c6cd011439836f84d7c
156-168
journalArticle
268
Geoderma
DOI 10.1016/j.geoderma.2016.01.010
Ludwig
B.
Linsler
D.
Höper
H.
Schmidt
H.
Piepho
H.-P.
Vohland
M.
Pitfalls in the use of middle-infrared spectroscopy: Representativeness and ranking criteria for the estimation of soil properties
2016
Scopus
https://www.scopus.com/inward/record.uri?eid=2-s2.0-84956717741&doi=10.1016%2fj.geoderma.2016.01.010&partnerID=40&md5=f0046d6f061c782715d9a6553826a66e
165-175
journalArticle
64
Ecological Indicators
DOI 10.1016/j.ecolind.2015.12.004
Horrigue
W.
Dequiedt
S.
Chemidlin Prévost-Bouré
N.
Jolivet
C.
Saby
N.P.A.
Arrouays
D.
Bispo
A.
Maron
P.-A.
Ranjard
L.
Predictive model of soil molecular microbial biomass
2016
Scopus
https://www.scopus.com/inward/record.uri?eid=2-s2.0-84954348290&doi=10.1016%2fj.ecolind.2015.12.004&partnerID=40&md5=e9847951c09dc51663eba95ffa65c1da
203-211
journalArticle
171
Agricultural Water Management
DOI 10.1016/j.agwat.2016.03.014
Ren
X.
Sun
D.
Wang
Q.
Modeling the effects of plant density on maize productivity and water balance in the Loess Plateau of China
2016
Scopus
https://www.scopus.com/inward/record.uri?eid=2-s2.0-84962310241&doi=10.1016%2fj.agwat.2016.03.014&partnerID=40&md5=7e577b506615ecc305c539f186ffae29
40-48
journalArticle
124
Computers and Electronics in Agriculture
DOI 10.1016/j.compag.2016.04.013
Montgomery
B.
Dragićević
S.
Dujmović
J.
Schmidt
M.
A GIS-based Logic Scoring of Preference method for evaluation of land capability and suitability for agriculture
2016
Scopus
https://www.scopus.com/inward/record.uri?eid=2-s2.0-84964895585&doi=10.1016%2fj.compag.2016.04.013&partnerID=40&md5=b281f9bf8969c06fd5e717381f48c269
340-353
journalArticle
180
Remote Sensing of Environment
DOI 10.1016/j.rse.2016.02.046
Escorihuela
M.J.
Quintana-Seguí
P.
Comparison of remote sensing and simulated soil moisture datasets in Mediterranean landscapes
2016
Scopus
https://www.scopus.com/inward/record.uri?eid=2-s2.0-84959549992&doi=10.1016%2fj.rse.2016.02.046&partnerID=40&md5=404f3d38d0b036fbdd32a022b94e5485
99-114
journalArticle
125
Computers and Electronics in Agriculture
DOI 10.1016/j.compag.2016.04.011
Kruize
J.W.
Wolfert
J.
Scholten
H.
Verdouw
C.N.
Kassahun
A.
Beulens
A.J.M.
A reference architecture for Farm Software Ecosystems
2016
Scopus
https://www.scopus.com/inward/record.uri?eid=2-s2.0-84964813430&doi=10.1016%2fj.compag.2016.04.011&partnerID=40&md5=0f889fd7cc953861a1bebc0961efc483
12-28
journalArticle
275
Geoderma
DOI 10.1016/j.geoderma.2016.04.012
Aldana-Jague
E.
Heckrath
G.
Macdonald
A.
van Wesemael
B.
Van Oost
K.
UAS-based soil carbon mapping using VIS-NIR (480-1000 nm) multi-spectral imaging: Potential and limitations
2016
Scopus
https://www.scopus.com/inward/record.uri?eid=2-s2.0-84966293673&doi=10.1016%2fj.geoderma.2016.04.012&partnerID=40&md5=1be2b5bbb4a38c97912b89e5b4169a47
55-66
journalArticle
126
Computers and Electronics in Agriculture
DOI 10.1016/j.compag.2016.05.009
Liu
Z.
Cheng
F.
Zhang
W.
A novel segmentation algorithm for clustered flexional agricultural products based on image analysis
2016
Scopus
https://www.scopus.com/inward/record.uri?eid=2-s2.0-84969932751&doi=10.1016%2fj.compag.2016.05.009&partnerID=40&md5=1dfaa09b03010b95b8e155e5709ac856
44-54
journalArticle
75
Environmental Earth Sciences
DOI 10.1007/s12665-016-5927-4
15
Satir
O.
Erdogan
M.A.
Monitoring the land use/cover changes and habitat quality using Landsat dataset and landscape metrics under the immigration effect in subalpine eastern Turkey
2016
Scopus
https://www.scopus.com/inward/record.uri?eid=2-s2.0-84979584501&doi=10.1007%2fs12665-016-5927-4&partnerID=40&md5=7b933f7755c7479bf01aeb9509d98fdb
journalArticle
127
Computers and Electronics in Agriculture
DOI 10.1016/j.compag.2016.07.006
Li
Y.
Cao
Z.
Lu
H.
Xiao
Y.
Zhu
Y.
Cremers
A.B.
In-field cotton detection via region-based semantic image segmentation
2016
Scopus
https://www.scopus.com/inward/record.uri?eid=2-s2.0-84978239436&doi=10.1016%2fj.compag.2016.07.006&partnerID=40&md5=680249a993ee4c298c63086049b2bf63
475-486
journalArticle
127
Computers and Electronics in Agriculture
DOI 10.1016/j.compag.2016.07.028
Ge
Y.
Bai
G.
Stoerger
V.
Schnable
J.C.
Temporal dynamics of maize plant growth, water use, and leaf water content using automated high throughput RGB and hyperspectral imaging
2016
Scopus
https://www.scopus.com/inward/record.uri?eid=2-s2.0-84979645273&doi=10.1016%2fj.compag.2016.07.028&partnerID=40&md5=3d4b821f0a06d5ce09f8cdee6fba410e
625-632
journalArticle
27
Land Degradation and Development
DOI 10.1002/ldr.2476
7
Russell
J.M.
Ward
D.
Historical Land-use and Vegetation Change in Northern Kwazulu-Natal, South Africa
2016
Scopus
https://www.scopus.com/inward/record.uri?eid=2-s2.0-84957639128&doi=10.1002%2fldr.2476&partnerID=40&md5=ef8a643384ef3e6366ee968049b6a370
1691-1699
journalArticle
69
Ecological Indicators
DOI 10.1016/j.ecolind.2016.04.013
Yong
D.L.
Barton
P.S.
Okada
S.
Crane
M.
Lindenmayer
D.B.
Birds as surrogates for mammals and reptiles: Are patterns of cross-taxonomic associations stable over time in a human-modified landscape?
2016
Scopus
https://www.scopus.com/inward/record.uri?eid=2-s2.0-84964265496&doi=10.1016%2fj.ecolind.2016.04.013&partnerID=40&md5=412760326b5775413cb9b1b5fc027cd3
152-164
journalArticle
176
Agricultural Water Management
DOI 10.1016/j.agwat.2016.05.013
Kumar
S.
Ramilan
T.
Ramarao
C.A.
Rao
C.S.
Whitbread
A.
Farm level rainwater harvesting across different agro climatic regions of India: Assessing performance and its determinants
2016
Scopus
https://www.scopus.com/inward/record.uri?eid=2-s2.0-84969750110&doi=10.1016%2fj.agwat.2016.05.013&partnerID=40&md5=7683da2ce4037c52b4d29c925e5899ad
55-66
journalArticle
128
Computers and Electronics in Agriculture
DOI 10.1016/j.compag.2016.09.001
Marx
S.E.
Luck
J.D.
Pitla
S.K.
Hoy
R.M.
Comparing various hardware/software solutions and conversion methods for Controller Area Network (CAN) bus data collection
2016
Scopus
https://www.scopus.com/inward/record.uri?eid=2-s2.0-84989867319&doi=10.1016%2fj.compag.2016.09.001&partnerID=40&md5=3d04dbb7ccc7e8c2e09323f56d731d3e
141-148
journalArticle
70
Ecological Indicators
DOI 10.1016/j.ecolind.2016.03.055
Naura
M.
Hornby
D.D.
Collins
A.L.
Sear
D.A.
Hill
C.
Jones
J.I.
Naden
P.S.
Mapping the combined risk of agricultural fine sediment input and accumulation for riverine ecosystems across England and Wales
2016
Scopus
https://www.scopus.com/inward/record.uri?eid=2-s2.0-84976412624&doi=10.1016%2fj.ecolind.2016.03.055&partnerID=40&md5=0b68109d1ce16e606116d9c688f4dec2
209-221
journalArticle
76
Applied Geography
DOI 10.1016/j.apgeog.2016.09.018
Perroy
R.L.
Melrose
J.
Cares
S.
The evolving agricultural landscape of post-plantation Hawai‘i
2016
Scopus
https://www.scopus.com/inward/record.uri?eid=2-s2.0-84988694133&doi=10.1016%2fj.apgeog.2016.09.018&partnerID=40&md5=89a3d298af58b6df6d907c0b7cafd1d1
154-162
journalArticle
187
Remote Sensing of Environment
DOI 10.1016/j.rse.2016.10.007
Erten
E.
Lopez-Sanchez
J.M.
Yuzugullu
O.
Hajnsek
I.
Retrieval of agricultural crop height from space: A comparison of SAR techniques
2016
Scopus
https://www.scopus.com/inward/record.uri?eid=2-s2.0-84991593765&doi=10.1016%2fj.rse.2016.10.007&partnerID=40&md5=6ad79176d2acb211d31da68c95f1ddf0
130-144
journalArticle
15
Paddy and Water Environment
DOI 10.1007/s10333-016-0530-6
1
Ebers
A.
Nguyen
T.T.
Grote
U.
Production efficiency of rice farms in Thailand and Cambodia: a comparative analysis of Ubon Ratchathani and Stung Treng provinces
2017
Scopus
https://www.scopus.com/inward/record.uri?eid=2-s2.0-84975257916&doi=10.1007%2fs10333-016-0530-6&partnerID=40&md5=82770b62bb006c76944e6d53fb091b23
79-92
journalArticle
165
Soil and Tillage Research
DOI 10.1016/j.still.2016.07.017
Biddoccu
M.
Ferraris
S.
Pitacco
A.
Cavallo
E.
Temporal variability of soil management effects on soil hydrological properties, runoff and erosion at the field scale in a hillslope vineyard, North-West Italy
2017
Scopus
https://www.scopus.com/inward/record.uri?eid=2-s2.0-84979955135&doi=10.1016%2fj.still.2016.07.017&partnerID=40&md5=b5acdca3db73b55d0234c6c7a2828ae4
46-58
journalArticle
153
Biosystems Engineering
DOI 10.1016/j.biosystemseng.2016.11.003
Arcidiacono
C.
Porto
S.M.C.
Mancino
M.
Cascone
G.
A threshold-based algorithm for the development of inertial sensor-based systems to perform real-time cow step counting in free-stall barns
2017
Scopus
https://www.scopus.com/inward/record.uri?eid=2-s2.0-85000443552&doi=10.1016%2fj.biosystemseng.2016.11.003&partnerID=40&md5=d259c4728d04d835daea924ab49efa69
99-109
journalArticle
26
Journal of Forest Economics
DOI 10.1016/j.jfe.2017.01.001
Mulenga
B.P.
Hadunka
P.
Richardson
R.B.
Rural households’ participation in charcoal production in Zambia: Does agricultural productivity play a role?
2017
Scopus
https://www.scopus.com/inward/record.uri?eid=2-s2.0-85014429166&doi=10.1016%2fj.jfe.2017.01.001&partnerID=40&md5=12b78f9e1bee284011f548105cf326d6
56-62
journalArticle
55
Environmental Control in Biology
DOI 10.2525/ecb.55.77
2
Tanigaki
Y.
Higashi
T.
Nagano
A.J.
Honjo
M.N.
Fukuda
H.
Transcriptome analysis of a cultivar of green perilla (perilla frutescens) using genetic similarity with other plants via public databases
2017
Scopus
https://www.scopus.com/inward/record.uri?eid=2-s2.0-85019832705&doi=10.2525%2fecb.55.77&partnerID=40&md5=5b54ba48f932b4d554d620bfad2c2578
77-83
journalArticle
28
Agro Food Industry Hi-Tech
1
Meng
W.
Zhang
L.
Research on logistics business platform of agricultural products in shaanxi province based on GIS+GPS
2017
Scopus
https://www.scopus.com/inward/record.uri?eid=2-s2.0-85020519681&partnerID=40&md5=7fadad0ff997df42b5dc8d1b174914c3
2565-2569
journalArticle
55
Soil Research
DOI 10.1071/SR16336
5-6
Herridge
D.F.
Validation of NBudget for estimating soil N supply in Australia's northern grains region in the absence of soil test data
2017
Scopus
https://www.scopus.com/inward/record.uri?eid=2-s2.0-85028553993&doi=10.1071%2fSR16336&partnerID=40&md5=c1addee6b375622f05f37d188a273c4c
590-599
journalArticle
60
Transactions of the ASABE
DOI 10.13031/trans.12159
4
Maucieri
C.
Borin
M.
CO2 emissions and maize biomass production using digestate liquid fraction in two soil texture types
2017
Scopus
https://www.scopus.com/inward/record.uri?eid=2-s2.0-85028841749&doi=10.13031%2ftrans.12159&partnerID=40&md5=634e11c7c2b47c915e7861fa1c153cc4
1325-1336
journalArticle
60
Transactions of the ASABE
DOI 10.13031/trans.12002
4
Wang
L.
Flanagan
D.C.
Cherkauer
K.A.
Development of a coupled water quality model
2017
Scopus
https://www.scopus.com/inward/record.uri?eid=2-s2.0-85028861914&doi=10.13031%2ftrans.12002&partnerID=40&md5=56f453122b0a68586898cab384a62070
1153-1170
journalArticle
60
Transactions of the ASABE
DOI 10.13031/trans.12072
4
Kukal
M.
Irmak
S.
Spatial and temporal changes in maize and soybean grain yield, precipitation use efficiency, and crop water productivity in the U.S. great plains
2017
Scopus
https://www.scopus.com/inward/record.uri?eid=2-s2.0-85028869576&doi=10.13031%2ftrans.12072&partnerID=40&md5=50f84031619c2266c541a811039d30f9
1189-1208
journalArticle
2
AIMS Agriculture and Food
DOI 10.3934/agrfood.2017.2.165
2
Duncan
J.M.A.
Dash
J.
Tompkins
E.L.
Observing adaptive capacity in Indian rice production systems
2017
Scopus
https://www.scopus.com/inward/record.uri?eid=2-s2.0-85037857013&doi=10.3934%2fagrfood.2017.2.165&partnerID=40&md5=52095b53b8261a548912cba57adffd3b
165-182
journalArticle
287
Geoderma
DOI 10.1016/j.geoderma.2016.06.027
Kravchenko
A.N.
Guber
A.K.
Soil pores and their contributions to soil carbon processes
2017
Scopus
https://www.scopus.com/inward/record.uri?eid=2-s2.0-84999089897&doi=10.1016%2fj.geoderma.2016.06.027&partnerID=40&md5=080668e9b41a0d2a56f6d6c5b5724c94
31-39
journalArticle
288
Geoderma
DOI 10.1016/j.geoderma.2016.10.037
St. Luce
M.
Ziadi
N.
Gagnon
B.
Karam
A.
Visible near infrared reflectance spectroscopy prediction of soil heavy metal concentrations in paper mill biosolid- and liming by-product-amended agricultural soils
2017
Scopus
https://www.scopus.com/inward/record.uri?eid=2-s2.0-84994860564&doi=10.1016%2fj.geoderma.2016.10.037&partnerID=40&md5=9df62b160d065d0ff5a4b9f6f169d902
23-36
journalArticle
239
Agriculture, Ecosystems and Environment
DOI 10.1016/j.agee.2017.01.014
Fenton
O.
Mellander
P.-E.
Daly
K.
Wall
D.P.
Jahangir
M.M.R.
Jordan
P.
Hennessey
D.
Huebsch
M.
Blum
P.
Vero
S.
Richards
K.G.
Integrated assessment of agricultural nutrient pressures and legacies in karst landscapes
2017
Scopus
https://www.scopus.com/inward/record.uri?eid=2-s2.0-85012298815&doi=10.1016%2fj.agee.2017.01.014&partnerID=40&md5=ca3bfc2009b77816bde5777c60a9cf68
246-256
journalArticle
289
Geoderma
DOI 10.1016/j.geoderma.2016.11.022
Zhang
Y.
Biswas
A.
Adamchuk
V.I.
Implementation of a sigmoid depth function to describe change of soil pH with depth
2017
Scopus
https://www.scopus.com/inward/record.uri?eid=2-s2.0-84997522594&doi=10.1016%2fj.geoderma.2016.11.022&partnerID=40&md5=2155f10fee2a081ca743624178debf2b
1-10
journalArticle
155
Biosystems Engineering
DOI 10.1016/j.biosystemseng.2016.11.010
Zhang
Y.
Lisle
A.T.
Phillips
C.J.C.
Development of an effective sampling strategy for ammonia, temperature and relative humidity measurement during sheep transport by ship
2017
Scopus
https://www.scopus.com/inward/record.uri?eid=2-s2.0-85006744033&doi=10.1016%2fj.biosystemseng.2016.11.010&partnerID=40&md5=597cf16325882366b18b5f522771019d
12-23
journalArticle
183
Agricultural Water Management
DOI 10.1016/j.agwat.2016.10.006
Jiménez-Carvajal
C.
Ruiz-Peñalver
L.
Vera-Repullo
J.A.
Jiménez-Buendía
M.
Antolino-Merino
A.
Molina-Martínez
J.M.
Weighing lysimetric system for the determination of the water balance during irrigation in potted plants
2017
Scopus
https://www.scopus.com/inward/record.uri?eid=2-s2.0-85006110900&doi=10.1016%2fj.agwat.2016.10.006&partnerID=40&md5=32d2085e64a4f55ae9ed2a8b7f790a75
78-85
journalArticle
183
Agricultural Water Management
DOI 10.1016/j.agwat.2016.10.020
López-Riquelme
J.A.
Pavón-Pulido
N.
Navarro-Hellín
H.
Soto-Valles
F.
Torres-Sánchez
R.
A software architecture based on FIWARE cloud for Precision Agriculture
2017
Scopus
https://www.scopus.com/inward/record.uri?eid=2-s2.0-85013392308&doi=10.1016%2fj.agwat.2016.10.020&partnerID=40&md5=622b0a7c615443923a97c007750b0c4f
123-135
journalArticle
9
GCB Bioenergy
DOI 10.1111/gcbb.12384
4
Ojeda
J.J.
Volenec
J.J.
Brouder
S.M.
Caviglia
O.P.
Agnusdei
M.G.
Evaluation of Agricultural Production Systems Simulator as yield predictor of Panicum virgatum and Miscanthus x giganteus in several US environments
2017
Scopus
https://www.scopus.com/inward/record.uri?eid=2-s2.0-84979626570&doi=10.1111%2fgcbb.12384&partnerID=40&md5=bf44a9a36625d4361d5719944183e1ab
796-816
journalArticle
135
Computers and Electronics in Agriculture
DOI 10.1016/j.compag.2017.02.004
Pezzuolo
A.
Dumont
B.
Sartori
L.
Marinello
F.
De Antoni Migliorati
M.
Basso
B.
Evaluating the impact of soil conservation measures on soil organic carbon at the farm scale
2017
Scopus
https://www.scopus.com/inward/record.uri?eid=2-s2.0-85013191679&doi=10.1016%2fj.compag.2017.02.004&partnerID=40&md5=2bfe1be69fc7d898459a0f89d846f708
175-182
journalArticle
136
Computers and Electronics in Agriculture
DOI 10.1016/j.compag.2017.03.002
Klein
T.
Samourkasidis
A.
Athanasiadis
I.N.
Bellocchi
G.
Calanca
P.
webXTREME: R-based web tool for calculating agroclimatic indices of extreme events
2017
Scopus
https://www.scopus.com/inward/record.uri?eid=2-s2.0-85015453816&doi=10.1016%2fj.compag.2017.03.002&partnerID=40&md5=4a71036971df0cc103e92e4093b09917
111-116
journalArticle
64
Land Use Policy
DOI 10.1016/j.landusepol.2017.01.049
Petrescu-Mag
R.M.
Petrescu
D.C.
Petrescu-Mag
I.V.
Whereto land fragmentation–land grabbing in Romania? The place of negotiation in reaching win–win community-based solutions
2017
Scopus
https://www.scopus.com/inward/record.uri?eid=2-s2.0-85014550408&doi=10.1016%2fj.landusepol.2017.01.049&partnerID=40&md5=3b018008c7b67a82f879816682a2b293
174-185
journalArticle
35
Irrigation Science
DOI 10.1007/s00271-017-0537-9
3
Trout
T.J.
Bausch
W.C.
USDA-ARS Colorado maize water productivity data set
2017
Scopus
https://www.scopus.com/inward/record.uri?eid=2-s2.0-85014758282&doi=10.1007%2fs00271-017-0537-9&partnerID=40&md5=db93525c291e030468a1f704b35ada78
241-249
journalArticle
169
Soil and Tillage Research
DOI 10.1016/j.still.2017.01.006
Vasu
D.
Singh
S.K.
Sahu
N.
Tiwary
P.
Chandran
P.
Duraisami
V.P.
Ramamurthy
V.
Lalitha
M.
Kalaiselvi
B.
Assessment of spatial variability of soil properties using geospatial techniques for farm level nutrient management
2017
Scopus
https://www.scopus.com/inward/record.uri?eid=2-s2.0-85011360890&doi=10.1016%2fj.still.2017.01.006&partnerID=40&md5=61361d7c00dd184ec2a69797df998de8
25-34
journalArticle
138
Computers and Electronics in Agriculture
DOI 10.1016/j.compag.2017.04.019
Sawant
S.
Durbha
S.S.
Jagarlapudi
A.
Interoperable agro-meteorological observation and analysis platform for precision agriculture: A case study in citrus crop water requirement estimation
2017
Scopus
https://www.scopus.com/inward/record.uri?eid=2-s2.0-85018776776&doi=10.1016%2fj.compag.2017.04.019&partnerID=40&md5=c21a63dccbfb2922c12cec66c93bac41
175-187
journalArticle
196
Remote Sensing of Environment
DOI 10.1016/j.rse.2017.05.017
Afshar
M.H.
Yilmaz
M.T.
The added utility of nonlinear methods compared to linear methods in rescaling soil moisture products
2017
Scopus
https://www.scopus.com/inward/record.uri?eid=2-s2.0-85019441820&doi=10.1016%2fj.rse.2017.05.017&partnerID=40&md5=dd04013e1779b8a96f5cc767d7b03915
224-237
journalArticle
81
Soil Science Society of America Journal
DOI 10.2136/sssaj2017.01.0024
4
Weiler
D.A.
Tornquist
C.G.
Parton
W.
Dos Santos
H.P.
Santi
A.
Bayer
C.
Crop biomass, soil carbon, and nitrous oxide as affected by management and climate: A daycent application in Brazil
2017
Scopus
https://www.scopus.com/inward/record.uri?eid=2-s2.0-85028722892&doi=10.2136%2fsssaj2017.01.0024&partnerID=40&md5=a86d897e268e6c60367a77c71e273f93
945-955
journalArticle
13
Custos e Agronegocio
3
Hu
R.
Yuan
L.
Shieh
C.-J.
Discussion of agricultural biotechnology innovation performance with data envelopment analysis
2017
Scopus
https://www.scopus.com/inward/record.uri?eid=2-s2.0-85037716419&partnerID=40&md5=0265e70d5a1352906e6473cf09f2c0e9
62-74
journalArticle
111
Soil Biology and Biochemistry
DOI 10.1016/j.soilbio.2017.03.010
Clivot
H.
Mary
B.
Valé
M.
Cohan
J.-P.
Champolivier
L.
Piraux
F.
Laurent
F.
Justes
E.
Quantifying in situ and modeling net nitrogen mineralization from soil organic matter in arable cropping systems
2017
Scopus
https://www.scopus.com/inward/record.uri?eid=2-s2.0-85017184328&doi=10.1016%2fj.soilbio.2017.03.010&partnerID=40&md5=a7098fc55250fe9fb512cb393f9edc53
44-59
journalArticle
140
Computers and Electronics in Agriculture
DOI 10.1016/j.compag.2017.06.008
Popović
T.
Latinović
N.
Pešić
A.
Zečević
Ž.
Krstajić
B.
Djukanović
S.
Architecting an IoT-enabled platform for precision agriculture and ecological monitoring: A case study
2017
Scopus
https://www.scopus.com/inward/record.uri?eid=2-s2.0-85020907365&doi=10.1016%2fj.compag.2017.06.008&partnerID=40&md5=06e7eae243f26e0bbdb7ab8c17701d44
255-265
journalArticle
161
Biosystems Engineering
DOI 10.1016/j.biosystemseng.2017.06.004
Hove
N.C.Y.
Demeyer
P.
Van der Heyden
C.
Van Weyenberg
S.
Van Langenhove
H.
Improving the repeatability of dynamic olfactometry according to EN 13725: A case study for pig odour
2017
Scopus
https://www.scopus.com/inward/record.uri?eid=2-s2.0-85021700586&doi=10.1016%2fj.biosystemseng.2017.06.004&partnerID=40&md5=f228fb657a3caa54dd0dde346a07c372
70-79
journalArticle
141
Computers and Electronics in Agriculture
DOI 10.1016/j.compag.2017.07.001
González-Esquiva
J.M.
Oates
M.J.
García-Mateos
G.
Moros-Valle
B.
Molina-Martínez
J.M.
Ruiz-Canales
A.
Development of a visual monitoring system for water balance estimation of horticultural crops using low cost cameras
2017
Scopus
https://www.scopus.com/inward/record.uri?eid=2-s2.0-85024098913&doi=10.1016%2fj.compag.2017.07.001&partnerID=40&md5=61c90fc67837fb706bfe84835e653f45
15-26
journalArticle
26
International Agricultural Engineering Journal
3
Li
X.
Gu
L.
Chen
X.
Liu
L.
Jia
L.
Cultivating online: An analysis on an agricultural Q&A community
2017
Scopus
https://www.scopus.com/inward/record.uri?eid=2-s2.0-85036458281&partnerID=40&md5=d4ddfc9b2307ca263d43fadf2496adeb
283-291
journalArticle
199
Remote Sensing of Environment
DOI 10.1016/j.rse.2017.07.015
Veloso
A.
Mermoz
S.
Bouvet
A.
Le Toan
T.
Planells
M.
Dejoux
J.-F.
Ceschia
E.
Understanding the temporal behavior of crops using Sentinel-1 and Sentinel-2-like data for agricultural applications
2017
Scopus
https://www.scopus.com/inward/record.uri?eid=2-s2.0-85026740667&doi=10.1016%2fj.rse.2017.07.015&partnerID=40&md5=be084b3e92f7b35ffe81d9faff9288c1
415-426
journalArticle
193
Agricultural Water Management
DOI 10.1016/j.agwat.2017.07.016
Kodur
S.
Improving the prediction of soil evaporation for different soil types under dryland cropping
2017
Scopus
https://www.scopus.com/inward/record.uri?eid=2-s2.0-85027517436&doi=10.1016%2fj.agwat.2017.07.016&partnerID=40&md5=0bdb886e7cfde0e585e5df7c45f71835
131-141
journalArticle
142
Computers and Electronics in Agriculture
DOI 10.1016/j.compag.2017.09.012
Lu
J.
Hu
J.
Zhao
G.
Mei
F.
Zhang
C.
An in-field automatic wheat disease diagnosis system
2017
Scopus
https://www.scopus.com/inward/record.uri?eid=2-s2.0-85029642675&doi=10.1016%2fj.compag.2017.09.012&partnerID=40&md5=6563b753d5cfb0e1ac871c7e639f787c
369-379
journalArticle
142
Computers and Electronics in Agriculture
DOI 10.1016/j.compag.2017.10.022
Roussey
C.
Bernard
S.
Pinet
F.
Reboud
X.
Cellier
V.
Sivadon
I.
Simonneau
D.
Bourigault
A.-L.
A methodology for the publication of agricultural alert bulletins as LOD
2017
Scopus
https://www.scopus.com/inward/record.uri?eid=2-s2.0-85034031753&doi=10.1016%2fj.compag.2017.10.022&partnerID=40&md5=5f69c219d8eaf096edd46342d79546d8
632-650
journalArticle
307
Geoderma
DOI 10.1016/j.geoderma.2017.07.030
Aynekulu
E.
Mekuria
W.
Tsegaye
D.
Feyissa
K.
Angassa
A.
de Leeuw
J.
Shepherd
K.
Long-term livestock exclosure did not affect soil carbon in southern Ethiopian rangelands
2017
Scopus
https://www.scopus.com/inward/record.uri?eid=2-s2.0-85026448047&doi=10.1016%2fj.geoderma.2017.07.030&partnerID=40&md5=63254d4472d3121d9cc1b2a142ddfd0f
1-7
journalArticle
83
Ecological Indicators
DOI 10.1016/j.ecolind.2017.07.049
Toma
P.
Miglietta
P.P.
Zurlini
G.
Valente
D.
Petrosillo
I.
A non-parametric bootstrap-data envelopment analysis approach for environmental policy planning and management of agricultural efficiency in EU countries
2017
Scopus
https://www.scopus.com/inward/record.uri?eid=2-s2.0-85026836330&doi=10.1016%2fj.ecolind.2017.07.049&partnerID=40&md5=0b1912952319f3a902bf86bf7dd4c96c
132-143
journalArticle
9
Forests
DOI 10.3390/f9010008
1
Mwangi
H.M.
Lariu
P.
Julich
S.
Patil
S.D.
McDonald
M.A.
Feger
K.-H.
Characterizing the intensity and dynamics of land-use change in the Mara River Basin, East Africa
2017
Scopus
https://www.scopus.com/inward/record.uri?eid=2-s2.0-85039792193&doi=10.3390%2ff9010008&partnerID=40&md5=a95ed6dd37d8272789ef508f6ad14a5f
journalArticle
44
European Review of Agricultural Economics
DOI 10.1093/erae/jbx017
5
Rosas
F.
Lence
S.H.
Duality theory in empirical work, revisited
2017
Scopus
https://www.scopus.com/inward/record.uri?eid=2-s2.0-85044165807&doi=10.1093%2ferae%2fjbx017&partnerID=40&md5=17a3ce06b490032e70781437cab2acf5
836-859
journalArticle
144
Computers and Electronics in Agriculture
DOI 10.1016/j.compag.2017.12.001
Barth
R.
IJsselmuiden
J.
Hemming
J.
Henten
E.J.V.
Data synthesis methods for semantic segmentation in agriculture: A Capsicum annuum dataset
2018
Scopus
https://www.scopus.com/inward/record.uri?eid=2-s2.0-85038213431&doi=10.1016%2fj.compag.2017.12.001&partnerID=40&md5=834b365fa3c21a375285a3e4aad2c799
284-296
journalArticle
204
Remote Sensing of Environment
DOI 10.1016/j.rse.2017.10.030
Chen
Y.
Lu
D.
Luo
L.
Pokhrel
Y.
Deb
K.
Huang
J.
Ran
Y.
Detecting irrigation extent, frequency, and timing in a heterogeneous arid agricultural region using MODIS time series, Landsat imagery, and ancillary data
2018
Scopus
https://www.scopus.com/inward/record.uri?eid=2-s2.0-85032226614&doi=10.1016%2fj.rse.2017.10.030&partnerID=40&md5=b983d2d1435dd3915a7647cbe4939508
197-211
journalArticle
195
Agricultural Water Management
DOI 10.1016/j.agwat.2017.10.010
Ojeda
J.J.
Caviglia
O.P.
Volenec
J.J.
Brouder
S.M.
Agnusdei
M.G.
Modelling stover and grain yields, and subsurface artificial drainage from long-term corn rotations using APSIM
2018
Scopus
https://www.scopus.com/inward/record.uri?eid=2-s2.0-85032859126&doi=10.1016%2fj.agwat.2017.10.010&partnerID=40&md5=a94be95b7ee422116d7336c1dfbc8d10
154-171
journalArticle
13
International Journal of Design and Nature and Ecodynamics
DOI 10.2495/DNE-V13-N3-307-314
3
Budaev
D.
Lada
A.
Simonova
E.
Skobelev
P.
Travin
V.
Yalovenko
O.
Voshchuk
G.
Zhilyaev
A.
Conceptual design of smart farming solution for precise agriculture
2018
Scopus
https://www.scopus.com/inward/record.uri?eid=2-s2.0-85053396216&doi=10.2495%2fDNE-V13-N3-307-314&partnerID=40&md5=7f6d088fcbc0b5d1921a9d0b7f11f3b5
307-314
journalArticle
4
International Journal of Sustainable Agricultural Management and Informatics
DOI 10.1504/IJSAMI.2018.094810
2
Lomotey
R.K.
Mammay
A.
Orji
R.
Mobile technology for smart agriculture: Deployment case for cocoa production
2018
Scopus
https://www.scopus.com/inward/record.uri?eid=2-s2.0-85054031127&doi=10.1504%2fIJSAMI.2018.094810&partnerID=40&md5=dc72a8d855c0666ab9454afb0b42bd6e
83-97
journalArticle
66
Acta Universitatis Agriculturae et Silviculturae Mendelianae Brunensis
DOI 10.11118/actaun201866041035
4
Urbancová
H.
Fajčíková
A.
Kala
V.
Learning methods and their efficiency in agricultural organisations in the Czech Republic
2018
Scopus
https://www.scopus.com/inward/record.uri?eid=2-s2.0-85054559560&doi=10.11118%2factaun201866041035&partnerID=40&md5=dca169a4df667148d724af5d2367f0be
1035-1041
journalArticle
10
Water (Switzerland)
DOI 10.3390/w10020121
2
Marchant
D.J.-U.
Peña
A.G.
Tamas
M.
Harou
J.J.
Simulatingwater allocation and cropping decisions in Yemen's Abyan Delta spate irrigation system
2018
Scopus
https://www.scopus.com/inward/record.uri?eid=2-s2.0-85041357810&doi=10.3390%2fw10020121&partnerID=40&md5=d418f829b65e37bdfe9a40345aea3a30
journalArticle
311
Geoderma
DOI 10.1016/j.geoderma.2017.01.018
Arias
O.V.
Garrido
A.
Villeta
M.
Tarquis
A.M.
Homogenisation of a soil properties map by principal component analysis to define index agricultural insurance policies
2018
Scopus
https://www.scopus.com/inward/record.uri?eid=2-s2.0-85009971892&doi=10.1016%2fj.geoderma.2017.01.018&partnerID=40&md5=62e835ff756590cf820b2265452c83f8
149-158
journalArticle
311
Geoderma
DOI 10.1016/j.geoderma.2017.02.013
Torre
I.G.
Losada
J.C.
Heck
R.J.
Tarquis
A.M.
Multifractal analysis of 3D images of tillage soil
2018
Scopus
https://www.scopus.com/inward/record.uri?eid=2-s2.0-85014115811&doi=10.1016%2fj.geoderma.2017.02.013&partnerID=40&md5=b283fd510be2b38ccfbe4c0f28bb6ac6
167-174
journalArticle
85
Ecological Indicators
DOI 10.1016/j.ecolind.2017.11.046
Alignier
A.
Le Cœur
D.
Lanoë
E.
Ferchaud
F.
Roche
B.
Thenail
C.
Ecobordure: A flora-based indicator to assess vegetation patterns of field margins and infer its local drivers. Design in Brittany (France)
2018
Scopus
https://www.scopus.com/inward/record.uri?eid=2-s2.0-85035014720&doi=10.1016%2fj.ecolind.2017.11.046&partnerID=40&md5=8adb2916bec72b9a74ab9f2b84f19f5e
832-840
journalArticle
145
Computers and Electronics in Agriculture
DOI 10.1016/j.compag.2017.12.026
Jeppesen
J.H.
Ebeid
E.
Jacobsen
R.H.
Toftegaard
T.S.
Open geospatial infrastructure for data management and analytics in interdisciplinary research
2018
Scopus
https://www.scopus.com/inward/record.uri?eid=2-s2.0-85039445105&doi=10.1016%2fj.compag.2017.12.026&partnerID=40&md5=2bdd21ac8406b47df446a63f3f543244
130-141
journalArticle
77
Environmental Earth Sciences
DOI 10.1007/s12665-017-7200-x
3
Duque
C.
Gómez Fontalva
J.M.
Murillo Díaz
J.M.
Calvache
M.L.
Estimating the water budget in a semi-arid region (Torrevieja aquifer—south-east Spain) by assessing groundwater numerical models and hydrochemical data
2018
Scopus
https://www.scopus.com/inward/record.uri?eid=2-s2.0-85040962734&doi=10.1007%2fs12665-017-7200-x&partnerID=40&md5=7f884d1fd09d615d828b137ef33f30af
journalArticle
10
Water (Switzerland)
DOI 10.3390/w10020148
2
Xu
H.
Wu
M.
A first estimation of county-based greenwater availability and its implications for agriculture and bioenergy production in the United States
2018
Scopus
https://www.scopus.com/inward/record.uri?eid=2-s2.0-85041470438&doi=10.3390%2fw10020148&partnerID=40&md5=94abdbb40e07afd284a2b4caa5355138
journalArticle
14
Agris On-line Papers in Economics and Informatics
DOI 10.7160/aol.2022.140108
1
Sudha
M.K.
Manorama
M.
Aditi
T.
Smart Agricultural Decision Support Systems for Predicting Soil Nutrition Value Using IoT and Ridge Regression
2022
Scopus
https://www.scopus.com/inward/record.uri?eid=2-s2.0-85129339591&doi=10.7160%2faol.2022.140108&partnerID=40&md5=618afc9f91d45dea0c2ecc8460761d47
95-106
journalArticle
19
Mathematical Biosciences and Engineering
DOI 10.3934/mbe.2022370
8
Pandey
V.
Anand
K.
Kalra
A.
Gupta
A.
Roy
P.P.
Kim
B.-G.
Enhancing object detection in aerial images
2022
Scopus
https://www.scopus.com/inward/record.uri?eid=2-s2.0-85131736189&doi=10.3934%2fmbe.2022370&partnerID=40&md5=756a74f18e0b90dbd104e3bf9a8d0ee3
7920-7932
journalArticle
65
Journal of the ASABE
DOI 10.13031/ja.15045
4
Adams
B.
Darr
M.
Validation Principles of Agricultural Machine Multibody Dynamics Models
2022
Scopus
https://www.scopus.com/inward/record.uri?eid=2-s2.0-85136590513&doi=10.13031%2fja.15045&partnerID=40&md5=a93f2b16060dcec4e3c827e9d3065076
801-814
journalArticle
Journal of Food Measurement and Characterization
DOI 10.1007/s11694-022-01795-3
Uğuz
S.
Şikaroğlu
G.
Yağız
A.
Disease detection and physical disorders classification for citrus fruit images using convolutional neural network
2022
Scopus
https://www.scopus.com/inward/record.uri?eid=2-s2.0-85145177295&doi=10.1007%2fs11694-022-01795-3&partnerID=40&md5=2f53c9be1904707682971282b50e59b5
journalArticle
68
INMATEH - Agricultural Engineering
DOI 10.35633/inmateh-68-58
3
Xie
S.
Bai
Y.
An
Q.
Song
J.
Tang
X.
Xie
F.
IDENTIFICATION SYSTEM OF TOMATO LEAF DISEASES BASED ON OPTIMIZED MobileNetV2
2022
基于改进MobileNetV2的番茄叶部病害识别
Scopus
https://www.scopus.com/inward/record.uri?eid=2-s2.0-85146645750&doi=10.35633%2finmateh-68-58&partnerID=40&md5=91643ef0b5174b04f9699bc5eb1a8c72
589-598
journalArticle
193
Computers and Electronics in Agriculture
DOI 10.1016/j.compag.2021.106650
Qiao
Y.
Guo
Y.
Yu
K.
He
D.
C3D-ConvLSTM based cow behaviour classification using video data for precision livestock farming
2022
Scopus
https://www.scopus.com/inward/record.uri?eid=2-s2.0-85122303759&doi=10.1016%2fj.compag.2021.106650&partnerID=40&md5=aa6ff11cdb46c202b6ff865a54e7dcfa
journalArticle
11
Ukrainian Food Journal
DOI 10.24263/2304-974X-2022-11-3-10
3
Erdei-Gally
S.
Vágány
J.
Role of precision agriculture in food supply
2022
Scopus
https://www.scopus.com/inward/record.uri?eid=2-s2.0-85149049319&doi=10.24263%2f2304-974X-2022-11-3-10&partnerID=40&md5=1e1d85a7ff97b625573a6c8353223789
458-473
journalArticle
193
Computers and Electronics in Agriculture
DOI 10.1016/j.compag.2021.106675
Xu
B.
Wang
W.
Guo
L.
Chen
G.
Li
Y.
Cao
Z.
Wu
S.
CattleFaceNet: A cattle face identification approach based on RetinaFace and ArcFace loss
2022
Scopus
https://www.scopus.com/inward/record.uri?eid=2-s2.0-85122520791&doi=10.1016%2fj.compag.2021.106675&partnerID=40&md5=3aada050829d428068724112140d8f67
journalArticle
193
Computers and Electronics in Agriculture
DOI 10.1016/j.compag.2022.106689
Brown
J.
Qiao
Y.
Clark
C.
Lomax
S.
Rafique
K.
Sukkarieh
S.
Automated aerial animal detection when spatial resolution conditions are varied
2022
Scopus
https://www.scopus.com/inward/record.uri?eid=2-s2.0-85123033975&doi=10.1016%2fj.compag.2022.106689&partnerID=40&md5=7d395eba35eb3cfd72a4c2767747a5b2
journalArticle
14
Water (Switzerland)
DOI 10.3390/w14030327
3
Kavka
P.
Jeřábek
J.
Landa
M.
SMODERP2D—Sheet and Rill Runoff Routine Validation at Three Scale Levels
2022
Scopus
https://www.scopus.com/inward/record.uri?eid=2-s2.0-85123727864&doi=10.3390%2fw14030327&partnerID=40&md5=2da9321156381a4726efb143408af6e9
journalArticle
10
PeerJ
DOI 10.7717/peerj.12870
Traba
J.
Pérez-Granados
C.
Extensive sheep grazing is associated with trends in steppe birds in Spain: Recommendations for the Common Agricultural Policy
2022
Scopus
https://www.scopus.com/inward/record.uri?eid=2-s2.0-85126548842&doi=10.7717%2fpeerj.12870&partnerID=40&md5=a4adbd63c0343ecb0ddd374435e878fc
journalArticle
114
Land Use Policy
DOI 10.1016/j.landusepol.2021.105954
Soubry
B.
Sherren
K.
"You keep using that word…": Disjointed definitions of resilience in food systems adaptation
2022
Scopus
https://www.scopus.com/inward/record.uri?eid=2-s2.0-85121977213&doi=10.1016%2fj.landusepol.2021.105954&partnerID=40&md5=04dd446ff6a07a47ba949c465dcc10a8
journalArticle
166
Soil Biology and Biochemistry
DOI 10.1016/j.soilbio.2021.108468
Mamet
S.D.
Helgason
B.L.
Lamb
E.G.
McGillivray
A.
Stanley
K.G.
Robinson
S.J.
Aziz
S.U.
Vail
S.
Siciliano
S.D.
Phenology-dependent root bacteria enhance yield of Brassica napus
2022
Scopus
https://www.scopus.com/inward/record.uri?eid=2-s2.0-85122471504&doi=10.1016%2fj.soilbio.2021.108468&partnerID=40&md5=45215650602c5c84fefedc159667fd1a
journalArticle
194
Computers and Electronics in Agriculture
DOI 10.1016/j.compag.2022.106776
Guo
X.
Lu
S.
Tang
Z.
Bai
Z.
Diao
L.
Zhou
H.
Li
L.
CG-ANER: Enhanced contextual embeddings and glyph features-based agricultural named entity recognition
2022
Scopus
https://www.scopus.com/inward/record.uri?eid=2-s2.0-85124189483&doi=10.1016%2fj.compag.2022.106776&partnerID=40&md5=c61ccb46fdf472a4bd3bf86a9bdfe643
journalArticle
194
Computers and Electronics in Agriculture
DOI 10.1016/j.compag.2022.106730
Billah
M.
Wang
X.
Yu
J.
Jiang
Y.
Real-time goat face recognition using convolutional neural network
2022
Scopus
https://www.scopus.com/inward/record.uri?eid=2-s2.0-85124271945&doi=10.1016%2fj.compag.2022.106730&partnerID=40&md5=8ac662ff931a3df2d31998f01bb2af15
journalArticle
194
Computers and Electronics in Agriculture
DOI 10.1016/j.compag.2022.106796
Biney
J.K.M.
Verifying the predictive performance for soil organic carbon when employing field Vis-NIR spectroscopy and satellite imagery obtained using two different sampling methods
2022
Scopus
https://www.scopus.com/inward/record.uri?eid=2-s2.0-85124897572&doi=10.1016%2fj.compag.2022.106796&partnerID=40&md5=c679c11102413cc800484546afafaefb
journalArticle
195
Computers and Electronics in Agriculture
DOI 10.1016/j.compag.2022.106706
Biase
A.G.
Albertini
T.Z.
de Mello
R.F.
On supervised learning to model and predict cattle weight in precision livestock breeding
2022
Scopus
https://www.scopus.com/inward/record.uri?eid=2-s2.0-85126048818&doi=10.1016%2fj.compag.2022.106706&partnerID=40&md5=66e54272d7d6e90d5ff5cd74e06c17d7
journalArticle
14
Water (Switzerland)
DOI 10.3390/w14081198
8
Al-Bakri
J.T.
D’urso
G.
Batchelor
C.
Abukhalaf
M.
Alobeiaat
A.
Al-Khreisat
A.
Vallee
D.
Remote Sensing-Based Agricultural Water Accounting for the North Jordan Valley
2022
Scopus
https://www.scopus.com/inward/record.uri?eid=2-s2.0-85128721201&doi=10.3390%2fw14081198&partnerID=40&md5=f6501b0cd73c19ff865a432c478a65ac
journalArticle
174
Physiologia Plantarum
DOI 10.1111/ppl.13672
2
Wang
J.
Sidharth
S.
Zeng
S.
Jiang
Y.
Chan
Y.O.
Lyu
Z.
McCubbin
T.
Mertz
R.
Sharp
R.E.
Joshi
T.
Bioinformatics for plant and agricultural discoveries in the age of multiomics: A review and case study of maize nodal root growth under water deficit
2022
Scopus
https://www.scopus.com/inward/record.uri?eid=2-s2.0-85128775790&doi=10.1111%2fppl.13672&partnerID=40&md5=117881ab7bc77824cdc44a1dd5e4c748
journalArticle
195
Computers and Electronics in Agriculture
DOI 10.1016/j.compag.2022.106786
Lawson
A.R.
Giri
K.
Thomson
A.L.
Karunaratne
S.B.
Smith
K.F.
Jacobs
J.L.
Morse-McNabb
E.M.
Multi-site calibration and validation of a wide-angle ultrasonic sensor and precise GPS to estimate pasture mass at the paddock scale
2022
Scopus
https://www.scopus.com/inward/record.uri?eid=2-s2.0-85125139770&doi=10.1016%2fj.compag.2022.106786&partnerID=40&md5=7b7ab522a02f0d9baf7e1a15242d22ac
journalArticle
221
Ocean and Coastal Management
DOI 10.1016/j.ocecoaman.2022.106082
Nguyen
H.
Chu
L.
Harper
R.J.
Dell
B.
Hoang
H.
Mangrove-shrimp farming: A triple-win approach for communities in the Mekong River Delta
2022
Scopus
https://www.scopus.com/inward/record.uri?eid=2-s2.0-85126089229&doi=10.1016%2fj.ocecoaman.2022.106082&partnerID=40&md5=17399b016dd921716d5f5016ff696e2a
journalArticle
19
International Journal of Environmental Science and Technology
DOI 10.1007/s13762-021-03300-7
5
Gangwar
D.S.
Tyagi
S.
Soni
S.K.
A techno-economic analysis of digital agriculture services: an ecological approach toward green growth
2022
Scopus
https://www.scopus.com/inward/record.uri?eid=2-s2.0-85104498295&doi=10.1007%2fs13762-021-03300-7&partnerID=40&md5=2119449fe27de6a3dcc9f4869533db8e
3859-3870
journalArticle
196
Computers and Electronics in Agriculture
DOI 10.1016/j.compag.2020.105965
Subirats-Coll
I.
Kolshus
K.
Turbati
A.
Stellato
A.
Mietzsch
E.
Martini
D.
Zeng
M.
AGROVOC: The linked data concept hub for food and agriculture
2022
Scopus
https://www.scopus.com/inward/record.uri?eid=2-s2.0-85127314050&doi=10.1016%2fj.compag.2020.105965&partnerID=40&md5=f08069b36539447aaed2f351130350b9
journalArticle
196
Computers and Electronics in Agriculture
DOI 10.1016/j.compag.2022.106909
Top
J.
Janssen
S.
Boogaard
H.
Knapen
R.
Şimşek-Şenel
G.
Cultivating FAIR principles for agri-food data
2022
Scopus
https://www.scopus.com/inward/record.uri?eid=2-s2.0-85127177971&doi=10.1016%2fj.compag.2022.106909&partnerID=40&md5=f2a00746d9c9dc0596c80ee26e364343
journalArticle
138
Ecological Indicators
DOI 10.1016/j.ecolind.2022.108869
Zhang
F.
Zhang
W.
Wu
S.
Fu
X.
Li
S.
Yue
S.
Analysis of UV–Vis spectral characteristics and content estimation of soil DOM under mulching practices
2022
Scopus
https://www.scopus.com/inward/record.uri?eid=2-s2.0-85128263294&doi=10.1016%2fj.ecolind.2022.108869&partnerID=40&md5=3aba67684f15cee774aebb38699ad372
journalArticle
8
Modeling Earth Systems and Environment
DOI 10.1007/s40808-021-01197-2
2
Ihinegbu
C.
Ogunwumi
T.
Multi-criteria modelling of drought: a study of Brandenburg Federal State, Germany
2022
Scopus
https://www.scopus.com/inward/record.uri?eid=2-s2.0-85107758324&doi=10.1007%2fs40808-021-01197-2&partnerID=40&md5=0dbeecfe04080bb78780697f331bdeac
2035-2049
journalArticle
179
Marine Pollution Bulletin
DOI 10.1016/j.marpolbul.2022.113748
Andréfouët
S.
Desclaux
T.
Buttin
J.
Jullien
S.
Aucan
J.
Le Gendre
R.
Liao
V.
Periodicity of wave-driven flows and lagoon water renewal for 74 Central Pacific Ocean atolls
2022
Scopus
https://www.scopus.com/inward/record.uri?eid=2-s2.0-85128208115&doi=10.1016%2fj.marpolbul.2022.113748&partnerID=40&md5=eeb59ddd17220acaeafa074df46e1d6e
journalArticle
196
Computers and Electronics in Agriculture
DOI 10.1016/j.compag.2022.106904
Gargiulo
J.I.
Lyons
N.A.
Clark
C.E.F.
Garcia
S.C.
The AMS Integrated Management Model: A decision-support system for automatic milking systems
2022
Scopus
https://www.scopus.com/inward/record.uri?eid=2-s2.0-85134621227&doi=10.1016%2fj.compag.2022.106904&partnerID=40&md5=db71f5a32511fbde1e75cfc05c17b677
journalArticle
9
Information Processing in Agriculture
DOI 10.1016/j.inpa.2021.04.012
2
Murphy
D.J.
O' Brien
B.
O' Donovan
M.
Condon
T.
Murphy
M.D.
A near infrared spectroscopy calibration for the prediction of fresh grass quality on Irish pastures
2022
Scopus
https://www.scopus.com/inward/record.uri?eid=2-s2.0-85106246697&doi=10.1016%2fj.inpa.2021.04.012&partnerID=40&md5=ef6b2c9db1528d0bc49d3768324650ff
243-253
journalArticle
197
Computers and Electronics in Agriculture
DOI 10.1016/j.compag.2022.106917
Blok
P.M.
Kootstra
G.
Elghor
H.E.
Diallo
B.
van Evert
F.K.
van Henten
E.J.
Active learning with MaskAL reduces annotation effort for training Mask R-CNN on a broccoli dataset with visually similar classes
2022
Scopus
https://www.scopus.com/inward/record.uri?eid=2-s2.0-85127789543&doi=10.1016%2fj.compag.2022.106917&partnerID=40&md5=bed361be1a5fa74eccea6870b8db4b6a
journalArticle
197
Computers and Electronics in Agriculture
DOI 10.1016/j.compag.2022.106946
Zhang
C.
Dong
J.
Ge
Q.
Quantifying the accuracies of six 30-m cropland datasets over China: A comparison and evaluation analysis
2022
Scopus
https://www.scopus.com/inward/record.uri?eid=2-s2.0-85128292481&doi=10.1016%2fj.compag.2022.106946&partnerID=40&md5=2fea029799c424716df274bdc7e06821
journalArticle
12
Agriculture (Switzerland)
DOI 10.3390/agriculture12060767
6
Borrero
J.D.
Mariscal
J.
A Case Study of a Digital Data Platform for the Agricultural Sector: A Valuable Decision Support System for Small Farmers
2022
Scopus
https://www.scopus.com/inward/record.uri?eid=2-s2.0-85131256615&doi=10.3390%2fagriculture12060767&partnerID=40&md5=b51b907e93d6570292ca14d744c74a2c
journalArticle
14
Water (Switzerland)
DOI 10.3390/w14111687
11
Gradilla-Hernández
M.S.
Díaz-Vázquez
D.
Yebra-Montes
C.
Castillo
A.F.
Shear
H.
Garcia-Gonzalez
A.
Anda
J.
Mazari-Hiriart
M.
Assessment of the Potential of Coordinating Two Interacting Monitoring Networks within the Lerma-Santiago Hydrologic System in Mexico
2022
Scopus
https://www.scopus.com/inward/record.uri?eid=2-s2.0-85131598119&doi=10.3390%2fw14111687&partnerID=40&md5=4602d78d9595c5c756af667be7a2333b
journalArticle
139
Ecological Indicators
DOI 10.1016/j.ecolind.2022.108974
Samaei
F.
Emami
H.
Lakzian
A.
Assessing soil quality of pasture and agriculture land uses in Shandiz county, northwestern Iran
2022
Scopus
https://www.scopus.com/inward/record.uri?eid=2-s2.0-85133905191&doi=10.1016%2fj.ecolind.2022.108974&partnerID=40&md5=2b2ef7a9216ceabcafb799c02fd978c0
journalArticle
13
Frontiers in Plant Science
DOI 10.3389/fpls.2022.808380
Albattah
W.
Javed
A.
Nawaz
M.
Masood
M.
Albahli
S.
Artificial Intelligence-Based Drone System for Multiclass Plant Disease Detection Using an Improved Efficient Convolutional Neural Network
2022
Scopus
https://www.scopus.com/inward/record.uri?eid=2-s2.0-85133468069&doi=10.3389%2ffpls.2022.808380&partnerID=40&md5=c9671e7244f430ba27263071944bd951
journalArticle
276
Remote Sensing of Environment
DOI 10.1016/j.rse.2022.113042
Zhang
P.
Du
P.
Guo
S.
Zhang
W.
Tang
P.
Chen
J.
Zheng
H.
A novel index for robust and large-scale mapping of plastic greenhouse from Sentinel-2 images
2022
Scopus
https://www.scopus.com/inward/record.uri?eid=2-s2.0-85127918237&doi=10.1016%2fj.rse.2022.113042&partnerID=40&md5=1cb00f9981a7fcc93cb77d6aa6143e1d
journalArticle
198
Computers and Electronics in Agriculture
DOI 10.1016/j.compag.2022.107059
Du
A.
Guo
H.
Lu
J.
Su
Y.
Ma
Q.
Ruchay
A.
Marinello
F.
Pezzuolo
A.
Automatic livestock body measurement based on keypoint detection with multiple depth cameras
2022
Scopus
https://www.scopus.com/inward/record.uri?eid=2-s2.0-85130718824&doi=10.1016%2fj.compag.2022.107059&partnerID=40&md5=037262d692c6fae822044e5f9a78ee83
journalArticle
199
Computers and Electronics in Agriculture
DOI 10.1016/j.compag.2022.107187
Williams
M.
Zhan Lai
S.
Classification of dairy cow excretory events using a tail-mounted accelerometer
2022
Scopus
https://www.scopus.com/inward/record.uri?eid=2-s2.0-85133950594&doi=10.1016%2fj.compag.2022.107187&partnerID=40&md5=ce868a2fecb7fc07491146c240eea582
journalArticle
78
Pest Management Science
DOI 10.1002/ps.7008
8
Wang
F.
Wang
S.
Xu
S.
Shen
J.
Cao
L.
Sha
Z.
Chu
Q.
A non-chemical weed control strategy, introducing duckweed into the paddy field
2022
Scopus
https://www.scopus.com/inward/record.uri?eid=2-s2.0-85133959269&doi=10.1002%2fps.7008&partnerID=40&md5=d4e4f8f6035625411a9fb80165c3124b
3654-3663
journalArticle
31
Animal Welfare
DOI 10.7120/09627286.31.1.013
3
Andrews
C.P.
On the use of body mass measures in severity assessment in laboratory passerine birds
2022
Scopus
https://www.scopus.com/inward/record.uri?eid=2-s2.0-85136198878&doi=10.7120%2f09627286.31.1.013&partnerID=40&md5=4d963e7afb5645fc62e9645cca7c638c
387-401
journalArticle
199
Computers and Electronics in Agriculture
DOI 10.1016/j.compag.2022.107127
Ngo
Q.H.
Kechadi
T.
Le-Khac
N.-A.
Knowledge representation in digital agriculture: A step towards standardised model
2022
Scopus
https://www.scopus.com/inward/record.uri?eid=2-s2.0-85132902124&doi=10.1016%2fj.compag.2022.107127&partnerID=40&md5=68251e7c8f53497bb5ae3c17727f0947
journalArticle
12
Journal of Agribusiness in Developing and Emerging Economies
DOI 10.1108/JADEE-11-2021-0307
4
Marin
A.
Stubrin
L.I.
Palacín Roitbarg
R.
Growing from the South in the seed market: Grupo Don Mario
2022
Scopus
https://www.scopus.com/inward/record.uri?eid=2-s2.0-85129294204&doi=10.1108%2fJADEE-11-2021-0307&partnerID=40&md5=4525ec562f563a0fee3c770bb864c4eb
656-672
journalArticle
9
Information Processing in Agriculture
DOI 10.1016/j.inpa.2021.07.002
3
Magaldi Linhares
H.
Braga
R.
Antônio Arbex
W.
Magalhães Campos
M.
Campos
F.
David
J.M.N.
Stroele
V.
FeedEfficiencyService: An architecture for the comparison of data from multiple studies related to dairy cattle feed efficiency indices
2022
Scopus
https://www.scopus.com/inward/record.uri?eid=2-s2.0-85112071308&doi=10.1016%2fj.inpa.2021.07.002&partnerID=40&md5=c994434407dcbe3d7dc98c2ec4557c0c
378-396
journalArticle
9
Information Processing in Agriculture
DOI 10.1016/j.inpa.2021.08.004
3
Cai
W.
Wei
R.
Xu
L.
Ding
X.
A method for modelling greenhouse temperature using gradient boost decision tree
2022
Scopus
https://www.scopus.com/inward/record.uri?eid=2-s2.0-85115094575&doi=10.1016%2fj.inpa.2021.08.004&partnerID=40&md5=252f54ed29584298852a51f645d7efed
343-354
journalArticle
29
Rice Science
DOI 10.1016/j.rsci.2022.02.003
5
Jeyaraj
P.R.
Asokan
S.P.
Samuel Nadar
E.R.
Computer-Assisted Real-Time Rice Variety Learning Using Deep Learning Network
2022
Scopus
https://www.scopus.com/inward/record.uri?eid=2-s2.0-85136005635&doi=10.1016%2fj.rsci.2022.02.003&partnerID=40&md5=e612ad96e724390416ad6cdf64092565
489-498
journalArticle
10
International Soil and Water Conservation Research
DOI 10.1016/j.iswcr.2021.11.003
3
John
K.
Bouslihim
Y.
Ofem
K.I.
Hssaini
L.
Razouk
R.
Okon
P.B.
Isong
I.A.
Agyeman
P.C.
Kebonye
N.M.
Qin
C.
Do model choice and sample ratios separately or simultaneously influence soil organic matter prediction?
2022
Scopus
https://www.scopus.com/inward/record.uri?eid=2-s2.0-85126130578&doi=10.1016%2fj.iswcr.2021.11.003&partnerID=40&md5=9eb62be65b5b273a997e88f0e37c2cb6
470-486
journalArticle
421
Geoderma
DOI 10.1016/j.geoderma.2022.115905
Paiva
A.F.D.S.
Poppiel
R.R.
Rosin
N.A.
Greschuk
L.T.
Rosas
J.T.F.
Demattê
J.A.M.
The Brazilian Program of soil analysis via spectroscopy (ProBASE): Combining spectroscopy and wet laboratories to understand new technologies
2022
Scopus
https://www.scopus.com/inward/record.uri?eid=2-s2.0-85130197359&doi=10.1016%2fj.geoderma.2022.115905&partnerID=40&md5=84b9d35433bb96cd697630538dae4ea4
journalArticle
14
Nutrients
DOI 10.3390/nu14173603
17
Kelly
R.K.
Pollard
Z.
Young
H.
Piernas
C.
Lentjes
M.
Mulligan
A.
Huybrechts
I.
Carter
J.L.
Key
T.J.
Perez-Cornago
A.
Evaluation of the New Individual Fatty Acid Dataset for UK Biobank: Analysis of Intakes and Sources in 207,997 Participants
2022
Scopus
https://www.scopus.com/inward/record.uri?eid=2-s2.0-85137561348&doi=10.3390%2fnu14173603&partnerID=40&md5=c09274c10ad2491350f43b442d6f144f
journalArticle
279
Remote Sensing of Environment
DOI 10.1016/j.rse.2022.113110
Vrieling
A.
Fava
F.
Leitner
S.
Merbold
L.
Cheng
Y.
Nakalema
T.
Groen
T.
Butterbach-Bahl
K.
Identification of temporary livestock enclosures in Kenya from multi-temporal PlanetScope imagery
2022
Scopus
https://www.scopus.com/inward/record.uri?eid=2-s2.0-85131663485&doi=10.1016%2fj.rse.2022.113110&partnerID=40&md5=59b2b11b4df1d9c1503a384a36f06bf9
journalArticle
69
Genetic Resources and Crop Evolution
DOI 10.1007/s10722-022-01377-8
7
Drosou
K.
Craig
H.
Palmer
K.
Kennedy
S.L.
Wishart
J.
Oliveira
H.R.
Civáň
P.
Martin
P.
Brown
T.A.
The evolutionary relationship between bere barley and other types of cultivated barley
2022
Scopus
https://www.scopus.com/inward/record.uri?eid=2-s2.0-85129310842&doi=10.1007%2fs10722-022-01377-8&partnerID=40&md5=54d70c26c1cad3f72f8fc4269a97f434
2361-2381
journalArticle
14
Water (Switzerland)
DOI 10.3390/w14193024
19
Gaznayee
H.A.A.
Al-Quraishi
A.M.F.
Mahdi
K.
Messina
J.P.
Zaki
S.H.
Razvanchy
H.A.S.
Hakzi
K.
Huebner
L.
Ababakr
S.H.
Riksen
M.
Ritsema
C.
Drought Severity and Frequency Analysis Aided by Spectral and Meteorological Indices in the Kurdistan Region of Iraq
2022
Scopus
https://www.scopus.com/inward/record.uri?eid=2-s2.0-85139965682&doi=10.3390%2fw14193024&partnerID=40&md5=65de080022d9a178e71e120ed4dae342
journalArticle
12
Animals
DOI 10.3390/ani12202872
20
Cassini
M.H.
Human–Wildlife Conflicts: Does Origin Matter?
2022
Scopus
https://www.scopus.com/inward/record.uri?eid=2-s2.0-85140408918&doi=10.3390%2fani12202872&partnerID=40&md5=c6b69be488a8247fe9f1e47d165aa61a
journalArticle
13
Frontiers in Plant Science
DOI 10.3389/fpls.2022.1023924
Zhou
Q.
Huang
Z.
Zheng
S.
Jiao
L.
Wang
L.
Wang
R.
A wheat spike detection method based on Transformer
2022
Scopus
https://www.scopus.com/inward/record.uri?eid=2-s2.0-85141221560&doi=10.3389%2ffpls.2022.1023924&partnerID=40&md5=bb71e73c4cc94f17885d032387523194
journalArticle
144
Forest Policy and Economics
DOI 10.1016/j.forpol.2022.102845
Li
Y.
Song
Z.
Have protected areas in China achieved the ecological and economic “win-win” goals? Evidence from the Giant Panda Reserves of the Min Mont Range
2022
Scopus
https://www.scopus.com/inward/record.uri?eid=2-s2.0-85138387067&doi=10.1016%2fj.forpol.2022.102845&partnerID=40&md5=3a120bc48f578a61e11d4fd3a90663d7
journalArticle
295
Quaternary Science Reviews
DOI 10.1016/j.quascirev.2022.107786
He
K.
Lu
H.
Jin
G.
Wang
C.
Zhang
H.
Zhang
J.
Xu
D.
Shen
C.
Wu
N.
Guo
Z.
Antipodal pattern of millet and rice demography in response to 4.2 ka climate event in China
2022
Scopus
https://www.scopus.com/inward/record.uri?eid=2-s2.0-85139354811&doi=10.1016%2fj.quascirev.2022.107786&partnerID=40&md5=4fafa6b2a61fb98d4551a1671a12002b
journalArticle
82
Agricultural Finance Review
DOI 10.1108/AFR-06-2021-0087
5
Wahdat
A.Z.
Gunderson
M.
Principal operators' farm risk attitudes in hot and cold climates
2022
Scopus
https://www.scopus.com/inward/record.uri?eid=2-s2.0-85116502919&doi=10.1108%2fAFR-06-2021-0087&partnerID=40&md5=9c499297c23f2df3cb1b93c8473ff1f6
797-814
journalArticle
81
Environmental Earth Sciences
DOI 10.1007/s12665-022-10596-2
21
Zhao
D.
Zeng
Y.
Wu
Q.
Mei
A.
Gao
S.
Du
X.
Yang
W.
Hydrogeochemical characterization and suitability assessment of groundwater in a typical coal mining subsidence area in China using self-organizing feature map
2022
Scopus
https://www.scopus.com/inward/record.uri?eid=2-s2.0-85140465097&doi=10.1007%2fs12665-022-10596-2&partnerID=40&md5=8b054364dcc6e722cfe861f67855eb87
journalArticle
202
Computers and Electronics in Agriculture
DOI 10.1016/j.compag.2022.107431
Li
H.
Gan
Y.
Wu
Y.
Guo
L.
EAGNet: A method for automatic extraction of agricultural greenhouses from high spatial resolution remote sensing images based on hybrid multi-attention
2022
Scopus
https://www.scopus.com/inward/record.uri?eid=2-s2.0-85140749194&doi=10.1016%2fj.compag.2022.107431&partnerID=40&md5=5dbdf81a31fd018356a39599649ea5f3
journalArticle
12
Animals
DOI 10.3390/ani12213055
21
Ma
X.
Lu
X.
Huang
Y.
Yang
X.
Xu
Z.
Mo
G.
Ren
Y.
Li
L.
An Advanced Chicken Face Detection Network Based on GAN and MAE
2022
Scopus
https://www.scopus.com/inward/record.uri?eid=2-s2.0-85141753535&doi=10.3390%2fani12213055&partnerID=40&md5=f3fea51f8c052b2a8ebaec5d4bbcb6dd
journalArticle
13
Forests
DOI 10.3390/f13111877
11
Duan
H.
Xu
N.
Assessing Social Values for Ecosystem Services in Rural Areas Based on the SolVES Model: A Case Study from Nanjing, China
2022
Scopus
https://www.scopus.com/inward/record.uri?eid=2-s2.0-85141834353&doi=10.3390%2ff13111877&partnerID=40&md5=12e899ee08e232175ff64f6b0e27b6fa
journalArticle
20
PLoS Biology
DOI 10.1371/journal.pbio.3001867
11
Campbell
M.A.
Loncar
S.
Kotin
R.M.
Gifford
R.J.
Comparative analysis reveals the long-term coevolutionary history of parvoviruses and vertebrates
2022
Scopus
https://www.scopus.com/inward/record.uri?eid=2-s2.0-85143088427&doi=10.1371%2fjournal.pbio.3001867&partnerID=40&md5=e9a3e34c9397b8a68851d96c013a9ab1
journalArticle
19
International Journal of Environmental Science and Technology
DOI 10.1007/s13762-022-03919-0
12
Celen
M.
Oruc
H.N.
Adiller
A.
Yıldız Töre
G.
Onkal Engin
G.
Contribution for pollution sources and their assessment in urban and industrial sites of Ergene River Basin, Turkey
2022
Scopus
https://www.scopus.com/inward/record.uri?eid=2-s2.0-85123495868&doi=10.1007%2fs13762-022-03919-0&partnerID=40&md5=c5fa5c7c9f789c2c1cf2ee6a8194ac5c
11789-11808
journalArticle
282
Remote Sensing of Environment
DOI 10.1016/j.rse.2022.113296
Hu
T.
Mallick
K.
Hulley
G.C.
Planells
L.P.
Göttsche
F.M.
Schlerf
M.
Hitzelberger
P.
Didry
Y.
Szantoi
Z.
Alonso
I.
Sobrino
J.A.
Skoković
D.
Roujean
J.-L.
Boulet
G.
Gamet
P.
Hook
S.
Continental-scale evaluation of three ECOSTRESS land surface temperature products over Europe and Africa: Temperature-based validation and cross-satellite comparison
2022
Scopus
https://www.scopus.com/inward/record.uri?eid=2-s2.0-85139393852&doi=10.1016%2fj.rse.2022.113296&partnerID=40&md5=4a471764a5c971c79eea3741d75ad91e
journalArticle
224
Biosystems Engineering
DOI 10.1016/j.biosystemseng.2022.11.004
Garrido-Izard
M.
Correa
E.C.
Requejo
J.M.
Villarroel
M.
Diezma
B.
Cleansing data from an electronic feeding station to improve estimation of feed efficiency
2022
Scopus
https://www.scopus.com/inward/record.uri?eid=2-s2.0-85142412640&doi=10.1016%2fj.biosystemseng.2022.11.004&partnerID=40&md5=27612b87584c86b776a8dd930326de0b
361-369
journalArticle
29
Land Degradation and Development
DOI 10.1002/ldr.2672
3
Brandolini
P.
Cevasco
A.
Capolongo
D.
Pepe
G.
Lovergine
F.
Del Monte
M.
Response of Terraced Slopes to a Very Intense Rainfall Event and Relationships with Land Abandonment: A Case Study from Cinque Terre (Italy)
2018
Scopus
https://www.scopus.com/inward/record.uri?eid=2-s2.0-85014767771&doi=10.1002%2fldr.2672&partnerID=40&md5=1ed1b23c774df663bc4cc1e1e2787833
630-642
journalArticle
27
Global Ecology and Biogeography
DOI 10.1111/geb.12697
3
Yu
Z.
Lu
C.
Historical cropland expansion and abandonment in the continental U.S. during 1850 to 2016
2018
Scopus
https://www.scopus.com/inward/record.uri?eid=2-s2.0-85038636505&doi=10.1111%2fgeb.12697&partnerID=40&md5=5ea5cf1d93092694acddfbc67224e5f3
322-333
journalArticle
146
Computers and Electronics in Agriculture
DOI 10.1016/j.compag.2018.01.021
Jiang
Q.
Qi
Z.
Madramootoo
C.A.
Singh
A.K.
Simulating hydrologic cycle and crop production in a subsurface drained and sub-irrigated field in Southern Quebec using RZWQM2
2018
Scopus
https://www.scopus.com/inward/record.uri?eid=2-s2.0-85041470866&doi=10.1016%2fj.compag.2018.01.021&partnerID=40&md5=37223726c6efe9d5cbe113f75f4422b8
31-42
journalArticle
5
Information Processing in Agriculture
DOI 10.1016/j.inpa.2017.11.003
1
Kaushik
N.
Chatterjee
N.
Automatic relationship extraction from agricultural text for ontology construction
2018
Scopus
https://www.scopus.com/inward/record.uri?eid=2-s2.0-85042761520&doi=10.1016%2fj.inpa.2017.11.003&partnerID=40&md5=1461bd2ca0bd4dee7d451f407f4d0a1e
60-73
journalArticle
201
Agricultural Water Management
DOI 10.1016/j.agwat.2018.01.009
Tolomio
M.
Borin
M.
Water table management to save water and reduce nutrient losses from agricultural fields: 6 years of experience in North-Eastern Italy
2018
Scopus
https://www.scopus.com/inward/record.uri?eid=2-s2.0-85041491265&doi=10.1016%2fj.agwat.2018.01.009&partnerID=40&md5=9f1fa558dc6ea4bed933270fa37cf50f
1-10
journalArticle
201
Agricultural Water Management
DOI 10.1016/j.agwat.2017.12.032
Qi
Z.
Feng
H.
Zhao
Y.
Zhang
T.
Yang
A.
Zhang
Z.
Spatial distribution and simulation of soil moisture and salinity under mulched drip irrigation combined with tillage in an arid saline irrigation district, northwest China
2018
Scopus
https://www.scopus.com/inward/record.uri?eid=2-s2.0-85040254157&doi=10.1016%2fj.agwat.2017.12.032&partnerID=40&md5=7028a548e39e2cd8723ce8e43f342475
219-231
journalArticle
147
Computers and Electronics in Agriculture
DOI 10.1016/j.compag.2018.01.023
Zheng
C.
Zhu
X.
Yang
X.
Wang
L.
Tu
S.
Xue
Y.
Automatic recognition of lactating sow postures from depth images by deep learning detector
2018
Scopus
https://www.scopus.com/inward/record.uri?eid=2-s2.0-85042304605&doi=10.1016%2fj.compag.2018.01.023&partnerID=40&md5=91e2286baeeba32d7063739fa0db578f
51-63
journalArticle
100
American Journal of Agricultural Economics
DOI 10.1093/ajae/aax087
3
Kosec
K.
Ghebru
H.
Holtemeyer
B.
Mueller
V.
Schmidt
E.
The effect of land access on youth employment and migration decisions: Evidence from rural Ethiopia
2018
Scopus
https://www.scopus.com/inward/record.uri?eid=2-s2.0-85053431351&doi=10.1093%2fajae%2faax087&partnerID=40&md5=d88520bd7e6887ff5f64012568dc1ce3
931-954
journalArticle
169
Biosystems Engineering
DOI 10.1016/j.biosystemseng.2018.02.009
Zhang
Y.
Gao
P.
Ahamed
T.
Development of a rescue system for agricultural machinery operators using machine vision
2018
Scopus
https://www.scopus.com/inward/record.uri?eid=2-s2.0-85042844370&doi=10.1016%2fj.biosystemseng.2018.02.009&partnerID=40&md5=473320e939a761e616652a48f5eb6659
149-164
journalArticle
148
Computers and Electronics in Agriculture
DOI 10.1016/j.compag.2018.02.020
Shine
P.
Scully
T.
Upton
J.
Murphy
M.D.
Multiple linear regression modelling of on-farm direct water and electricity consumption on pasture based dairy farms
2018
Scopus
https://www.scopus.com/inward/record.uri?eid=2-s2.0-85042858341&doi=10.1016%2fj.compag.2018.02.020&partnerID=40&md5=5b4cd78e450b341831ad9ba53c0b9c1f
337-346
journalArticle
10
Water (Switzerland)
DOI 10.3390/w10060728
6
Wu
X.
Lu
G.
Wu
Z.
He
H.
Zhou
J.
Liu
Z.
An integration approach for mapping field capacity of China based on multi-source soil datasets
2018
Scopus
https://www.scopus.com/inward/record.uri?eid=2-s2.0-85048080481&doi=10.3390%2fw10060728&partnerID=40&md5=00b96c166f6b10a9a0c7e3b976b0c1a4
journalArticle
150
Computers and Electronics in Agriculture
DOI 10.1016/j.compag.2018.04.023
Sharif
M.
Khan
M.A.
Iqbal
Z.
Azam
M.F.
Lali
M.I.U.
Javed
M.Y.
Detection and classification of citrus diseases in agriculture based on optimized weighted segmentation and feature selection
2018
Scopus
https://www.scopus.com/inward/record.uri?eid=2-s2.0-85046444985&doi=10.1016%2fj.compag.2018.04.023&partnerID=40&md5=d3f1884a1d1c6bb3347c723928e247f5
220-234
journalArticle
150
Computers and Electronics in Agriculture
DOI 10.1016/j.compag.2018.05.004
Guo
L.
Welch
M.
Dobos
R.
Kwan
P.
Wang
W.
Comparison of grazing behaviour of sheep on pasture with different sward surface heights using an inertial measurement unit sensor
2018
Scopus
https://www.scopus.com/inward/record.uri?eid=2-s2.0-85047263262&doi=10.1016%2fj.compag.2018.05.004&partnerID=40&md5=98452eb49adec9161147750b528db631
394-401
journalArticle
29
Land Degradation and Development
DOI 10.1002/ldr.3019
8
Murthy
K.
Bagchi
S.
Spatial patterns of long-term vegetation greening and browning are consistent across multiple scales: Implications for monitoring land degradation
2018
Scopus
https://www.scopus.com/inward/record.uri?eid=2-s2.0-85051299974&doi=10.1002%2fldr.3019&partnerID=40&md5=f068a8ac4a199fc70bb3ad0e458a6c22
2485-2495
journalArticle
194
Quaternary Science Reviews
DOI 10.1016/j.quascirev.2018.06.026
Gurjazkaite
K.
Routh
J.
Djamali
M.
Vaezi
A.
Poher
Y.
Beni
A.N.
Tavakoli
V.
Kylin
H.
Vegetation history and human-environment interactions through the late Holocene in Konar Sandal, SE Iran
2018
Scopus
https://www.scopus.com/inward/record.uri?eid=2-s2.0-85049877861&doi=10.1016%2fj.quascirev.2018.06.026&partnerID=40&md5=8ce48adde2b6359630bac5d08b32e1f8
143-155
journalArticle
93
Ecological Indicators
DOI 10.1016/j.ecolind.2018.05.069
Whitney
K.
Scudiero
E.
El-Askary
H.M.
Skaggs
T.H.
Allali
M.
Corwin
D.L.
Validating the use of MODIS time series for salinity assessment over agricultural soils in California, USA
2018
Scopus
https://www.scopus.com/inward/record.uri?eid=2-s2.0-85048001300&doi=10.1016%2fj.ecolind.2018.05.069&partnerID=40&md5=918e14a866a5456d870251b4cf48584c
889-898
journalArticle
216
Remote Sensing of Environment
DOI 10.1016/j.rse.2018.06.028
Kellenberger
B.
Marcos
D.
Tuia
D.
Detecting mammals in UAV images: Best practices to address a substantially imbalanced dataset with deep learning
2018
Scopus
https://www.scopus.com/inward/record.uri?eid=2-s2.0-85049529086&doi=10.1016%2fj.rse.2018.06.028&partnerID=40&md5=384f0ba56539b45054d5d38d18f245f3
139-153
journalArticle
174
Biosystems Engineering
DOI 10.1016/j.biosystemseng.2018.08.002
Ramirez
B.C.
Gao
Y.
Hoff
S.J.
Harmon
J.D.
Thermal environment sensor array: Part 1 development and field performance assessment
2018
Scopus
https://www.scopus.com/inward/record.uri?eid=2-s2.0-85052067665&doi=10.1016%2fj.biosystemseng.2018.08.002&partnerID=40&md5=8738eb0a08ab9fbfeee451040941e9f7
329-340
journalArticle
41
Journal of Food Process Engineering
DOI 10.1111/jfpe.12824
6
Patil
R.C.
Gawande
R.R.
Drying characteristics of amla candy in solar tunnel greenhouse dryer
2018
Scopus
https://www.scopus.com/inward/record.uri?eid=2-s2.0-85052450572&doi=10.1111%2fjfpe.12824&partnerID=40&md5=73527c2a3dd5ee0b92a9d3e47359feb8
journalArticle
10
GCB Bioenergy
DOI 10.1111/gcbb.12532
11
Cintas
O.
Berndes
G.
Englund
O.
Cutz
L.
Johnsson
F.
Geospatial supply–demand modeling of biomass residues for co-firing in European coal power plants
2018
Scopus
https://www.scopus.com/inward/record.uri?eid=2-s2.0-85051082689&doi=10.1111%2fgcbb.12532&partnerID=40&md5=13de92a965fc4af6d172226fbf958eeb
786-803
journalArticle
154
Computers and Electronics in Agriculture
DOI 10.1016/j.compag.2018.08.045
Moon
A.
Kim
J.
Zhang
J.
Son
S.W.
Evaluating fidelity of lossy compression on spatiotemporal data from an IoT enabled smart farm
2018
Scopus
https://www.scopus.com/inward/record.uri?eid=2-s2.0-85053779977&doi=10.1016%2fj.compag.2018.08.045&partnerID=40&md5=f1cc0fbb0e6bc23ba183487fa105f9a3
304-313
journalArticle
200
Quaternary Science Reviews
DOI 10.1016/j.quascirev.2018.10.004
Kaniewski
D.
Marriner
N.
Morhange
C.
Rius
D.
Carre
M.-B.
Faivre
S.
Van Campo
E.
Croatia's mid-Late Holocene (5200-3200 BP) coastal vegetation shaped by human societies
2018
Scopus
https://www.scopus.com/inward/record.uri?eid=2-s2.0-85054467230&doi=10.1016%2fj.quascirev.2018.10.004&partnerID=40&md5=56cd61259bcb25a4de70ec3cbfd43537
334-350
journalArticle
95
Ecological Indicators
DOI 10.1016/j.ecolind.2018.05.088
Zhang
H.
Fan
J.
Wang
J.
Cao
W.
Harris
W.
Spatial and temporal variability of grassland yield and its response to climate change and anthropogenic activities on the Tibetan Plateau from 1988 to 2013
2018
Scopus
https://www.scopus.com/inward/record.uri?eid=2-s2.0-85050087674&doi=10.1016%2fj.ecolind.2018.05.088&partnerID=40&md5=e1746f22df76db2cb3b30f3e554bfc9d
141-151
journalArticle
218
Remote Sensing of Environment
DOI 10.1016/j.rse.2018.09.028
Punalekar
S.M.
Verhoef
A.
Quaife
T.L.
Humphries
D.
Bermingham
L.
Reynolds
C.K.
Application of Sentinel-2A data for pasture biomass monitoring using a physically based radiative transfer model
2018
Scopus
https://www.scopus.com/inward/record.uri?eid=2-s2.0-85054316283&doi=10.1016%2fj.rse.2018.09.028&partnerID=40&md5=663b2464b9e1c1c915048fa4946bbdd9
207-220
journalArticle
155
Computers and Electronics in Agriculture
DOI 10.1016/j.compag.2018.10.034
Wang
Y.
Wang
Y.
Citrus ontology development based on the eight-point charter of agriculture
2018
Scopus
https://www.scopus.com/inward/record.uri?eid=2-s2.0-85055751520&doi=10.1016%2fj.compag.2018.10.034&partnerID=40&md5=c88de0a3cda610f5a2ec11f39d67418b
359-370
journalArticle
184
Soil and Tillage Research
DOI 10.1016/j.still.2018.08.003
Brune
P.F.
Ryan
B.J.
Technow
F.
Myers
D.B.
Relating planter downforce and soil strength
2018
Scopus
https://www.scopus.com/inward/record.uri?eid=2-s2.0-85051637310&doi=10.1016%2fj.still.2018.08.003&partnerID=40&md5=7bd01f5af7878b7049587ff6b732121d
243-252
journalArticle
218
Remote Sensing of Environment
DOI 10.1016/j.rse.2018.09.015
Gholizadeh
A.
Žižala
D.
Saberioon
M.
Borůvka
L.
Soil organic carbon and texture retrieving and mapping using proximal, airborne and Sentinel-2 spectral imaging
2018
Scopus
https://www.scopus.com/inward/record.uri?eid=2-s2.0-85053836935&doi=10.1016%2fj.rse.2018.09.015&partnerID=40&md5=26c21702d4fb56fb7d2541b5f23594ef
89-103
journalArticle
International Agricultural Engineering Journal
4
Okinda
C.
Shen
M.
Li
J.
Nyalala
I.
Liu
L.
Lu
M.
Zhang
G.
Detection of an onset of farrowing by classification of crated sow’s activities
2018
Scopus
https://www.scopus.com/inward/record.uri?eid=2-s2.0-85064275025&partnerID=40&md5=876169b8b29af3555a399e26e21a8634
387-395
journalArticle
82
Soil Science Society of America Journal
DOI 10.2136/sssaj2018.05.0190
6
Varvaris
I.
Børgesen
C.D.
Kjærgaard
C.
Iversen
B.V.
Three two-dimensional approaches for simulating the water flow dynamics in a heterogeneous tile-drained agricultural field in Denmark
2018
Scopus
https://www.scopus.com/inward/record.uri?eid=2-s2.0-85059327070&doi=10.2136%2fsssaj2018.05.0190&partnerID=40&md5=652fb306732e08813304a27cadbeb411
1367-1383
journalArticle
156
Computers and Electronics in Agriculture
DOI 10.1016/j.compag.2018.11.028
Junior
C.H.
Oliveira
T.
Yanaze
M.
The adoption stages (Evaluation, Adoption, and Routinisation) of ERP systems with business analytics functionality in the context of farms
2019
Scopus
https://www.scopus.com/inward/record.uri?eid=2-s2.0-85057406708&doi=10.1016%2fj.compag.2018.11.028&partnerID=40&md5=586c8cd73096012ef7cd9f86a5b85253
334-348
journalArticle
220
Remote Sensing of Environment
DOI 10.1016/j.rse.2018.10.031
Griffiths
P.
Nendel
C.
Hostert
P.
Intra-annual reflectance composites from Sentinel-2 and Landsat for national-scale crop and land cover mapping
2019
Scopus
https://www.scopus.com/inward/record.uri?eid=2-s2.0-85056189333&doi=10.1016%2fj.rse.2018.10.031&partnerID=40&md5=20ca31657b1fdc6da4b8755cbf33f6a5
135-151
journalArticle
156
Computers and Electronics in Agriculture
DOI 10.1016/j.compag.2018.12.013
Rajeswari
S.
Suthendran
K.
C5.0: Advanced Decision Tree (ADT) classification model for agricultural data analysis on cloud
2019
Scopus
https://www.scopus.com/inward/record.uri?eid=2-s2.0-85058153070&doi=10.1016%2fj.compag.2018.12.013&partnerID=40&md5=924069d301b5a9ac87b2b79ec067a473
530-539
journalArticle
57
Soil Research
DOI 10.1071/SR18323
3
Raeesi
M.
Zolfaghari
A.A.
Yazdani
M.R.
Gorji
M.
Sabetizade
M.
Prediction of soil organic matter using an inexpensive colour sensor in arid and semiarid areas of Iran
2019
Scopus
https://www.scopus.com/inward/record.uri?eid=2-s2.0-85063603363&doi=10.1071%2fSR18323&partnerID=40&md5=887b53f073ad0e850eae03924246c99c
276-286
journalArticle
28
Ekoloji
107
Guo
T.
Wang
Y.
Big data application issues in the agricultural modernization of china
2019
Scopus
https://www.scopus.com/inward/record.uri?eid=2-s2.0-85063972060&partnerID=40&md5=9242c206ed052dc847c93fc8cf10ce2e
3677-3688
journalArticle
14
International Journal of Design and Nature and Ecodynamics
DOI 10.2495/DNE-V14-N1-30-40
1
Lee
T.-I.
Chou
Y.-H.
Huang
T.-N.
Users' perceptions and attitudes towards edible campus
2019
Scopus
https://www.scopus.com/inward/record.uri?eid=2-s2.0-85061533322&doi=10.2495%2fDNE-V14-N1-30-40&partnerID=40&md5=91f90b3cfa408677d39e5717e062e93c
30-40
journalArticle
62
Transactions of the ASABE
DOI 10.13031/trans.12803
1
Calcante
A.
Brambilla
M.
Bisaglia
C.
Oberti
R.
Estimating the total lubricant oil consumption rate in agricultural tractors
2019
Scopus
https://www.scopus.com/inward/record.uri?eid=2-s2.0-85064158380&doi=10.13031%2ftrans.12803&partnerID=40&md5=e75b268dfd236aaac1eb1391e03ac827
197-204
journalArticle
19
African Journal of Food, Agriculture, Nutrition and Development
DOI 10.18697/AJFAND.84.BLFB1014
1
Kuteesa
A.
Kyotalimye
M.
Documentation and data handling: How can Africa promote record keeping and investment in data management?
2019
Scopus
https://www.scopus.com/inward/record.uri?eid=2-s2.0-85065014873&doi=10.18697%2fAJFAND.84.BLFB1014&partnerID=40&md5=76f6423433c52ee2fd8b083d19f255fe
14171-14189
journalArticle
11
Water (Switzerland)
DOI 10.3390/w11081564
8
Karnieli
A.
Shtein
A.
Panov
N.
Weisbrod
N.
Tal
A.
Was drought really the trigger behind the Syrian Civil War in 2011?
2019
Scopus
https://www.scopus.com/inward/record.uri?eid=2-s2.0-85070257972&doi=10.3390%2fw11081564&partnerID=40&md5=3e736e3aa2ae3a00f5a23667d411261e
journalArticle
62
Transactions of the ASABE
DOI 10.13031/trans.13170
2
Luck
J.D.
Shearer
S.A.
Sama
M.P.
Development and preliminary evaluation of an integrated individual nozzle direct injection and carrier flow rate control system for pesticide applications
2019
Scopus
https://www.scopus.com/inward/record.uri?eid=2-s2.0-85069490426&doi=10.13031%2ftrans.13170&partnerID=40&md5=4bb6d574fd71a5ec5cabba7036fba398
505-514
journalArticle
3
Phytobiomes Journal
DOI 10.1094/PBIOMES-01-19-0008-R
1
Kusstatscher
P.
Cernava
T.
Harms
K.
Maier
J.
Eigner
H.
Berg
G.
Zachow
C.
Disease incidence in sugar beet fields is correlated with microbial diversity and distinct biological markers
2019
Scopus
https://www.scopus.com/inward/record.uri?eid=2-s2.0-85070445551&doi=10.1094%2fPBIOMES-01-19-0008-R&partnerID=40&md5=a3839eeab2fdeacb3c436c52361e360c
22-30
journalArticle
58
INMATEH - Agricultural Engineering
DOI 10.35633/INMATEH-58-11
2
Liu
H.
Zhang
K.
Liu
X.
Song
Z.
A design reuse method for agricultural machinery cad model with light propagation simulation
2019
Scopus
https://www.scopus.com/inward/record.uri?eid=2-s2.0-85077293574&doi=10.35633%2fINMATEH-58-11&partnerID=40&md5=e18a5cb2f1c49271080dd16c67a60967
105-114
journalArticle
180
Biosystems Engineering
DOI 10.1016/j.biosystemseng.2019.01.019
Augustin
K.
Kuhwald
M.
Brunotte
J.
Duttmann
R.
FiTraM: A model for automated spatial analyses of wheel load, soil stress and wheel pass frequency at field scale
2019
Scopus
https://www.scopus.com/inward/record.uri?eid=2-s2.0-85061452456&doi=10.1016%2fj.biosystemseng.2019.01.019&partnerID=40&md5=efb2dcd3caa543f1a21317c39c37c461
108-120
journalArticle
30
Land Degradation and Development
DOI 10.1002/ldr.3271
7
Basupi
L.V.
Dougill
A.J.
Quinn
C.H.
Institutional challenges in pastoral landscape management: Towards sustainable land management in Ngamiland, Botswana
2019
Scopus
https://www.scopus.com/inward/record.uri?eid=2-s2.0-85062361905&doi=10.1002%2fldr.3271&partnerID=40&md5=217e06dd94c556360415f71fc1066622
839-851
journalArticle
213
Agricultural Water Management
DOI 10.1016/j.agwat.2018.10.032
Rahman
M.M.
Zhang
W.
Wang
K.
Assessment on surface energy imbalance and energy partitioning using ground and satellite data over a semi-arid agricultural region in north China
2019
Scopus
https://www.scopus.com/inward/record.uri?eid=2-s2.0-85055635353&doi=10.1016%2fj.agwat.2018.10.032&partnerID=40&md5=0015a26d9b793ef80b363a9c2e19a622
245-259
journalArticle
234
Field Crops Research
DOI 10.1016/j.fcr.2019.02.005
Li
Y.
Guan
K.
Yu
A.
Peng
B.
Zhao
L.
Li
B.
Peng
J.
Toward building a transparent statistical model for improving crop yield prediction: Modeling rainfed corn in the U.S
2019
Scopus
https://www.scopus.com/inward/record.uri?eid=2-s2.0-85061643850&doi=10.1016%2fj.fcr.2019.02.005&partnerID=40&md5=aaaa104e9cd546ea0178c47bc63a7c23
55-65
journalArticle
225
Remote Sensing of Environment
DOI 10.1016/j.rse.2018.02.010
González-Zamora
Á.
Sánchez
N.
Pablos
M.
Martínez-Fernández
J.
CCI soil moisture assessment with SMOS soil moisture and in situ data under different environmental conditions and spatial scales in Spain
2019
Scopus
https://www.scopus.com/inward/record.uri?eid=2-s2.0-85041917566&doi=10.1016%2fj.rse.2018.02.010&partnerID=40&md5=b9140f11fb0c6270d7c6892582640d70
469-482
journalArticle
17
Journal of Culinary Science and Technology
DOI 10.1080/15428052.2018.1428707
3
Okumus
B.
Sonmez
S.
An analysis on current food regulations for and inspection challenges of street food: Case of Florida
2019
Scopus
https://www.scopus.com/inward/record.uri?eid=2-s2.0-85042931894&doi=10.1080%2f15428052.2018.1428707&partnerID=40&md5=b8b7834d66be5ed112defe8a848343d9
209-223
journalArticle
161
Computers and Electronics in Agriculture
DOI 10.1016/j.compag.2019.01.044
Cruz
S.M.S.D.
Nascimento
J.A.P.D.
Towards integration of data-driven agronomic experiments with data provenance
2019
Scopus
https://www.scopus.com/inward/record.uri?eid=2-s2.0-85062153231&doi=10.1016%2fj.compag.2019.01.044&partnerID=40&md5=deaf94d01b2e513e0a57576ebf29988a
14-28
journalArticle
161
Computers and Electronics in Agriculture
DOI 10.1016/j.compag.2018.08.037
Zehner
N.
Niederhauser
J.J.
Schick
M.
Umstatter
C.
Development and validation of a predictive model for calving time based on sensor measurements of ingestive behavior in dairy cows
2019
Scopus
https://www.scopus.com/inward/record.uri?eid=2-s2.0-85052944213&doi=10.1016%2fj.compag.2018.08.037&partnerID=40&md5=fc3e66b0bc33518d20f98a8238b25e8c
62-71
journalArticle
162
Computers and Electronics in Agriculture
DOI 10.1016/j.compag.2019.05.013
Carpentier
L.
Vranken
E.
Berckmans
D.
Paeshuyse
J.
Norton
T.
Development of sound-based poultry health monitoring tool for automated sneeze detection
2019
Scopus
https://www.scopus.com/inward/record.uri?eid=2-s2.0-85065313661&doi=10.1016%2fj.compag.2019.05.013&partnerID=40&md5=2ab7168fb778e2efe93c62b62e97d7a4
573-581
journalArticle
221
Agricultural Water Management
DOI 10.1016/j.agwat.2019.03.046
Timlin
D.
Kang
K.
Evaluation of the agricultural policy environmental extender (APEX) for the Chesapeake Bay watershed
2019
Scopus
https://www.scopus.com/inward/record.uri?eid=2-s2.0-85065982038&doi=10.1016%2fj.agwat.2019.03.046&partnerID=40&md5=31c9e6fad3a5707248acb1e06414f727
477-485
journalArticle
184
Biosystems Engineering
DOI 10.1016/j.biosystemseng.2019.06.001
Utamima
A.
Reiners
T.
Ansaripoor
A.H.
Optimisation of agricultural routing planning in field logistics with Evolutionary Hybrid Neighbourhood Search
2019
Scopus
https://www.scopus.com/inward/record.uri?eid=2-s2.0-85068032055&doi=10.1016%2fj.biosystemseng.2019.06.001&partnerID=40&md5=561f7799267eaa44be87bdab04c38083
166-180
journalArticle
163
Computers and Electronics in Agriculture
DOI 10.1016/j.compag.2019.05.049
Tian
M.
Guo
H.
Chen
H.
Wang
Q.
Long
C.
Ma
Y.
Automated pig counting using deep learning
2019
Scopus
https://www.scopus.com/inward/record.uri?eid=2-s2.0-85067302123&doi=10.1016%2fj.compag.2019.05.049&partnerID=40&md5=c42aa19c9a7110c63af4996c90651a84
journalArticle
185
Biosystems Engineering
DOI 10.1016/j.biosystemseng.2018.06.005
Sun
C.
Nakashima
H.
Shimizu
H.
Miyasaka
J.
Ohdoi
K.
Physics engine application to overturning dynamics analysis on banks and uniform slopes for an agricultural tractor with a rollover protective structure
2019
Scopus
https://www.scopus.com/inward/record.uri?eid=2-s2.0-85049008448&doi=10.1016%2fj.biosystemseng.2018.06.005&partnerID=40&md5=a5b6f9665dcdc5cf53905fef61851245
150-160
journalArticle
192
Soil and Tillage Research
DOI 10.1016/j.still.2019.04.012
Liu
G.
Dabney
S.M.
Yoder
D.C.
Wells
R.R.
Vieira
D.A.N.
Modeling land management effects on the size distribution of eroded sediment
2019
Scopus
https://www.scopus.com/inward/record.uri?eid=2-s2.0-85065705674&doi=10.1016%2fj.still.2019.04.012&partnerID=40&md5=03f9ba6409ac6c113e4bfcb7543f4e21
121-133
journalArticle
232
Remote Sensing of Environment
DOI 10.1016/j.rse.2019.111285
Ge
Y.
Hu
S.
Ren
Z.
Jia
Y.
Wang
J.
Liu
M.
Zhang
D.
Zhao
W.
Luo
Y.
Fu
Y.
Bai
H.
Chen
Y.
Mapping annual land use changes in China's poverty-stricken areas from 2013 to 2018
2019
Scopus
https://www.scopus.com/inward/record.uri?eid=2-s2.0-85068560327&doi=10.1016%2fj.rse.2019.111285&partnerID=40&md5=cdd6503bf5c910b3ca75f6d9de77d523
journalArticle
18
Ethnobotany Research and Applications
DOI 10.32859/era.18.27.1-10
Lokho
K.
Narasimhan
D.
Bamboo-the ‘timber’ of Mao-Naga community
2019
Scopus
https://www.scopus.com/inward/record.uri?eid=2-s2.0-85100190304&doi=10.32859%2fera.18.27.1-10&partnerID=40&md5=313e04b449f091422b13a127e99b05c7
1-10
journalArticle
12
Avian Biology Research
DOI 10.1177/1758155919856770
4
Guilherme
J.L.
Rocha
A.
Lousa
H.
Alves
J.A.
Are artificial agricultural ponds a suitable alternative nesting habitat for the Little Ringed Plover?
2019
Scopus
https://www.scopus.com/inward/record.uri?eid=2-s2.0-85068323067&doi=10.1177%2f1758155919856770&partnerID=40&md5=c24f061d4257ba09804c8e63de73c050
133-138
journalArticle
165
Computers and Electronics in Agriculture
DOI 10.1016/j.compag.2019.104973
Kounalakis
T.
Triantafyllidis
G.A.
Nalpantidis
L.
Deep learning-based visual recognition of rumex for robotic precision farming
2019
Scopus
https://www.scopus.com/inward/record.uri?eid=2-s2.0-85071398904&doi=10.1016%2fj.compag.2019.104973&partnerID=40&md5=5d779e33dadc915f0f6b3f841eaa227a
journalArticle
352
Geoderma
DOI 10.1016/j.geoderma.2017.10.049
Piikki
K.
Söderström
M.
Digital soil mapping of arable land in Sweden – Validation of performance at multiple scales
2019
Scopus
https://www.scopus.com/inward/record.uri?eid=2-s2.0-85032943849&doi=10.1016%2fj.geoderma.2017.10.049&partnerID=40&md5=effccb826cc502baf968e9f11d03b505
342-350
journalArticle
353
Geoderma
DOI 10.1016/j.geoderma.2019.07.017
Chandrasekhar
P.
Kreiselmeier
J.
Schwen
A.
Weninger
T.
Julich
S.
Feger
K.-H.
Schwärzel
K.
Modeling the evolution of soil structural pore space in agricultural soils following tillage
2019
Scopus
https://www.scopus.com/inward/record.uri?eid=2-s2.0-85068973089&doi=10.1016%2fj.geoderma.2019.07.017&partnerID=40&md5=40efad84ab64ea9ec08d15e09fb57381
401-414
journalArticle
50
Agricultural Economics (United Kingdom)
DOI 10.1111/agec.12517
6
Kaila
H.
Tarp
F.
Can the Internet improve agricultural production? Evidence from Viet Nam
2019
Scopus
https://www.scopus.com/inward/record.uri?eid=2-s2.0-85074784568&doi=10.1111%2fagec.12517&partnerID=40&md5=e2ccf379d521fe60fceeeb7b0190d736
675-691
journalArticle
90-91
NJAS - Wageningen Journal of Life Sciences
DOI 10.1016/j.njas.2019.02.003
Regan
Á.
‘Smart farming’ in Ireland: A risk perception study with key governance actors
2019
Scopus
https://www.scopus.com/inward/record.uri?eid=2-s2.0-85061452703&doi=10.1016%2fj.njas.2019.02.003&partnerID=40&md5=ef7ba022e6318d0b0350bd9df59dad46
journalArticle
167
Computers and Electronics in Agriculture
DOI 10.1016/j.compag.2019.105042
Woszczyk
A.
Szerement
J.
Lewandowski
A.
Kafarski
M.
Szypłowska
A.
Wilczek
A.
Skierucha
W.
An open-ended probe with an antenna for the measurement of the water content in the soil
2019
Scopus
https://www.scopus.com/inward/record.uri?eid=2-s2.0-85073462913&doi=10.1016%2fj.compag.2019.105042&partnerID=40&md5=fdda337c219d45127ef881c99bbec84e
journalArticle
28
International Agricultural Engineering Journal
4
Zhang
H.
Shen
M.
Lu
M.
Okinda
C.
Zhang
S.
Ding
D.
Wang
J.
Automatic recognition of sheep chewing sounds based on sparse representation classification
2019
Scopus
https://www.scopus.com/inward/record.uri?eid=2-s2.0-85081977178&partnerID=40&md5=06de0ebec9b8f10a3d27e66955236362
411-421
journalArticle
11
Agris On-line Papers in Economics and Informatics
DOI 10.7160/aol.2019.110410
4
Sabou
J.P.
Cihelka
P.
Ulman
M.
Klimešová
D.
Measuring the similarities of twitter hashtags for agriculture in the Czech Language
2019
Scopus
https://www.scopus.com/inward/record.uri?eid=2-s2.0-85078782815&doi=10.7160%2faol.2019.110410&partnerID=40&md5=6529724c4608f11cf06a76c014328db9
105-112
journalArticle
29
Animal Welfare
DOI 10.7120/09627286.29.1.069
1
Reese
L.
Ladwig-Wiegard
M.
von Fersen
L.
Haase
G.
Will
H.
Merle
R.
Encke
D.
Maegdefrau
H.
Baumgartner
K.
Thöne-Reineke
C.
Deflighting zoo birds and its welfare considerations
2020
Scopus
https://www.scopus.com/inward/record.uri?eid=2-s2.0-85078818345&doi=10.7120%2f09627286.29.1.069&partnerID=40&md5=4f3756983f6a1377936d2c60081cc513
69-80
journalArticle
11
Ecosphere
DOI 10.1002/ecs2.3004
1
Lee
M.S.
Comas
J.
Stefanescu
C.
Albajes
R.
The Catalan butterfly monitoring scheme has the capacity to detect effects of modifying agricultural practices
2020
Scopus
https://www.scopus.com/inward/record.uri?eid=2-s2.0-85079125453&doi=10.1002%2fecs2.3004&partnerID=40&md5=5dcd71a7f9d2206b3f7fb125a394355a
journalArticle
12
Water (Switzerland)
DOI 10.3390/w12010250
1
Salem
A.
Dezso
J.
El-Rawy
M.
Lóczy
D.
Hydrological modeling to assess the efficiency of groundwater replenishment through natural reservoirs in the Hungarian drava river floodplain
2020
Scopus
https://www.scopus.com/inward/record.uri?eid=2-s2.0-85079489477&doi=10.3390%2fw12010250&partnerID=40&md5=b98ced369bdcde44152ec2928568f6e4
journalArticle
12
Water (Switzerland)
DOI 10.3390/w12010244
1
Vito
L.D.
Fairbrother
M.
Russel
D.
Implementing the water framework directive and tackling diffuse pollution from agriculture: Lessons from England and Scotland
2020
Scopus
https://www.scopus.com/inward/record.uri?eid=2-s2.0-85079490443&doi=10.3390%2fw12010244&partnerID=40&md5=38efceabf5791a5f06b44738ead90845
journalArticle
16
International Journal of Agricultural Resources, Governance and Ecology
DOI 10.1504/IJARGE.2020.107067
1
Newar
S.
Saini
G.K.
Singh
V.
Agro-tech ontology: A solution for accelerating agricultural productivity in the state of Rajasthan, India
2020
Scopus
https://www.scopus.com/inward/record.uri?eid=2-s2.0-85084476592&doi=10.1504%2fIJARGE.2020.107067&partnerID=40&md5=5ec018a3f9809a20d1de39ab972f3daa
2-22
journalArticle
53
Polish Journal of Soil Science
DOI 10.17951/pjss/2020.53.1.125
1
Ljusa
M.
Custovic
H.
Hodzic
S.
The impact of climate change on soil water balance and agricultural production sustainability in mediterranean part of bosnia and herzegovina
2020
Scopus
https://www.scopus.com/inward/record.uri?eid=2-s2.0-85087852434&doi=10.17951%2fpjss%2f2020.53.1.125&partnerID=40&md5=449283e0ade90c18505f48f9739ab33d
125-135
journalArticle
63
Transactions of the ASABE
DOI 10.13031/trans.13568
1
Padmaja
R.
Kavitha
K.
Pramanik
S.
Duche
V.D.
Singh
Y.U.
Whitbread
A.M.
Singh
R.
Garg
K.K.
Leder
S.
Gender transformative impacts from watershed interventions: Insights from a mixed-methods study in the Bundelkhand region of India
2020
Scopus
https://www.scopus.com/inward/record.uri?eid=2-s2.0-85084649077&doi=10.13031%2ftrans.13568&partnerID=40&md5=af9638febf3ffb84e57954166ec0bf37
153-163
journalArticle
24
Journal of Agricultural Extension
DOI 10.4314/jae.v24i4.10
4
Ifeanyi-obi
C.C.
Ibiso
H.D.
Extension Agents Perception of Open Data Usage in Agricultural Communication in Abia State
2020
Scopus
https://www.scopus.com/inward/record.uri?eid=2-s2.0-85102782366&doi=10.4314%2fjae.v24i4.10&partnerID=40&md5=bf225fad07ddf720b8776bc2cabc3419
91-99
journalArticle
280
Agricultural and Forest Meteorology
DOI 10.1016/j.agrformet.2019.107812
Cowan
N.
Levy
P.
Maire
J.
Coyle
M.
Leeson
S.R.
Famulari
D.
Carozzi
M.
Nemitz
E.
Skiba
U.
An evaluation of four years of nitrous oxide fluxes after application of ammonium nitrate and urea fertilisers measured using the eddy covariance method
2020
Scopus
https://www.scopus.com/inward/record.uri?eid=2-s2.0-85073610839&doi=10.1016%2fj.agrformet.2019.107812&partnerID=40&md5=926ad42f5b8cbe1cd0a71d12bfe8d1e1
journalArticle
1
Vegetation Classification and Survey
DOI 10.3897/VCS/2020/61419
Bürger
J.
Metcalfe
H.
Redwitz
C.
Cirujeda
A.
Fogliatto
S.
Fried
G.
Dostatny
D.F.
Gerowitt
B.
Glemnitz
M.
González-Andújar
J.L.
Plaza
E.H.
Izquierdo
J.
Kolářová
M.
Ņečajeva
J.
Petit
S.
Pinke
G.
Schumacher
M.
Ulber
L.
Vidotto
F.
Arable Weeds and Management in Europe
2020
Scopus
https://www.scopus.com/inward/record.uri?eid=2-s2.0-85127280853&doi=10.3897%2fVCS%2f2020%2f61419&partnerID=40&md5=08669d8422ace7f22958fd6f3378ea11
169-170
journalArticle
71
Journal of Agricultural Economics
DOI 10.1111/1477-9552.12338
1
Rada
N.
Liefert
W.
Liefert
O.
Evaluating Agricultural Productivity and Policy in Russia
2020
Scopus
https://www.scopus.com/inward/record.uri?eid=2-s2.0-85067429140&doi=10.1111%2f1477-9552.12338&partnerID=40&md5=5ecde08e96a5b8ad3a1e75805c428a09
96-117
journalArticle
43
Ecography
DOI 10.1111/ecog.04722
2
Cramer
K.L.
O'Dea
A.
Leonard-Pingel
J.S.
Norris
R.D.
Millennial-scale change in the structure of a Caribbean reef ecosystem and the role of human and natural disturbance
2020
Scopus
https://www.scopus.com/inward/record.uri?eid=2-s2.0-85075085174&doi=10.1111%2fecog.04722&partnerID=40&md5=58e62c2a948aaa50d0eaaa09db964dbd
283-293
journalArticle
229
Agricultural Water Management
DOI 10.1016/j.agwat.2019.105938
Mhawej
M.
Caiserman
A.
Nasrallah
A.
Dawi
A.
Bachour
R.
Faour
G.
Automated evapotranspiration retrieval model with missing soil-related datasets: The proposal of SEBALI
2020
Scopus
https://www.scopus.com/inward/record.uri?eid=2-s2.0-85076117241&doi=10.1016%2fj.agwat.2019.105938&partnerID=40&md5=102d9dfd2ede2f6ecee6318c63c0d143
journalArticle
362
Geoderma
DOI 10.1016/j.geoderma.2019.114012
M. Sanches
G.
S. Graziano Magalhães
P.
dos Santos Luciano
A.C.
A. Camargo
L.
C.J. Franco
H.
Comprehensive assessment of spatial soil variability related to topographic parameters in sugarcane fields
2020
Scopus
https://www.scopus.com/inward/record.uri?eid=2-s2.0-85076786093&doi=10.1016%2fj.geoderma.2019.114012&partnerID=40&md5=3c6715bfb220a4efb3740f58fa4ec979
journalArticle
170
Computers and Electronics in Agriculture
DOI 10.1016/j.compag.2020.105279
Aghelpour
P.
Bahrami-Pichaghchi
H.
Kisi
O.
Comparison of three different bio-inspired algorithms to improve ability of neuro fuzzy approach in prediction of agricultural drought, based on three different indexes
2020
Scopus
https://www.scopus.com/inward/record.uri?eid=2-s2.0-85079044380&doi=10.1016%2fj.compag.2020.105279&partnerID=40&md5=3d8a5ac1043ee6e8712d4e4758b697ed
journalArticle
239
Remote Sensing of Environment
DOI 10.1016/j.rse.2020.111671
Mulligan
M.
van Soesbergen
A.
Hole
D.G.
Brooks
T.M.
Burke
S.
Hutton
J.
Mapping nature's contribution to SDG 6 and implications for other SDGs at policy relevant scales
2020
Scopus
https://www.scopus.com/inward/record.uri?eid=2-s2.0-85078211758&doi=10.1016%2fj.rse.2020.111671&partnerID=40&md5=bd8fec66396f1caf78edcb5614a4273b
journalArticle
192
Biosystems Engineering
DOI 10.1016/j.biosystemseng.2020.02.001
Hu
H.
Dai
B.
Shen
W.
Wei
X.
Sun
J.
Li
R.
Zhang
Y.
Cow identification based on fusion of deep parts features
2020
Scopus
https://www.scopus.com/inward/record.uri?eid=2-s2.0-85079633492&doi=10.1016%2fj.biosystemseng.2020.02.001&partnerID=40&md5=24319c709b6fa245f7bd04204238d9f0
245-256
journalArticle
94
Land Use Policy
DOI 10.1016/j.landusepol.2020.104507
Rahman
S.
Anik
A.R.
Productivity and efficiency impact of climate change and agroecology on Bangladesh agriculture
2020
Scopus
https://www.scopus.com/inward/record.uri?eid=2-s2.0-85079163540&doi=10.1016%2fj.landusepol.2020.104507&partnerID=40&md5=fd6a01734d9d87b383782c06719f3e24
journalArticle
171
Computers and Electronics in Agriculture
DOI 10.1016/j.compag.2020.105300
Xu
B.
Wang
W.
Falzon
G.
Kwan
P.
Guo
L.
Chen
G.
Tait
A.
Schneider
D.
Automated cattle counting using Mask R-CNN in quadcopter vision system
2020
Scopus
https://www.scopus.com/inward/record.uri?eid=2-s2.0-85080029752&doi=10.1016%2fj.compag.2020.105300&partnerID=40&md5=3ac81821b1ce0d17accc6697e00baba4
journalArticle
12
Water (Switzerland)
DOI 10.3390/W12041060
4
Gracia-de-Rentería
P.
Philippidis
G.
Ferrer-Pérez
H.
Sanjuán
A.I.
Living at the water's edge: A world-wide econometric panel estimation of arable water footprint drivers
2020
Scopus
https://www.scopus.com/inward/record.uri?eid=2-s2.0-85086804108&doi=10.3390%2fW12041060&partnerID=40&md5=21f525c5aeff7075044e930cba345f07
journalArticle
173
Computers and Electronics in Agriculture
DOI 10.1016/j.compag.2020.105378
Barth
R.
Hemming
J.
Van Henten
E.J.
Optimising realism of synthetic images using cycle generative adversarial networks for improved part segmentation
2020
Scopus
https://www.scopus.com/inward/record.uri?eid=2-s2.0-85083496168&doi=10.1016%2fj.compag.2020.105378&partnerID=40&md5=041e39c4ab7e76e9adcfd299f2e3a3ab
journalArticle
11
Forests
DOI 10.3390/F11050595
5
Kokkoris
I.P.
Mallinis
G.
Bekri
E.S.
Vlami
V.
Zogaris
S.
Chrysafis
I.
Mitsopoulos
I.
Dimopoulos
P.
National set of MAES indicators in Greece: Ecosystem services and management implications
2020
Scopus
https://www.scopus.com/inward/record.uri?eid=2-s2.0-85086500614&doi=10.3390%2fF11050595&partnerID=40&md5=ad22798c9c8819be35bd82f52aa639e1
journalArticle
194
Biosystems Engineering
DOI 10.1016/j.biosystemseng.2020.03.011
Liu
D.
He
D.
Norton
T.
Automatic estimation of dairy cattle body condition score from depth image using ensemble model
2020
Scopus
https://www.scopus.com/inward/record.uri?eid=2-s2.0-85082649244&doi=10.1016%2fj.biosystemseng.2020.03.011&partnerID=40&md5=79929ed01e4283280f7ed834d0ba16ef
16-27
journalArticle
173
Computers and Electronics in Agriculture
DOI 10.1016/j.compag.2020.105448
Godara
S.
Toshniwal
D.
Sequential pattern mining combined multi-criteria decision-making for farmers’ queries characterization
2020
Scopus
https://www.scopus.com/inward/record.uri?eid=2-s2.0-85083779084&doi=10.1016%2fj.compag.2020.105448&partnerID=40&md5=60458db0a6433dc5a5d1b59f4a9e7b8c
journalArticle
79
Environmental Earth Sciences
DOI 10.1007/s12665-020-08998-1
11
van Rooyen
J.D.
Watson
A.P.
Miller
J.A.
Combining quantity and quality controls to determine groundwater vulnerability to depletion and deterioration throughout South Africa
2020
Scopus
https://www.scopus.com/inward/record.uri?eid=2-s2.0-85085273456&doi=10.1007%2fs12665-020-08998-1&partnerID=40&md5=ab7fd71e246979882f803e2bd661448d
journalArticle
12
Water (Switzerland)
DOI 10.3390/W12061531
6
Stefanidis
K.
Christopoulou
A.
Poulos
S.
Dassenakis
E.
Dimitriou
E.
Nitrogen and phosphorus loads in Greek Rivers: Implications for management in compliance with the water framework directive
2020
Scopus
https://www.scopus.com/inward/record.uri?eid=2-s2.0-85086708881&doi=10.3390%2fW12061531&partnerID=40&md5=d503ec701165743ab610f3fb356a4fbb
journalArticle
94
Food Policy
DOI 10.1016/j.foodpol.2020.101840
Ayerst
S.
Brandt
L.
Restuccia
D.
Market constraints, misallocation, and productivity in Vietnam agriculture
2020
Scopus
https://www.scopus.com/inward/record.uri?eid=2-s2.0-85079652675&doi=10.1016%2fj.foodpol.2020.101840&partnerID=40&md5=3f9dc24976bc6f650c8d1acc918c7fc8
journalArticle
146
Journal of Irrigation and Drainage Engineering
DOI 10.1061/(ASCE)IR.1943-4774.0001482
7
Gaj
N.
Madramootoo
C.A.
Effects of Perforation Geometry on Pipe Drainage in Agricultural Lands
2020
Scopus
https://www.scopus.com/inward/record.uri?eid=2-s2.0-85084675784&doi=10.1061%2f%28ASCE%29IR.1943-4774.0001482&partnerID=40&md5=5f762f65accee8784da2f4e496d9cefb
journalArticle
44
Ecosystem Services
DOI 10.1016/j.ecoser.2020.101137
Gutiérrez-Arellano
C.
Mulligan
M.
Small-sized protected areas contribute more per unit area to tropical crop pollination than large protected areas
2020
Scopus
https://www.scopus.com/inward/record.uri?eid=2-s2.0-85086713828&doi=10.1016%2fj.ecoser.2020.101137&partnerID=40&md5=78cc1324a6841df21e713a4ef18f8e2f
journalArticle
102
American Journal of Agricultural Economics
DOI 10.1002/ajae.12084
4
Cardwell
R.
Ghazalian
P.L.
The Effects of Untying International Food Assistance: The Case of Canada
2020
Scopus
https://www.scopus.com/inward/record.uri?eid=2-s2.0-85083060547&doi=10.1002%2fajae.12084&partnerID=40&md5=f6d48861ac9c854387e0f3643bfbc1b7
1056-1078
journalArticle
175
Computers and Electronics in Agriculture
DOI 10.1016/j.compag.2020.105593
Espejo-Garcia
B.
Mylonas
N.
Athanasakos
L.
Fountas
S.
Improving weeds identification with a repository of agricultural pre-trained deep neural networks
2020
Scopus
https://www.scopus.com/inward/record.uri?eid=2-s2.0-85086985586&doi=10.1016%2fj.compag.2020.105593&partnerID=40&md5=f6de31a006adc2871dbf42f1d0e527b6
journalArticle
196
Biosystems Engineering
DOI 10.1016/j.biosystemseng.2020.05.022
Azizi
A.
Abbaspour-Gilandeh
Y.
Vannier
E.
Dusséaux
R.
Mseri-Gundoshmian
T.
Moghaddam
H.A.
Semantic segmentation: A modern approach for identifying soil clods in precision farming
2020
Scopus
https://www.scopus.com/inward/record.uri?eid=2-s2.0-85086990088&doi=10.1016%2fj.biosystemseng.2020.05.022&partnerID=40&md5=bc05eb447cf5b8c76851cabe540f96da
172-182
journalArticle
373
Geoderma
DOI 10.1016/j.geoderma.2020.114447
Schulze
R.E.
Schütte
S.
Mapping soil organic carbon at a terrain unit resolution across South Africa
2020
Scopus
https://www.scopus.com/inward/record.uri?eid=2-s2.0-85084949621&doi=10.1016%2fj.geoderma.2020.114447&partnerID=40&md5=7ef540a53daa3758596b6a30c2a78b8a
journalArticle
176
Computers and Electronics in Agriculture
DOI 10.1016/j.compag.2020.105652
Zhang
P.
Yang
L.
Li
D.
EfficientNet-B4-Ranger: A novel method for greenhouse cucumber disease recognition under natural complex environment
2020
Scopus
https://www.scopus.com/inward/record.uri?eid=2-s2.0-85088667394&doi=10.1016%2fj.compag.2020.105652&partnerID=40&md5=310ab8fb1313beda4de0a0d544eb855b
journalArticle
176
Computers and Electronics in Agriculture
DOI 10.1016/j.compag.2020.105473
Serrano-Notivoli
R.
Tomás-Burguera
M.
Martí
A.
Beguería
S.
An integrated package to evaluate climatic suitability for agriculture
2020
Scopus
https://www.scopus.com/inward/record.uri?eid=2-s2.0-85088914039&doi=10.1016%2fj.compag.2020.105473&partnerID=40&md5=e6f045a06df51ee8663cd3804b4b0a4d
journalArticle
15
PLoS ONE
DOI 10.1371/journal.pone.0238781
9 September
Illius
A.W.
Lievaart-Peterson
K.
McNeilly
T.N.
Savill
N.J.
Epidemiology and control of maedi-visna virus: Curing the flock
2020
Scopus
https://www.scopus.com/inward/record.uri?eid=2-s2.0-85090818270&doi=10.1371%2fjournal.pone.0238781&partnerID=40&md5=32387777c93d6123d7158321f7c693f3
journalArticle
117
Ecological Indicators
DOI 10.1016/j.ecolind.2020.106551
Campos
P.
Álvarez
A.
Oviedo
J.L.
Mesa
B.
Caparrós
A.
Ovando
P.
Environmental incomes: Refined standard and extended accounts applied to cork oak open woodlands in Andalusia, Spain
2020
Scopus
https://www.scopus.com/inward/record.uri?eid=2-s2.0-85085523786&doi=10.1016%2fj.ecolind.2020.106551&partnerID=40&md5=aac1770e738494d1ad2cf29c7e232ab4
journalArticle
248
Remote Sensing of Environment
DOI 10.1016/j.rse.2020.111960
Diao
C.
Remote sensing phenological monitoring framework to characterize corn and soybean physiological growing stages
2020
Scopus
https://www.scopus.com/inward/record.uri?eid=2-s2.0-85087198322&doi=10.1016%2fj.rse.2020.111960&partnerID=40&md5=b205d3d131df16a9c5482e2427ae9c7c
journalArticle
198
Biosystems Engineering
DOI 10.1016/j.biosystemseng.2020.07.019
Achour
B.
Belkadi
M.
Filali
I.
Laghrouche
M.
Lahdir
M.
Image analysis for individual identification and feeding behaviour monitoring of dairy cows based on Convolutional Neural Networks (CNN)
2020
Scopus
https://www.scopus.com/inward/record.uri?eid=2-s2.0-85089190213&doi=10.1016%2fj.biosystemseng.2020.07.019&partnerID=40&md5=e6d6aa8a5c4691a42f4119db76bab60d
31-49
journalArticle
177
Computers and Electronics in Agriculture
DOI 10.1016/j.compag.2020.105627
Fuentes
A.
Yoon
S.
Park
J.
Park
D.S.
Deep learning-based hierarchical cattle behavior recognition with spatio-temporal information
2020
Scopus
https://www.scopus.com/inward/record.uri?eid=2-s2.0-85089937288&doi=10.1016%2fj.compag.2020.105627&partnerID=40&md5=fafbf6e3e2fcc8ef6a28b0506f316571
journalArticle
177
Computers and Electronics in Agriculture
DOI 10.1016/j.compag.2020.105661
Barman
U.
Choudhury
R.D.
Sahu
D.
Barman
G.G.
Comparison of convolution neural networks for smartphone image based real time classification of citrus leaf disease
2020
Scopus
https://www.scopus.com/inward/record.uri?eid=2-s2.0-85089242157&doi=10.1016%2fj.compag.2020.105661&partnerID=40&md5=c53b44ae7c58f47c5250d83ab59a90b5
journalArticle
198
Biosystems Engineering
DOI 10.1016/j.biosystemseng.2020.08.007
Nilsson
R.S.
Zhou
K.
Method and bench-marking framework for coverage path planning in arable farming
2020
Scopus
https://www.scopus.com/inward/record.uri?eid=2-s2.0-85090183756&doi=10.1016%2fj.biosystemseng.2020.08.007&partnerID=40&md5=126333bc21ad530ed2cf0f2840cd4470
248-265
journalArticle
12
Water (Switzerland)
DOI 10.3390/w12102690
10
Sternberg
T.
McCarthy
C.
Hoshino
B.
Does china’s belt and road initiative threaten food security in central asia?
2020
Scopus
https://www.scopus.com/inward/record.uri?eid=2-s2.0-85092738487&doi=10.3390%2fw12102690&partnerID=40&md5=f1644080b429a2c8d711da2f7bf909da
journalArticle
12
Water (Switzerland)
DOI 10.3390/w12102813
10
Cruz
M.G.
Hernandez
E.A.
Uddameri
V.
Climatic influences on agricultural drought risks using semiparametric kernel density estimation
2020
Scopus
https://www.scopus.com/inward/record.uri?eid=2-s2.0-85092727976&doi=10.3390%2fw12102813&partnerID=40&md5=9c91b37058020e4a5e94069d01575575
journalArticle
185
Agricultural Systems
DOI 10.1016/j.agsy.2020.102934
Gonzalez-Ollauri
A.
Thomson
C.S.
Mickovski
S.B.
Waste to Land (W2L): A novel tool to show and predict the spatial effect of applying biosolids on the environment
2020
Scopus
https://www.scopus.com/inward/record.uri?eid=2-s2.0-85089889187&doi=10.1016%2fj.agsy.2020.102934&partnerID=40&md5=a67d575893b56647cc0a5b85b0765f19
journalArticle
376
Geoderma
DOI 10.1016/j.geoderma.2020.114529
Gurung
R.B.
Ogle
S.M.
Breidt
F.J.
Williams
S.A.
Parton
W.J.
Bayesian calibration of the DayCent ecosystem model to simulate soil organic carbon dynamics and reduce model uncertainty
2020
Scopus
https://www.scopus.com/inward/record.uri?eid=2-s2.0-85087483059&doi=10.1016%2fj.geoderma.2020.114529&partnerID=40&md5=aeb30dd1eb734655dfb7e03bf4ca43c6
journalArticle
241
Agricultural Water Management
DOI 10.1016/j.agwat.2020.106387
Ramos
T.B.
Castanheira
N.
Oliveira
A.R.
Paz
A.M.
Darouich
H.
Simionesei
L.
Farzamian
M.
Gonçalves
M.C.
Soil salinity assessment using vegetation indices derived from Sentinel-2 multispectral data. application to Lezíria Grande, Portugal
2020
Scopus
https://www.scopus.com/inward/record.uri?eid=2-s2.0-85087828342&doi=10.1016%2fj.agwat.2020.106387&partnerID=40&md5=cc4d609fb9a67e1efc67633b8a42be9c
journalArticle
47
Journal of Biogeography
DOI 10.1111/jbi.13950
11
García-Navas
V.
Thuiller
W.
Farmland bird assemblages exhibit higher functional and phylogenetic diversity than forest assemblages in France
2020
Scopus
https://www.scopus.com/inward/record.uri?eid=2-s2.0-85090771535&doi=10.1111%2fjbi.13950&partnerID=40&md5=675b94d7080b0ae3b1b72506810e66c1
2392-2404
journalArticle
12
Water (Switzerland)
DOI 10.3390/w12113215
11
Moslenko
L.
Blagrave
K.
Filazzola
A.
Shuvo
A.
Sharma
S.
Identifying the influence of land cover and human population on chlorophyll a concentrations using a Pseudo-watershed analytical framework
2020
Scopus
https://www.scopus.com/inward/record.uri?eid=2-s2.0-85096364692&doi=10.3390%2fw12113215&partnerID=40&md5=0e48e043b5d98f811506b79410bde44e
1-16
journalArticle
378
Geoderma
DOI 10.1016/j.geoderma.2020.114582
Zimmer
T.
Buligon
L.
de Arruda Souza
V.
Romio
L.C.
Roberti
D.R.
Influence of clearness index and soil moisture in the soil thermal dynamic in natural pasture in the Brazilian Pampa biome
2020
Scopus
https://www.scopus.com/inward/record.uri?eid=2-s2.0-85088828376&doi=10.1016%2fj.geoderma.2020.114582&partnerID=40&md5=f6460e1268b19043b45e24f798ea4909
journalArticle
158
Industrial Crops and Products
DOI 10.1016/j.indcrop.2020.112949
Min
X.
Liu
Z.
Wang
Y.
Liu
W.
Comparative transcriptomic analysis provides insights into the coordinated mechanisms of leaves and roots response to cold stress in Common Vetch
2020
Scopus
https://www.scopus.com/inward/record.uri?eid=2-s2.0-85092618882&doi=10.1016%2fj.indcrop.2020.112949&partnerID=40&md5=c93aa3a3d405b9722ebac55cb5c94c8a
journalArticle
12
Water (Switzerland)
DOI 10.3390/w12123479
12
Donmez
C.
Sari
O.
Berberoglu
S.
Cilek
A.
Satir
O.
Volk
M.
Improving the applicability of the swat model to simulate flow and nitrate dynamics in a flat data-scarce agricultural region in the mediterranean
2020
Scopus
https://www.scopus.com/inward/record.uri?eid=2-s2.0-85100065793&doi=10.3390%2fw12123479&partnerID=40&md5=01c0143efb1f41c12b364d70d37b668d
1-24
journalArticle
381
Geoderma
DOI 10.1016/j.geoderma.2020.114645
Hu
B.
Bourennane
H.
Arrouays
D.
Denoroy
P.
Lemercier
B.
Saby
N.P.A.
Developing pedotransfer functions to harmonize extractable soil phosphorus content measured with different methods: A case study across the mainland of France
2021
Scopus
https://www.scopus.com/inward/record.uri?eid=2-s2.0-85089884123&doi=10.1016%2fj.geoderma.2020.114645&partnerID=40&md5=8e75b7055c75c6def814256615c177b8
journalArticle
243
Agricultural Water Management
DOI 10.1016/j.agwat.2020.106479
Zhou
K.
Li
J.
Zhang
T.
Kang
A.
The use of combined soil moisture data to characterize agricultural drought conditions and the relationship among different drought types in China
2021
Scopus
https://www.scopus.com/inward/record.uri?eid=2-s2.0-85090204888&doi=10.1016%2fj.agwat.2020.106479&partnerID=40&md5=f8938194d792a4ef708b4d35e080ea90
journalArticle
252
Remote Sensing of Environment
DOI 10.1016/j.rse.2020.112173
Féret
J.-B.
Berger
K.
de Boissieu
F.
Malenovský
Z.
PROSPECT-PRO for estimating content of nitrogen-containing leaf proteins and other carbon-based constituents
2021
Scopus
https://www.scopus.com/inward/record.uri?eid=2-s2.0-85095734273&doi=10.1016%2fj.rse.2020.112173&partnerID=40&md5=ed08a9ef16cced1eff37eb1a938604c0
journalArticle
27
Journal of Agricultural Education and Extension
DOI 10.1080/1389224X.2021.1873156
4
Fieldsend
A.F.
Cronin
E.
Varga
E.
Biró
S.
Rogge
E.
‘Sharing the space’ in the agricultural knowledge and innovation system: multi-actor innovation partnerships with farmers and foresters in Europe
2021
Scopus
https://www.scopus.com/inward/record.uri?eid=2-s2.0-85099554596&doi=10.1080%2f1389224X.2021.1873156&partnerID=40&md5=a4e087d3c14b05d916095d46fa7ed062
423-442
journalArticle
6
AIMS Agriculture and Food
DOI 10.3934/AGRFOOD.2021011
1
Kusumiyati
Munawar
A.A.
Suhandy
D.
Fast, simultaneous and contactless assessment of intact mango fruit by means of near infrared spectroscopy
2021
Scopus
https://www.scopus.com/inward/record.uri?eid=2-s2.0-85099954878&doi=10.3934%2fAGRFOOD.2021011&partnerID=40&md5=021ca5214d3c5b71cf3d5ccce85b24c1
172-184
journalArticle
37
Sarhad Journal of Agriculture
DOI 10.17582/journal.sja/2021/37.2.538.547
2
Aslam
F.
alman
A.
Jan
I.
Aneel
S.S.
Policy Analytics-Insights from Pakistan and India Water Policies
2021
Scopus
https://www.scopus.com/inward/record.uri?eid=2-s2.0-85107837660&doi=10.17582%2fjournal.sja%2f2021%2f37.2.538.547&partnerID=40&md5=5273481146919b3b64de986f69eb5f30
538-547
journalArticle
5
Phytobiomes Journal
DOI 10.1094/PBIOMES-09-20-0062-A
2
Willman
M.
Keener
H.M.
Benitez
M.-S.
Sequence resource of bacterial communities associated with hemp in Ohio
2021
Scopus
https://www.scopus.com/inward/record.uri?eid=2-s2.0-85111652179&doi=10.1094%2fPBIOMES-09-20-0062-A&partnerID=40&md5=27d4f672ad45b79c725ebae81f5e1aaa
244-247
journalArticle
64
INMATEH - Agricultural Engineering
DOI 10.35633/inmateh-64-29
Zheng
J.
Li
M.
Hu
S.
Xiao
X.
Li
H.
Li
W.
RESEARCH ON OPTIMIZATION OF AGRICULTURAL MACHINERY FAULT MONITORING SYSTEM BASED ON ARTIFICIAL NEURAL NETWORK ALGORITHM
2021
Scopus
https://www.scopus.com/inward/record.uri?eid=2-s2.0-85113305038&doi=10.35633%2finmateh-64-29&partnerID=40&md5=97670f24775a0f139abe2524c87a0f4d
297-306
journalArticle
64
Transactions of the ASABE
DOI 10.13031/trans.14658
6
Guo
Y.
Qiao
Y.
Sukkarieh
S.
Chai
L.
He
D.
BIGRU-ATTENTION BASED COW BEHAVIOR CLASSIFICATION USING VIDEO DATA FOR PRECISION LIVESTOCK FARMING
2021
Scopus
https://www.scopus.com/inward/record.uri?eid=2-s2.0-85117474887&doi=10.13031%2ftrans.14658&partnerID=40&md5=2d215dd94329af2f94a2b08180595a91
1823-1833
journalArticle
23
Journal of Agricultural and Food Information
DOI 10.1080/10496505.2021.2013850
1-2
Williams
S.C.
Data Practices Ten Years Later: A New Review of Selected Publications by Crop Sciences Faculty
2021
Scopus
https://www.scopus.com/inward/record.uri?eid=2-s2.0-85122492996&doi=10.1080%2f10496505.2021.2013850&partnerID=40&md5=c2ed0aa5f523236e71f6c951c858923f
28-43
journalArticle
64
Transactions of the ASABE
DOI 10.13031/trans.14510
6
Askar
M.H.
Youssef
M.A.
Hesterberg
D.L.
King
K.W.
Amoozegar
A.
Skaggs
R.W.
Chescheir
G.M.
Ghane
E.
DRAINMOD-P: A MODEL FOR SIMULATING PHOSPHORUS DYNAMICS AND TRANSPORT IN DRAINED AGRICULTURAL LANDS: II. MODEL TESTING
2021
Scopus
https://www.scopus.com/inward/record.uri?eid=2-s2.0-85124938123&doi=10.13031%2ftrans.14510&partnerID=40&md5=6693c694cdf29338830b87620deca669
1849-1866
journalArticle
17
International Journal of Agricultural and Statistical Sciences
Amin
H.M.
Shada
M.S.
Abdullah
A.S.
Ali
M.K.
VEGETABLES FRAMER’S ATTITUDES TOWARDS PARTICIPATING IN THE TRAINING COURSES IN AL-ALAM DISTRICT / SALAH AL-DIN GOVERNMENT
2021
Scopus
https://www.scopus.com/inward/record.uri?eid=2-s2.0-85125856014&partnerID=40&md5=8e169a4a75070aa8fd3c03e247ac8942
1457-1465
journalArticle
9
PeerJ
DOI 10.7717/peerj.10758
Maneerat
P.
Niwitpong
S.-A.
Estimating the average daily rainfall in Thailand using confidence intervals for the common mean of several delta-lognormal distributions
2021
Scopus
https://www.scopus.com/inward/record.uri?eid=2-s2.0-85099867438&doi=10.7717%2fpeerj.10758&partnerID=40&md5=27523dab041d817731f089b3d845c600
journalArticle
121
Ecological Indicators
DOI 10.1016/j.ecolind.2020.107033
Sandeep
P.
Obi Reddy
G.P.
Jegankumar
R.
Arun Kumar
K.C.
Monitoring of agricultural drought in semi-arid ecosystem of Peninsular India through indices derived from time-series CHIRPS and MODIS datasets
2021
Scopus
https://www.scopus.com/inward/record.uri?eid=2-s2.0-85092725180&doi=10.1016%2fj.ecolind.2020.107033&partnerID=40&md5=9a5a95d1527206062505036da4db8523
journalArticle
13
Water (Switzerland)
DOI 10.3390/w13020113
2
Cambi
M.
Giambastiani
Y.
Giannetti
F.
Nuti
E.
Dani
A.
Preti
F.
Integrated low-cost approach for measuring the state of conservation of agricultural terraces in tuscany, Italy
2021
Scopus
https://www.scopus.com/inward/record.uri?eid=2-s2.0-85099780769&doi=10.3390%2fw13020113&partnerID=40&md5=f1da614991d784fb6cad45c6fec6fd52
journalArticle
253
Quaternary Science Reviews
DOI 10.1016/j.quascirev.2020.106776
Vermeersch
S.
Riehl
S.
Starkovich
B.M.
Kamlah
J.
Developments in subsistence during the Early Bronze Age through the Iron Age in the southern and central Levant: Integration of faunal and botanical remains using multivariate statistics
2021
Scopus
https://www.scopus.com/inward/record.uri?eid=2-s2.0-85098710711&doi=10.1016%2fj.quascirev.2020.106776&partnerID=40&md5=80b4a5c91d99822a82080035f8ad8a78
journalArticle
244
Agricultural Water Management
DOI 10.1016/j.agwat.2020.106597
Revuelta-Acosta
J.D.
Flanagan
D.C.
Engel
B.A.
King
K.W.
Improvement of the Water Erosion Prediction Project (WEPP) model for quantifying field scale subsurface drainage discharge
2021
Scopus
https://www.scopus.com/inward/record.uri?eid=2-s2.0-85094879117&doi=10.1016%2fj.agwat.2020.106597&partnerID=40&md5=a4535783c28dffddcec5d1a020655257
journalArticle
80
Environmental Earth Sciences
DOI 10.1007/s12665-020-09359-8
3
do Rego
E.L.
Boaventura
G.R.
Leite
O.D.
Araújo
D.F.
Souza
A.S.
Peres
L.G.M.
Lima
A.S.C.
da Silva
J.D.S.
de Souza
J.R.
Geochemical baseline of trace and major elements in sediments in the Rio de Ondas Basin (Bahia, Brazil)
2021
Scopus
https://www.scopus.com/inward/record.uri?eid=2-s2.0-85100307064&doi=10.1007%2fs12665-020-09359-8&partnerID=40&md5=49bc015e816dab8c3b96a66cb3fb9053
journalArticle
182
Computers and Electronics in Agriculture
DOI 10.1016/j.compag.2020.105980
Vermeulen
L.M.
Munch
Z.
Palmer
A.
Fractional vegetation cover estimation in southern African rangelands using spectral mixture analysis and Google Earth Engine
2021
Scopus
https://www.scopus.com/inward/record.uri?eid=2-s2.0-85100103766&doi=10.1016%2fj.compag.2020.105980&partnerID=40&md5=3671a17ad6ddaba5210f95b74b3010c8
journalArticle
11
Agriculture (Switzerland)
DOI 10.3390/agriculture11020131
2
Aguiar
A.S.
Monteiro
N.N.
Dos Santos
F.N.
Solteiro Pires
E.J.
Silva
D.
Sousa
A.J.
Boaventura-Cunha
J.
Bringing semantics to the vineyard: An approach on deep learning-based vine trunk detection
2021
Scopus
https://www.scopus.com/inward/record.uri?eid=2-s2.0-85101115919&doi=10.3390%2fagriculture11020131&partnerID=40&md5=155a45644304221dc20b94fcd61672d3
1-20
journalArticle
6
mSystems
DOI 10.1128/MSYSTEMS.01048-20
1
Myers
K.N.
Conn
D.
Brown
A.M.V.
Essential Amino Acid Enrichment and Positive Selection Highlight Endosymbiont's Role in a Global Virus-Vectoring Pest
2021
Scopus
https://www.scopus.com/inward/record.uri?eid=2-s2.0-85102282531&doi=10.1128%2fMSYSTEMS.01048-20&partnerID=40&md5=4631144b22a59f842cda36298d558bcf
journalArticle
182
Computers and Electronics in Agriculture
DOI 10.1016/j.compag.2021.106055
Li
Y.
Yang
J.
Meta-learning baselines and database for few-shot classification in agriculture
2021
Scopus
https://www.scopus.com/inward/record.uri?eid=2-s2.0-85101217081&doi=10.1016%2fj.compag.2021.106055&partnerID=40&md5=e870befbb5cfec8a1dcc6e94a9fea1bd
journalArticle
255
Remote Sensing of Environment
DOI 10.1016/j.rse.2021.112292
Mardian
J.
Berg
A.
Daneshfar
B.
Evaluating the temporal accuracy of grassland to cropland change detection using multitemporal image analysis
2021
Scopus
https://www.scopus.com/inward/record.uri?eid=2-s2.0-85099512440&doi=10.1016%2fj.rse.2021.112292&partnerID=40&md5=a54c69c95b6a6214f588de1bd4fe6932
journalArticle
204
Biosystems Engineering
DOI 10.1016/j.biosystemseng.2021.01.001
Kupper
T.
Eugster
R.
Sintermann
J.
Häni
C.
Ammonia emissions from an uncovered dairy slurry storage tank over two years: Interactions with tank operations and meteorological conditions
2021
Scopus
https://www.scopus.com/inward/record.uri?eid=2-s2.0-85100238203&doi=10.1016%2fj.biosystemseng.2021.01.001&partnerID=40&md5=d62c56e65d8daff920bdf030ec663514
36-49
journalArticle
21
Current Applied Science and Technology
2
Moriom Khatun
M.
Siddik
M.S.
Rahman
M.A.
Khaled
S.
Content analysis of COVID-19 and agriculture news in Bangladesh using topic modeling algorithm
2021
Scopus
https://www.scopus.com/inward/record.uri?eid=2-s2.0-85097389771&partnerID=40&md5=3f2e7fd0f8304e9478cdff3930ccc724
296-314
journalArticle
19
Paddy and Water Environment
DOI 10.1007/s10333-021-00842-x
2
Hirano
A.
Effects of climate change on spatiotemporal patterns of tropical cyclone tracks and their implications for coastal agriculture in Myanmar
2021
Scopus
https://www.scopus.com/inward/record.uri?eid=2-s2.0-85100446133&doi=10.1007%2fs10333-021-00842-x&partnerID=40&md5=4b07c8636b31cdb81e60d0c903c99ec5
261-269
journalArticle
204
Biosystems Engineering
DOI 10.1016/j.biosystemseng.2021.01.014
Espejo-Garcia
B.
Mylonas
N.
Athanasakos
L.
Vali
E.
Fountas
S.
Combining generative adversarial networks and agricultural transfer learning for weeds identification
2021
Scopus
https://www.scopus.com/inward/record.uri?eid=2-s2.0-85100388257&doi=10.1016%2fj.biosystemseng.2021.01.014&partnerID=40&md5=5ffa91fe1b6d1c2c3a08c983ea032a5e
79-89
journalArticle
103
Land Use Policy
DOI 10.1016/j.landusepol.2021.105322
O'Donoghue
C.
Buckley
C.
Chyzheuskaya
A.
Green
S.
Howley
P.
Hynes
S.
Upton
V.
Ryan
M.
The spatial impact of rural economic change on river water quality
2021
Scopus
https://www.scopus.com/inward/record.uri?eid=2-s2.0-85100406712&doi=10.1016%2fj.landusepol.2021.105322&partnerID=40&md5=004178e5ba3f005e78aef555cc29f887
journalArticle
183
Computers and Electronics in Agriculture
DOI 10.1016/j.compag.2021.106064
Zhang
K.
Wu
Q.
Chen
Y.
Detecting soybean leaf disease from synthetic image using multi-feature fusion faster R-CNN
2021
Scopus
https://www.scopus.com/inward/record.uri?eid=2-s2.0-85102027155&doi=10.1016%2fj.compag.2021.106064&partnerID=40&md5=d191f8ec3b456fc91abb97532044449a
journalArticle
13
Water (Switzerland)
DOI 10.3390/w13070894
7
Liu
P.
Zheng
C.
Wen
M.
Luo
X.
Wu
Z.
Liu
Y.
Chai
S.
Huang
L.
Ecological risk assessment and contamination history of heavy metals in the sediments of chagan lake, northeast china
2021
Scopus
https://www.scopus.com/inward/record.uri?eid=2-s2.0-85103496873&doi=10.3390%2fw13070894&partnerID=40&md5=b0728fee33f3b85eb16babbea968ad3f
journalArticle
13
Water (Switzerland)
DOI 10.3390/w13070958
7
Masciale
R.
Amalfitano
S.
Frollini
E.
Ghergo
S.
Melita
M.
Parrone
D.
Preziosi
E.
Vurro
M.
Zoppini
A.
Passarella
G.
Assessing natural background levels in the groundwater bodies of the apulia region (Southern Italy)
2021
Scopus
https://www.scopus.com/inward/record.uri?eid=2-s2.0-85104095352&doi=10.3390%2fw13070958&partnerID=40&md5=aa4e7077cdd22cc20755bd4d788ddbb5
journalArticle
32
Land Degradation and Development
DOI 10.1002/ldr.3871
6
Zhu
L.
Zhang
L.
Wang
J.
Lv
J.
Combining finite mixture distribution, receptor model, and geostatistical simulation to evaluate heavy metals pollution in soils: Source and spatial pattern
2021
Scopus
https://www.scopus.com/inward/record.uri?eid=2-s2.0-85099057364&doi=10.1002%2fldr.3871&partnerID=40&md5=f28d2cffbb6f2700212a3257be3b4566
2105-2115
journalArticle
209
Soil and Tillage Research
DOI 10.1016/j.still.2021.104959
Madarász
B.
Jakab
G.
Szalai
Z.
Juhos
K.
Kotroczó
Z.
Tóth
A.
Ladányi
M.
Long-term effects of conservation tillage on soil erosion in Central Europe: A random forest-based approach
2021
Scopus
https://www.scopus.com/inward/record.uri?eid=2-s2.0-85101360793&doi=10.1016%2fj.still.2021.104959&partnerID=40&md5=58906ab030efa5529a5d0827d295e31c
journalArticle
184
Computers and Electronics in Agriculture
DOI 10.1016/j.compag.2021.106081
Ahmad
A.
Saraswat
D.
Aggarwal
V.
Etienne
A.
Hancock
B.
Performance of deep learning models for classifying and detecting common weeds in corn and soybean production systems
2021
Scopus
https://www.scopus.com/inward/record.uri?eid=2-s2.0-85102341863&doi=10.1016%2fj.compag.2021.106081&partnerID=40&md5=98bcca6d11e99ffdf9166748d2db819e
journalArticle
205
Biosystems Engineering
DOI 10.1016/j.biosystemseng.2021.02.009
Jin
H.
Shuvo Bakar
K.
Henderson
B.L.
Bramley
R.G.V.
Gobbett
D.L.
An efficient geostatistical analysis tool for on-farm experiments targeted at localised treatment
2021
Scopus
https://www.scopus.com/inward/record.uri?eid=2-s2.0-85102868105&doi=10.1016%2fj.biosystemseng.2021.02.009&partnerID=40&md5=2ff8e244d99dc3ae73c86f3c447664ae
121-136
journalArticle
185
Computers and Electronics in Agriculture
DOI 10.1016/j.compag.2021.106133
Andrew
W.
Gao
J.
Mullan
S.
Campbell
N.
Dowsey
A.W.
Burghardt
T.
Visual identification of individual Holstein-Friesian cattle via deep metric learning
2021
Scopus
https://www.scopus.com/inward/record.uri?eid=2-s2.0-85105690946&doi=10.1016%2fj.compag.2021.106133&partnerID=40&md5=ecdfe5c00494ecc729a5ce64d4e8d1f1
journalArticle
184
Computers and Electronics in Agriculture
DOI 10.1016/j.compag.2021.106059
Perugachi-Diaz
Y.
Tomczak
J.M.
Bhulai
S.
Deep learning for white cabbage seedling prediction
2021
Scopus
https://www.scopus.com/inward/record.uri?eid=2-s2.0-85103279230&doi=10.1016%2fj.compag.2021.106059&partnerID=40&md5=ee26552f7cd71fbdb6343c598a79b8a6
journalArticle
10
Agricultural Research
DOI 10.1007/s40003-020-00494-z
2
Kumar
P.
Kumar
P.
Shukla
A.K.
Spatial Modeling of Some Selected Soil Nutrients Using Geostatistical Approach for Jhandutta Block (Bilaspur District), Himachal Pradesh, India
2021
Scopus
https://www.scopus.com/inward/record.uri?eid=2-s2.0-85094810816&doi=10.1007%2fs40003-020-00494-z&partnerID=40&md5=07dd46229fc8c865323db17f39f6b139
262-273
journalArticle
11
Agronomy
DOI 10.3390/agronomy11061227
6
Linaza
M.T.
Posada
J.
Bund
J.
Eisert
P.
Quartulli
M.
Döllner
J.
Pagani
A.
Olaizola
I.G.
Barriguinha
A.
Moysiadis
T.
Lucat
L.
Data-driven artificial intelligence applications for sustainable precision agriculture
2021
Scopus
https://www.scopus.com/inward/record.uri?eid=2-s2.0-85108974664&doi=10.3390%2fagronomy11061227&partnerID=40&md5=fae1da19e9f42ca5553175044a400e35
journalArticle
186
Computers and Electronics in Agriculture
DOI 10.1016/j.compag.2021.106205
Moradizadeh
M.
Srivastava
P.K.
A new model for an improved AMSR2 satellite soil moisture retrieval over agricultural areas
2021
Scopus
https://www.scopus.com/inward/record.uri?eid=2-s2.0-85107691673&doi=10.1016%2fj.compag.2021.106205&partnerID=40&md5=70834cdaac4fd8e7e61527ac22c756f5
journalArticle
20
Comprehensive Reviews in Food Science and Food Safety
DOI 10.1111/1541-4337.12773
4
Galvan
D.
Effting
L.
Torres Neto
L.
Conte-Junior
C.A.
An overview of research of essential oils by self-organizing maps: A novel approach for meta-analysis study
2021
Scopus
https://www.scopus.com/inward/record.uri?eid=2-s2.0-85107925845&doi=10.1111%2f1541-4337.12773&partnerID=40&md5=21ec3219c8888bb4be4e6809a7483ecc
3136-3163
journalArticle
169
Marine Pollution Bulletin
DOI 10.1016/j.marpolbul.2021.112526
Seceh
C.
Pinazo
C.
Rodier
M.
Lajaunie-Salla
K.
Mazoyer
C.
Grenz
C.
Le Gendre
R.
Biogeochemical model of nitrogen cycling in Ahe (French Polynesia), a South Pacific coral atoll with pearl farming
2021
Scopus
https://www.scopus.com/inward/record.uri?eid=2-s2.0-85107334929&doi=10.1016%2fj.marpolbul.2021.112526&partnerID=40&md5=4a27380846cb5e0b10e43a82bff7181f
journalArticle
187
Computers and Electronics in Agriculture
DOI 10.1016/j.compag.2021.106253
Peng
Y.
Wang
Y.
An industrial-grade solution for agricultural image classification tasks
2021
Scopus
https://www.scopus.com/inward/record.uri?eid=2-s2.0-85107811057&doi=10.1016%2fj.compag.2021.106253&partnerID=40&md5=a1ed6ba812e0c8d470a978427a641e8d
journalArticle
187
Computers and Electronics in Agriculture
DOI 10.1016/j.compag.2021.106254
Su
Q.
Tang
J.
Zhai
J.
Sun
Y.
He
D.
Automatic tracking of the dairy goat in the surveillance video
2021
Scopus
https://www.scopus.com/inward/record.uri?eid=2-s2.0-85107921161&doi=10.1016%2fj.compag.2021.106254&partnerID=40&md5=ec2c50d2fd5d3c1986efe137c991522f
journalArticle
187
Computers and Electronics in Agriculture
DOI 10.1016/j.compag.2021.106275
Wang
K.
Wu
P.
Cui
H.
Xuan
C.
Su
H.
Identification and classification for sheep foraging behavior based on acoustic signal and deep learning
2021
Scopus
https://www.scopus.com/inward/record.uri?eid=2-s2.0-85108347458&doi=10.1016%2fj.compag.2021.106275&partnerID=40&md5=22c65f3f708535c149ec40f7b59a1d1d
journalArticle
80
Environmental Earth Sciences
DOI 10.1007/s12665-021-09800-6
16
Sandeep
P.
Kumar
K.C.A.
Haritha
S.
Risk modelling of soil erosion in semi-arid watershed of Tamil Nadu, India using RUSLE integrated with GIS and Remote Sensing
2021
Scopus
https://www.scopus.com/inward/record.uri?eid=2-s2.0-85112042408&doi=10.1007%2fs12665-021-09800-6&partnerID=40&md5=b5b58b0e73ec288f0ae3f4d49a988415
journalArticle
255
Agricultural Water Management
DOI 10.1016/j.agwat.2021.107015
Satoh
Y.
Kakiuchi
H.
Calibration method to address influences of temperature and electrical conductivity for a low-cost soil water content sensor in the agricultural field
2021
Scopus
https://www.scopus.com/inward/record.uri?eid=2-s2.0-85107717024&doi=10.1016%2fj.agwat.2021.107015&partnerID=40&md5=feae8aeb0f0e53691903b945827417ee
journalArticle
255
Agricultural Water Management
DOI 10.1016/j.agwat.2021.107001
Mondol
M.A.H.
Zhu
X.
Dunkerley
D.
Henley
B.J.
Observed meteorological drought trends in Bangladesh identified with the Effective Drought Index (EDI)
2021
Scopus
https://www.scopus.com/inward/record.uri?eid=2-s2.0-85108256963&doi=10.1016%2fj.agwat.2021.107001&partnerID=40&md5=a9f1fdb8c028b48d0d326109d59bfd17
journalArticle
12
Forests
DOI 10.3390/f12081078
8
Stonesifer
C.S.
Calkin
D.E.
Thompson
M.P.
Belval
E.J.
Is this flight necessary? The aviation use summary (aus): A framework for strategic, risk-informed aviation decision support
2021
Scopus
https://www.scopus.com/inward/record.uri?eid=2-s2.0-85113710770&doi=10.3390%2ff12081078&partnerID=40&md5=37ca4911f724d0dda74d27ca4d0fdc66
journalArticle
32
Land Degradation and Development
DOI 10.1002/ldr.4014
14
Palmate
S.S.
Pandey
A.
Pandey
R.P.
Mishra
S.K.
Assessing the land degradation and greening response to changes in hydro-climatic variables using a conceptual framework: A case-study in central India
2021
Scopus
https://www.scopus.com/inward/record.uri?eid=2-s2.0-85108072643&doi=10.1002%2fldr.4014&partnerID=40&md5=5fff8281af1d62a55dd5645131fddfb2
4132-4148
journalArticle
64
Ecological Informatics
DOI 10.1016/j.ecoinf.2021.101359
Nzabarinda
V.
Bao
A.
Xu
W.
Uwamahoro
S.
Huang
X.
Gao
Z.
Umugwaneza
A.
Kayumba
P.M.
Maniraho
A.P.
Jiang
Z.
Impact of cropland development intensity and expansion on natural vegetation in different African countries
2021
Scopus
https://www.scopus.com/inward/record.uri?eid=2-s2.0-85111346124&doi=10.1016%2fj.ecoinf.2021.101359&partnerID=40&md5=3d4fb9f8bbfbaba09cf39e8a9ba2fa45
journalArticle
188
Computers and Electronics in Agriculture
DOI 10.1016/j.compag.2021.106365
Bahlo
C.
Dahlhaus
P.
Livestock data – Is it there and is it FAIR? A systematic review of livestock farming datasets in Australia
2021
Scopus
https://www.scopus.com/inward/record.uri?eid=2-s2.0-85111927884&doi=10.1016%2fj.compag.2021.106365&partnerID=40&md5=d0391380c45173c1a271c83587ba1e3d
journalArticle
44
Journal of Food Process Engineering
DOI 10.1111/jfpe.13782
9
Xu
J.-J.
Liong
S.-T.
Tan
L.-K.
Gan
Y.S.
Find the centroid: A vision-based approach for optimal object grasping
2021
Scopus
https://www.scopus.com/inward/record.uri?eid=2-s2.0-85108949972&doi=10.1111%2fjfpe.13782&partnerID=40&md5=0f53ce12ede0f0353205fed58c16cff5
journalArticle
13
Water (Switzerland)
DOI 10.3390/w13182464
18
Bilal
H.
Govindan
R.
Al-Ansari
T.
Investigation of groundwater depletion in the state of qatar and its implication to energy water and food nexus
2021
Scopus
https://www.scopus.com/inward/record.uri?eid=2-s2.0-85114713982&doi=10.3390%2fw13182464&partnerID=40&md5=df3674b3aed5c03f6d8aaa38ffa6f540
journalArticle
248
Comparative Biochemistry and Physiology Part - C: Toxicology and Pharmacology
DOI 10.1016/j.cbpc.2021.109081
Wu
A.
Yu
Q.
Lu
H.
Lou
Z.
Zhao
Y.
Luo
T.
Fu
Z.
Jin
Y.
Developmental toxicity of procymidone to larval zebrafish based on physiological and transcriptomic analysis
2021
Scopus
https://www.scopus.com/inward/record.uri?eid=2-s2.0-85106300936&doi=10.1016%2fj.cbpc.2021.109081&partnerID=40&md5=7c67f628e3fe7f0dd6e57193aaf636bd
journalArticle
11
Agronomy
DOI 10.3390/agronomy11091890
9
Aguiar
A.S.
Magalhães
S.A.
Dos Santos
F.N.
Castro
L.
Pinho
T.
Valente
J.
Martins
R.
Boaventura-Cunha
J.
Grape bunch detection at different growth stages using deep learning quantized models
2021
Scopus
https://www.scopus.com/inward/record.uri?eid=2-s2.0-85116639398&doi=10.3390%2fagronomy11091890&partnerID=40&md5=e41eed283edde0030d98b8180d13deed
journalArticle
189
Computers and Electronics in Agriculture
DOI 10.1016/j.compag.2021.106354
Soares
V.H.A.
Ponti
M.A.
Gonçalves
R.A.
Campello
R.J.G.B.
Cattle counting in the wild with geolocated aerial images in large pasture areas
2021
Scopus
https://www.scopus.com/inward/record.uri?eid=2-s2.0-85112519543&doi=10.1016%2fj.compag.2021.106354&partnerID=40&md5=24444147c5a31101f1b130339ef2fa0e
journalArticle
189
Computers and Electronics in Agriculture
DOI 10.1016/j.compag.2021.106371
Kim
W.-S.
Lee
D.-H.
Kim
T.
Kim
G.
Kim
H.
Sim
T.
Kim
Y.-J.
One-shot classification-based tilled soil region segmentation for boundary guidance in autonomous tillage
2021
Scopus
https://www.scopus.com/inward/record.uri?eid=2-s2.0-85113680896&doi=10.1016%2fj.compag.2021.106371&partnerID=40&md5=11ef4b5a5cc748f01fd069def05d4012
journalArticle
189
Computers and Electronics in Agriculture
DOI 10.1016/j.compag.2021.106404
Wosner
O.
Farjon
G.
Bar-Hillel
A.
Object detection in agricultural contexts: A multiple resolution benchmark and comparison to human
2021
Scopus
https://www.scopus.com/inward/record.uri?eid=2-s2.0-85114096000&doi=10.1016%2fj.compag.2021.106404&partnerID=40&md5=2f2e8d1f0222636a6d93e6d3543f295f
journalArticle
189
Computers and Electronics in Agriculture
DOI 10.1016/j.compag.2021.106417
Huang
E.
Mao
A.
Gan
H.
Camila Ceballos
M.
Parsons
T.D.
Xue
Y.
Liu
K.
Center clustering network improves piglet counting under occlusion
2021
Scopus
https://www.scopus.com/inward/record.uri?eid=2-s2.0-85114128077&doi=10.1016%2fj.compag.2021.106417&partnerID=40&md5=cca8aef0ddc06bf07deb59f402e13404
journalArticle
13
Water (Switzerland)
DOI 10.3390/w13192661
19
Quinn
N.W.T.
Tansey
M.K.
Lu
T.J.
Comparison of deterministic and statistical models for water quality compliance forecasting in the San Joaquin river basin, California
2021
Scopus
https://www.scopus.com/inward/record.uri?eid=2-s2.0-85115930564&doi=10.3390%2fw13192661&partnerID=40&md5=b0cd19db5e9f9357acb30500df09fd98
journalArticle
131
Ecological Indicators
DOI 10.1016/j.ecolind.2021.108129
Umuhoza
J.
Jiapaer
G.
Yin
H.
Mind'je
R.
Gasirabo
A.
Nzabarinda
V.
Umwali
E.D.
The analysis of grassland carrying capacity and its impact factors in typical mountain areas in Central Asia—A case of Kyrgyzstan and Tajikistan
2021
Scopus
https://www.scopus.com/inward/record.uri?eid=2-s2.0-85113324713&doi=10.1016%2fj.ecolind.2021.108129&partnerID=40&md5=f503f2dae829c70c3c9f8f383fc80ab7
journalArticle
265
Remote Sensing of Environment
DOI 10.1016/j.rse.2021.112623
Judge
J.
Liu
P.-W.
Monsiváis-Huertero
A.
Bongiovanni
T.
Chakrabarti
S.
Steele-Dunne
S.C.
Preston
D.
Allen
S.
Bermejo
J.P.
Rush
P.
DeRoo
R.
Colliander
A.
Cosh
M.
Impact of vegetation water content information on soil moisture retrievals in agricultural regions: An analysis based on the SMAPVEX16-MicroWEX dataset
2021
Scopus
https://www.scopus.com/inward/record.uri?eid=2-s2.0-85113982351&doi=10.1016%2fj.rse.2021.112623&partnerID=40&md5=657d284367c077eed1593cf412316550
journalArticle
190
Computers and Electronics in Agriculture
DOI 10.1016/j.compag.2021.106445
Chen
Y.
Xiong
Y.
Zhang
B.
Zhou
J.
Zhang
Q.
3D point cloud semantic segmentation toward large-scale unstructured agricultural scene classification
2021
Scopus
https://www.scopus.com/inward/record.uri?eid=2-s2.0-85114742960&doi=10.1016%2fj.compag.2021.106445&partnerID=40&md5=a52f6d8a1c5c4710ece01e7d4c6974e7
journalArticle
190
Computers and Electronics in Agriculture
DOI 10.1016/j.compag.2021.106467
Zhao
W.
Chen
X.
Li
Y.
Xu
J.
Li
X.
A recognition of farming behavior method based on EPCI-LSTM model
2021
Scopus
https://www.scopus.com/inward/record.uri?eid=2-s2.0-85115343866&doi=10.1016%2fj.compag.2021.106467&partnerID=40&md5=2177b371ebc493818b9744fbfd0e9282
journalArticle
11
Agronomy
DOI 10.3390/agronomy11112245
11
Rangwala
M.
Liu
J.
Ahluwalia
K.S.
Ghajar
S.
Dhami
H.S.
Tracy
B.F.
Tokekar
P.
Williams
R.K.
Deeppastl: Spatio-temporal deep learning methods for predicting long-term pasture terrains using synthetic datasets
2021
Scopus
https://www.scopus.com/inward/record.uri?eid=2-s2.0-85118993826&doi=10.3390%2fagronomy11112245&partnerID=40&md5=8a5aae435bdc1f591b826e6dc905c1d9
journalArticle
402
Geoderma
DOI 10.1016/j.geoderma.2021.115350
Jeanneau
A.
Herrmann
T.
Ostendorf
B.
Mapping the spatio-temporal variability of hillslope erosion with the G2 model and GIS: A case-study of the South Australian agricultural zone
2021
Scopus
https://www.scopus.com/inward/record.uri?eid=2-s2.0-85111197726&doi=10.1016%2fj.geoderma.2021.115350&partnerID=40&md5=7d4c0a476b8cdeb71f40807fa72e50b1
journalArticle
402
Geoderma
DOI 10.1016/j.geoderma.2021.115347
Fontenelli
J.V.
Adamchuk
V.I.
Ferreira
M.M.C.
Amaral
L.R.
Guimarães
C.C.B.
Demattê
J.A.M.
Magalhães
P.S.G.
Evaluating the synergy of three soil spectrometers for improving the prediction and mapping of soil properties in a high anthropic management area: A case of study from Southeast Brazil
2021
Scopus
https://www.scopus.com/inward/record.uri?eid=2-s2.0-85111069838&doi=10.1016%2fj.geoderma.2021.115347&partnerID=40&md5=5414504d9df7394c8bc1a48342608851
journalArticle
14
Bioenergy Research
DOI 10.1007/s12155-020-10216-6
4
Herrera
A.M.N.
Esteves
E.M.M.
Morgado
C.R.V.
Esteves
V.P.P.
Carbon Footprint Analysis of Bioenergy Production from Cattle Manure in the Brazilian Central-West
2021
Scopus
https://www.scopus.com/inward/record.uri?eid=2-s2.0-85095692951&doi=10.1007%2fs12155-020-10216-6&partnerID=40&md5=99c95efe35e24b82b0e8a83d28a0211e
1265-1276
journalArticle
21
BMC Plant Biology
DOI 10.1186/s12870-020-02817-2
1
Wang
Y.
Zhang
W.
Liu
W.
Ahammed
G.J.
Wen
W.
Guo
S.
Shu
S.
Sun
J.
Auxin is involved in arbuscular mycorrhizal fungi-promoted tomato growth and NADP-malic enzymes expression in continuous cropping substrates
2021
Scopus
https://www.scopus.com/inward/record.uri?eid=2-s2.0-85100106558&doi=10.1186%2fs12870-020-02817-2&partnerID=40&md5=a29351b30b7806552892786a99828e72
journalArticle
191
Computers and Electronics in Agriculture
DOI 10.1016/j.compag.2021.106482
Xie
B.
Jiao
W.
Wen
C.
Hou
S.
Zhang
F.
Liu
K.
Li
J.
Feature detection method for hind leg segmentation of sheep carcass based on multi-scale dual attention U-Net
2021
Scopus
https://www.scopus.com/inward/record.uri?eid=2-s2.0-85116864935&doi=10.1016%2fj.compag.2021.106482&partnerID=40&md5=bbc603a4a142bfce1a4b414e353b7ee5
journalArticle
191
Computers and Electronics in Agriculture
DOI 10.1016/j.compag.2021.106510
Güldenring
R.
Nalpantidis
L.
Self-supervised contrastive learning on agricultural images
2021
Scopus
https://www.scopus.com/inward/record.uri?eid=2-s2.0-85118586411&doi=10.1016%2fj.compag.2021.106510&partnerID=40&md5=e11a5ebc9974007f32088735bd5d45b4
journalArticle
191
Computers and Electronics in Agriculture
DOI 10.1016/j.compag.2021.106518
Dong
S.
Wang
R.
Liu
K.
Jiao
L.
Li
R.
Du
J.
Teng
Y.
Wang
F.
CRA-Net: A channel recalibration feature pyramid network for detecting small pests
2021
Scopus
https://www.scopus.com/inward/record.uri?eid=2-s2.0-85118832022&doi=10.1016%2fj.compag.2021.106518&partnerID=40&md5=a2e41e65b4f17faeb5afb338986243c1
journalArticle
133
Ecological Indicators
DOI 10.1016/j.ecolind.2021.108463
Rayner
M.
Balzter
H.
Jones
L.
Whelan
M.
Stoate
C.
Effects of improved land-cover mapping on predicted ecosystem service outcomes in a lowland river catchment
2021
Scopus
https://www.scopus.com/inward/record.uri?eid=2-s2.0-85120743235&doi=10.1016%2fj.ecolind.2021.108463&partnerID=40&md5=8dddc35b16852dea71e41fc07ccf58ca
journalArticle
11
Agronomy
DOI 10.3390/agronomy11122440
12
Kateb
F.A.
Monowar
M.M.
Hamid
M.A.
Ohi
A.Q.
Mridha
M.F.
FruitDet: Attentive feature aggregation for real-time fruit detection in orchards
2021
Scopus
https://www.scopus.com/inward/record.uri?eid=2-s2.0-85121668508&doi=10.3390%2fagronomy11122440&partnerID=40&md5=9fc8c87e668918d3953a04e5d0182333
journalArticle
114
Journal of Economic Entomology
DOI 10.1093/jee/toab192
6
Maino
J.L.
Cushen
A.
Valavi
R.
Umina
P.A.
Spatial Variation in Australian Neonicotinoid Usage and Priorities for Resistance Monitoring
2021
Scopus
https://www.scopus.com/inward/record.uri?eid=2-s2.0-85122412328&doi=10.1093%2fjee%2ftoab192&partnerID=40&md5=dd865e6e5d00a9e2df24dbf91fa8dd7b
2524-2533
journalArticle
9
Journal of Experimental Biology and Agricultural Sciences
DOI 10.18006/2021.9(6).863.870
6
Nirgude
V.
Rathi
S.
A ROBUST DEEP LEARNING APPROACH TO ENHANCE THE ACCURACY OF POMEGRANATE FRUIT DISEASE DETECTION UNDER REAL FIELD CONDITION
2021
Scopus
https://www.scopus.com/inward/record.uri?eid=2-s2.0-85124185138&doi=10.18006%2f2021.9%286%29.863.870&partnerID=40&md5=4b4c6af1ea12c7a7784ec98c710fc53c
863-870
journalArticle
404
Geoderma
DOI 10.1016/j.geoderma.2021.115298
Rhymes
J.M.
Wynne-Jones
S.
Prysor Williams
A.
Harris
I.M.
Rose
D.
Chadwick
D.R.
Jones
D.L.
Identifying barriers to routine soil testing within beef and sheep farming systems
2021
Scopus
https://www.scopus.com/inward/record.uri?eid=2-s2.0-85108635734&doi=10.1016%2fj.geoderma.2021.115298&partnerID=40&md5=80f1464a7053226de5c43dfb425f0211
journalArticle
82
Brazilian Journal of Biology
DOI 10.1590/1519-6984.242635
Ehtisham
Akhtar
A.
Khan
K.A.
Iqbal
M.
Bano
S.A.
Hussain
M.
Munawar
N.
Habiba
U.
Identification and crop damage assessment of indian crested porcupine (Hystrix indica) in selected zones of abbottabad, pakistan
2022
Avaliação de identificação e dano de cultura de porco-espinho indiano (Hystrix indica) em zonas selecionadas de abbottabad, paquistão
Scopus
https://www.scopus.com/inward/record.uri?eid=2-s2.0-85110141233&doi=10.1590%2f1519-6984.242635&partnerID=40&md5=9e3667f652c3b50ba431c30b8b1e5ac6
journalArticle
54
Pakistan Journal of Botany
DOI 10.30848/PJB2022-1(4)
1
Naqvi
S.A.A.
Islam
A.
Waseem
L.A.
Hussain
D.
Naqvi
R.Z.
Kazmi
S.J.H.
Sajjad
M.
Shaikh
S.
Geo-spatially integrated soil quality evaluation: A case of Toba Tek Singh, Pakistan
2022
Scopus
https://www.scopus.com/inward/record.uri?eid=2-s2.0-85115655390&doi=10.30848%2fPJB2022-1%284%29&partnerID=40&md5=f4d224f381bb966835a461c45ae9c42a
journalArticle
164
Soil Biology and Biochemistry
DOI 10.1016/j.soilbio.2021.108467
Wu
J.
Cheng
X.
Xing
W.
Liu
G.
Soil-atmosphere exchange of CH4 in response to nitrogen addition in diverse upland and wetland ecosystems: A meta-analysis
2022
Scopus
https://www.scopus.com/inward/record.uri?eid=2-s2.0-85118346568&doi=10.1016%2fj.soilbio.2021.108467&partnerID=40&md5=8bc224caf9024e896a81e5705a73d080
journalArticle
Animal Production Science
DOI 10.1071/AN17503
McCosker
K.D.
Perkins
N.R.
Fordyce
G.
O'Rourke
P.K.
McGowan
M.R.
Reproductive performance of northern Australia beef herds. 5. Factors influencing risk of non-pregnancy
2022
Scopus
https://www.scopus.com/inward/record.uri?eid=2-s2.0-85127396660&doi=10.1071%2fAN17503&partnerID=40&md5=a4186d21408e15be3fd06c55f67b0ad5
journalArticle
51
JOURNAL OF ENVIRONMENTAL QUALITY
DOI 10.1002/jeq2.20351
3
Williams
M. R.
Welikhe
P.
Bos
J.
King
K.
Akland
M.
Augustine
D.
Baffaut
C.
Beck
E. G.
Bierer
A.
Bosch
D. D.
Boughton
E.
Brandani
C.
Brooks
E.
Buda
A.
Cavigelli
M.
Faulkner
J.
Feyereisen
G.
Fortuna
A.
Gamble
J.
Hanrahan
B.
Hussain
M.
Kohmann
M.
Kovar
J.
Lee
B.
Leytem
A.
Liebig
M.
Line
D.
Macrae
M.
Moorman
T.
Moriasi
D.
Nelson
N.
Ortega-Pieck
A.
Osmond
D.
Pisani
O.
Ragosta
J.
Reba
M.
Saha
A.
Sanchez
J.
Silveira
M.
Smith
D.
Spiegal
S.
Swain
H.
Unrine
J.
Webb
P.
White
K.
Wilson
H.
Yasarer
L.
P-FLUX: A phosphorus budget dataset spanning diverse agricultural production systems in the United States and Canada
Quantifying spatial and temporal fluxes of phosphorus (P) within and among agricultural production systems is critical for sustaining agricultural production while minimizing environmental impacts. To better understand P fluxes in agricultural landscapes, P-FLUX, a detailed and harmonized dataset of P inputs, outputs, and budgets, as well as estimated uncertainties for each P flux and budget, was developed. Data were collected from 24 research sites and 61 production systems through the Long-term Agroecosystem Research (LTAR) network and partner organizations spanning 22 U.S. states and 2 Canadian provinces. The objectives of this paper are to (a) present and provide a description of the P-FLUX dataset, (b) provide summary analyses of the agricultural production systems included in the dataset and the variability in P inputs and outputs across systems, and (c) provide details for accessing the dataset, dataset limitations, and an example of future use. P-FLUX includes information on select site characteristics (area, soil series), crop rotation, P inputs (P application rate, source, timing, placement, P in irrigation water, atmospheric deposition), P outputs (crop removal, hydrologic losses), P budgets (agronomic budget, overall budget), uncertainties associated with each flux and budget, and data sources. Phosphorus fluxes and budgets vary across agricultural production systems and are useful resources to improve P use efficiency and develop management strategies to mitigate environmental impacts of agricultural systems. P-FLUX is available for download through the USDA Ag Data Commons ().
2022 MAY
WOS:000786531000001
451-461
journalArticle
12
SCIENTIFIC REPORTS
DOI 10.1038/s41598-022-10277-x
1
Acosta-Quezada
Pablo G.
Valladolid-Salinas
Edin H.
Murquincho-Chuncho
Janina M.
Jadan-Verinas
Eudaldo
Ruiz-Gonzalez
Mario X.
Heterogeneous effects of climatic conditions on Andean bean landraces and cowpeas highlight alternatives for crop management and conservation
The use and conservation of agrobiodiversity have become critical to face the actual and future challenges imposed by climate change. Collecting phytogenetic resources is a first step for their conservation; however, the genetic material must be analysed to understand their potential to improve agricultural resilience and adaptation to the new climatic conditions. We have selected nine Phaseolus vulgaris, one P. lunatus and two Vigna unguiculata landraces from two different climatic backgrounds of the Andean region of South Ecuador and one P. vulgaris commercial cultivar, and we grew them under two different conditions of temperature and humidity (open field and greenhouse). Then, we recorded data for 32 characters of plant architecture, flower and fruit characteristics and yield, and 17 events in the phenology of the plants. We analysed the impact of treatment on species, climatic background, and each of the landraces, and identified both characters and landraces that are mostly affected by changes in their environmental conditions. Overall, higher temperatures were benign for all materials except for two P. vulgaris landraces from cold background, which performed better or developed faster under cold conditions. Finally, we calculated a climate resilience landrace index, which allowed us to classify the landraces by their plasticity to new environmental conditions, and found heterogeneous landrace susceptibility to warmer conditions. Two P. vulgaris landraces were highlighted as critical targets for conservation.
2022 APR 21
WOS:000784878300022
journalArticle
22
SENSORS
DOI 10.3390/s22093391
9
Dong
Bo
Zhang
Kai
A Tightly Coupled Visual-Inertial GNSS State Estimator Based on Point-Line Feature
Visual-inertial odometry (VIO) is known to suffer from drifting and can only provide local coordinates. In this paper, we propose a tightly coupled GNSS-VIO system based on point-line features for robust and drift-free state estimation. Feature-based methods are not robust in complex areas such as weak or repeated textures. To deal with this problem, line features with more environmental structure information can be extracted. In addition, to eliminate the accumulated drift of VIO, we tightly fused the GNSS measurement with visual and inertial information. The GNSS pseudorange measurements are real-time and unambiguous but experience large errors. The GNSS carrier phase measurements can achieve centimeter-level positioning accuracy, but the solution to the whole-cycle ambiguity is complex and time-consuming, which degrades the real-time performance of a state estimator. To combine the advantages of the two measurements, we use the carrier phase smoothed pseudorange instead of pseudorange to perform state estimation. Furthermore, the existence of the GNSS receiver and IMU also makes the extrinsic parameter calibration crucial. Our proposed system can calibrate the extrinsic translation parameter between the GNSS receiver and IMU in real-time. Finally, we show that the states represented in the ECEF frame are fully observable, and the tightly coupled GNSS-VIO state estimator is consistent. We conducted experiments on public datasets. The experimental results demonstrate that the positioning precision of our system is improved and the system is robust and real-time.
2022 MAY
WOS:000794857400001
journalArticle
22
SENSORS
DOI 10.3390/s22103913
10
Balivada
Srinivasa
Grant
Gregory
Zhang
Xufeng
Ghosh
Monisha
Guha
Supratik
Matamala
Roser
A Wireless Underground Sensor Network Field Pilot for Agriculture and Ecology: Soil Moisture Mapping Using Signal Attenuation
Wireless Underground Sensor Networks (WUSNs) that collect geospatial in situ sensor data are a backbone of internet-of-things (IoT) applications for agriculture and terrestrial ecology. In this paper, we first show how WUSNs can operate reliably under field conditions year-round and at the same time be used for determining and mapping soil conditions from the buried sensor nodes. We demonstrate the design and deployment of a 23-node WUSN installed at an agricultural field site that covers an area with a 530 m radius. The WUSN has continuously operated since September 2019, enabling real-time monitoring of soil volumetric water content (VWC), soil temperature (ST), and soil electrical conductivity. Secondly, we present data collected over a nine-month period across three seasons. We evaluate the performance of a deep learning algorithm in predicting soil VWC using various combinations of the received signal strength (RSSI) from each buried wireless node, above-ground pathloss, the distance between wireless node and receive antenna (D), ST, air temperature (AT), relative humidity (RH), and precipitation as input parameters to the model. The AT, RH, and precipitation were obtained from a nearby weather station. We find that a model with RSSI, D, AT, ST, and RH as inputs was able to predict soil VWC with an R-2 of 0.82 for test datasets, with a Root Mean Square Error of +/- 0.012 (m(3)/m(3)). Hence, a combination of deep learning and other easily available soil and climatic parameters can be a viable candidate for replacing expensive soil VWC sensors in WUSNs.
2022 MAY
WOS:000803372900001
journalArticle
435
JOURNAL OF HAZARDOUS MATERIALS
DOI 10.1016/j.jhazmat.2022.128981
Zhao
Ze-Ying
Wang
Peng-Yang
Xiong
Xiao-Bin
Wang
Yi-Bo
Zhou
Rui
Tao
Hong-Yan
Grace
Uzamurera Aimee
Wang
Ning
Xiong
You-Cai
Environmental risk of multi-year polythene film mulching and its green solution in arid irrigation region
Environmental risk of multi-year polythene film mulching (PM) was evaluated and investigated. The location observation following 19-year (2000-2018) PM in irrigated region indicated that the cumulative accumulation of soil microplastics was as high as 2900 +/- 19.5 n kg- 1. Microplastic accumulation was tightly associated with soil plasticizer concentration (Pearson's r = 0.728, p <0.05), and the concentration of dominant phthalic acid esters (PAEs) was up to 117.5-705 mu g kg- 1. As such, we conducted organic mulching substitute experiment (2019-2020) with non-mulching (CK), maize straw mulching (SM), living clover mulching (CM), PM, PM+SM and PM+CM respectively. The data showed that organic mulching (SM, CM) achieved similar productivity benefit as PM-involved treatments (p > 0.05). Critically, total concentration of PAEs decreased by 6.43% in SM relative to CK, and by 9.61% in PM+SM relative to PM respectively. High throughput sequencing indicated that the proportions of predominant bacteria and fungi were totally lower in PM than those of organic mulching, particularly Sphingomonadaceae and Stachybotryaceae. KEGG analyses indicated that organic mulching promoted the metabolisms of polycyclic aromatic hydrocarbons, benzoic acid (probability>75%) and heterologous organism metabolism (p<0.001), due to improved microbial community assembly. Therefore, organic mulching efficiently accelerated microbial mineralization of PM pollutants, and may act as a green solution to displace PM.
2022 AUG 5
WOS:000798744300001
journalArticle
17
PLOS ONE
DOI 10.1371/journal.pone.0267215
5
Kitchen
Newell R.
Ransom
Curtis J.
Schepers
James S.
Hatfield
Jerry L.
Massey
Raymond
Drummond
Scott T.
A new perspective when examining maize fertilizer nitrogen use efficiency, incrementally
For maize (Zea mays L.), nitrogen (N) fertilizer use is often summarized from field to global scales using average N use efficiency (NUE). But expressing NUE as averages is misleading because grain increase to added N diminishes near optimal yield. Thus, environmental risks increase as economic benefits decrease. Here, we use empirical datasets obtained in North America of maize grain yield response to N fertilizer (n = 189) to create and interpret incremental NUE (iNUE), or the change in NUE with change in N fertilization. We show for those last units of N applied to reach economic optimal N rate (EONR) iNUE for N removed with the grain is only about 6%. Conversely stated, for those last units of N applied over 90% is either lost to the environment during the growing season, remains as inorganic soil N that too may be lost after the growing season, or has been captured within maize stover and roots or soil organic matter pools. Results also showed iNUE decrease averaged 0.63% for medium-textured soils and 0.37% for fine-textured soils, attributable to fine-textured soils being more predisposed to denitrification and/or lower mineralization. Further analysis demonstrated the critical nature growing season water amount and distribution has on iNUE. Conditions with too much rainfall and/or uneven rainfall produced low iNUE. Producers realize this from experience, and it is uncertain weather that largely drives insurance fertilizer additions. Nitrogen fertilization creating low iNUE is environmentally problematic. Our results show that with modest sub-EONR fertilization and minor forgone profit, average NUE improvements of similar to 10% can be realized. Further, examining iNUE creates unique perspective and ideas for how to improve N fertilizer management tools, educational programs, and public policies and regulations.
2022 MAY 11
WOS:000818854500023
journalArticle
58
ISOTOPES IN ENVIRONMENTAL AND HEALTH STUDIES
DOI 10.1080/10256016.2022.2070615
3
Stevenson
Jamie Lee
Geris
Josie
Birkel
Christian
Tetzlaff
Doerthe
Soulsby
Chris
Assessing land use influences on isotopic variability and stream water ages in urbanising rural catchments
Stable water isotopes are invaluable in helping understand catchment functioning and are widely used in experimental catchments, with higher frequency data becoming increasingly common. Such datasets incur substantial logistical costs, reducing their feasibility for use by decision makers needing to understand multi-catchment, landscape-scale functioning over a relatively short period to assess the impact of proposed land use change. Instead, reconnaissance style surveys (high spatial resolution across the landscape at a lower temporal frequency, over a relatively short period) offer an alternative, complementary approach. To test if such sampling could identify heterogeneities in hydrological functioning, and associated landscape controls, we sampled 27 stream sites fortnightly for one year within a peri-urban landscape undergoing land use change. Visual examination of raw data and application of mean transit time and young water fraction models indicated urbanisation, agriculture and responsive soils caused more rapid cycling of precipitation to stream water, whereas mature forestry provided attenuation. We were also able to identify contiguous catchments which functioned fundamentally differently, meaning their response to land use alteration would also be different. This study demonstrated how stable water isotopes can be a valuable, low-cost addition to tools available for environmental decision makers by providing local, process-based information.
2022 MAY 4
WOS:000795216000001
277-300
journalArticle
837
SCIENCE OF THE TOTAL ENVIRONMENT
DOI 10.1016/j.scitotenv.2022.155758
Burke
William J.
Snapp
Sieglinde S.
Peter
Brad G.
Jayne
Thom S.
Sustainable intensification in jeopardy: Transdisciplinary evidence from Malawi
In Africa, achieving sustainable agricultural intensification-increasing agricultural output without deleterious environmental impacts or converting more land for cultivation-will depend greatly on the actions of smallholder farmers and the policies that influence them. Whatever the future holds, the vast majority of farmers right now are small. Using multiple lines of evidence across disciplines, we examine trends in productivity of land and fertilizers in Malawi. Unfortunately, our effort uncovers disturbing trends that indicate intensification and sustainability are at risk. Two time series datasets of satellite-based vegetative indices show a generally flat but highly variable trend in the productivity of agricultural land with epochs of steep decline. This is notably despite substantial (and successful) government effort to promote fertilizer use. We also compile evidence from several studies over three decades that use field-level data from farmers and suggest substantial declining maize yield response to fertilizer over time. These trends are consistent with soil degradation, the disappearance of fallow land and minimal investment in rehabilitation practices in densely populated areas, putting agricultural productivity in jeopardy. These signs of the harmful impacts that narrow approaches to productivity improvement may be having in Malawi are an early warning sign to policy makers in Malawi and around the continent that a more holistic and nuanced strategy is necessary for sustainable intensification in agriculture.
2022 SEP 1
WOS:000806055400011
journalArticle
179
MARINE POLLUTION BULLETIN
DOI 10.1016/j.marpolbul.2022.113748
Andrefouet
Serge
Desclaux
Terence
Buttin
Julie
Jullien
Swen
Aucan
Jerome
Le Gendre
Romain
Liao
Vetea
Periodicity of wave-driven flows and lagoon water renewal for 74 Central Pacific Ocean atolls
French Polynesia atolls are spread on a vast 2300 by 1200 km Central Pacific Ocean area exposed to spatially and temporally dependent wave forcing. They also have a wide range of closed to open morphologies and several have been suitable to develop from black-lipped pearl oysters a substantial pearl farming activity in the past 30 years, representing nowadays the 2nd source of income for French Polynesia. Considering here only the component of lagoon renewal that is driven by waves, we investigate for 74 atolls different lagoon renewal metrics using 20 years of wave model data at 0.05 degrees spatial resolution. Wavelet spectral analyses highlight that atolls, even in close vicinity, can be exposed to different and characteristic periodicities in wave-driven flows and water renewal. These characteristics are discussed in relation to pearl farming atolls, including atolls known to be efficient oyster spat producers, a critical activity for pearl farming sustainability.
2022 JUN
WOS:000809653300004
journalArticle
837
SCIENCE OF THE TOTAL ENVIRONMENT
DOI 10.1016/j.scitotenv.2022.155893
Singh
Gurjeet
Das
Narendra N.
A data-driven approach using the remotely sensed soil moisture product to identify water-demand in agricultural regions
Effective agricultural water management requires accurate and timely identification of crop water stress at the farm scale for irrigation advisories or to allocate the optimal amount of water for irrigation. Various drought indices are being utilized to map the water-stressed locations/farms in agricultural regions. Most of these existing drought indices provide some degree of characterization of water stress but do not adequately provide spatially resolved high resolution (farm-scale) information for decision-making about irrigation advisories or water allocation. These existing drought indices need modeling and climatology information, hence making them data-intensive and complex to compute. Therefore, a reliable, simple, and computationally easy method without modeling to characterize the water stress at high-resolution is essential for the operational mapping of water-stressed farms in agricultural regions. The proposed new approach facilitates improved and quick decision-making without compromising much of the skills imparted by the established drought indices. This study aims to formulate a water-demand index (WDI) based on a parameter independent data-driven approach using readily available remote sensing observations and weather data. We hypothesize that the WDI for an agricultural domain can be characterized by soil moisture, vegetative growth (NDVI), and heat unit (growing degree day, GDD). To this end, we used remote sensing-based soil moisture and NDVI and modeled ambient temperature datasets to generate weekly WDI maps at 1 km. The proposed methodology is verified over a few intensively irrigated agricultural-dominated areas with different climatic conditions. Our results suggest that the proposed approach characterizes water-stressed fields through WDI maps with good spatial representativeness. Overall, this study provides a framework to generate weekly WDI maps quickly with readily available measurements. These water-demand maps will help water resource managers to reduce dependence on established drought indices and prioritize the specific regions/fields with high water demand for optimum water allocations to improve crop health and ultimately maximize water-use efficiency.
2022 SEP 1
WOS:000806302700012
journalArticle
2022
COMPUTATIONAL INTELLIGENCE AND NEUROSCIENCE
DOI 10.1155/2022/6564014
Yang
Hui
Zheng
Zhuohang
Sun
Chu
E-Commerce Marketing Optimization of Agricultural Products Based on Deep Learning and Data Mining
China Internet plus agriculture was first put forward in 2015 by the Chinese government's work report, laying the foundation for the development of Internet plus agriculture and promoting the rapid growth of e-commerce marketing of agricultural products. The combination of agricultural product marketing and e-commerce effectively reduces the intermediate links of agricultural product sales. Many e-commerce professional villages have sprung up in some rural areas across the country, and the number of rural e-commerce stores has continued to grow. At this stage, rural e-commerce has become a new way of agricultural trade, and rural e-commerce has formed a unique rural e-store. At present, the e-commerce market share of agricultural products in rural stores is very large, and its advantages are favored by the government, scientific research institutions, and agricultural products processing enterprises. However, with the gradual development of rural e-commerce, it has also encountered many difficulties. Based on this point, this study applies deep learning and data mining to optimize e-commerce marketing. First, with the growth of the online scale of agricultural product transaction data, the creation of traditional shallow model cannot meet the needs of online data processing. Therefore, this study decides to use the deep learning theory for optimization. It has excellent performance in the technical fields of big data processing and image and voice processing and has strong construction ability, which can effectively represent the characteristics of the model. Combined with the characteristics of e-commerce agricultural products processing and consumer practice, this study designs and develops a new customer value evaluation model based on data mining and e-commerce agricultural products value characteristics in the field of e-commerce. By combining deep learning and data mining technology, this study applies it to the field of e-commerce, so as to promote the transformation of marketing optimization.
2022 MAY 18
WOS:000805178400016
journalArticle
29
ENVIRONMENTAL SCIENCE AND POLLUTION RESEARCH
DOI 10.1007/s11356-022-20900-z
47
Singh
Bhavna
Venkatramanan
Veluswamy
Deshmukh
Benidhar
Monitoring of land use land cover dynamics and prediction of urban growth using Land Change Modeler in Delhi and its environs, India
In the recent decades, cities have been expanding at a great pace which changes the landscape rapidly as a result of inflow of people from rural areas and economic progression. Therefore, understanding spatiotemporal dynamics of human induced land use land cover changes has become an important issue to deal with the challenges for making sustainable cities. This study aims to determine the rate of landscape transformations along with its causes and consequences as well as predicting urban growth pattern in Delhi and its environs. Landsat satellite images of 1989, 2000, 2010 and 2020 were used to determine the changes in land use land cover using supervised maximum likelihood classification. Subsequently, Land Change Modeler (LCM) module of TerrSet software was used to generate future urban growth for the year 2030 based on 2010 and 2020 dataset. Validation was carried out by overlaying the actual and simulated 2020 maps. The change detection results showed that urban and open areas increased by 13.44% and 2.40%, respectively, with a substantial decrease in crop land (10.88%) from 1989 to 2020 and forest area increased by 3.48% in 2020 due to restoration programmes Furthermore, the simulated output of 2030 predicted an increase of 24.30% in urban area and kappa coefficient 0.96. Thus, knowledge of the present and predicted changes will help decision-makers and planners during the process of formulating new sustainable policies, master plans and economic strategies for rapidly growing cities with urban blue-green infrastructures.
2022 OCT
WOS:000799632100001
71534-71554
journalArticle
317
JOURNAL OF ENVIRONMENTAL MANAGEMENT
DOI 10.1016/j.jenvman.2022.115365
Bregaglio
Simone
Savian
Francesco
Raparelli
Elisabetta
Morelli
Danilo
Epifani
Rosanna
Pietrangeli
Fabio
Nigro
Camilla
Bugiani
Riccardo
Pini
Stefano
Culatti
Paolo
Tognetti
Danilo
Spanna
Federico
Gerardi
Marco
Delillo
Irene
Bajocco
Sofia
Fanchini
Davide
Fila
Gianni
Ginaldi
Fabrizio
Manici
Luisa M.
A public decision support system for the assessment of plant disease infection risk shared by Italian regions
Integrated pest management (IPM) practices proved to be efficient in reducing pesticide use and ensuring economic farming sustainability. Digital decision support systems (DSS) to support the adoption of IPM practices from plant protection services are required by European legislation. Available DSSs used by Italian plant protection services are heterogeneous with regards to disease forecasting models, datasets for their calibration, and level of integration in operational decision-making. This study presents the MISFITS-DSS, which has been jointly developed by a public research institution and nine regional plant protection services with the objective of harmonizing data collection and decision support for Italian farmers. Participatory approach allowed designing a predictive workflow relying on specific domain expertise, in order to explicitly match actual user needs. The DSS calibration entailed the risk of grapevine downy mildew infection (5-point scale from very low to very high), and phenological observations in 2012-2017 as reference data. Process-based models of primary and secondary infections have been implemented and tested via sensitivity analysis (Morris method) under contrasting weather conditions. Hindcast simulations of grapevine phenology, host susceptibility and disease pressure were post processed by machine-learning classifiers to predict the reference infection risk. Results indicate that IPM principles are implemented by plant protection services since years. The accurate reproduction of grapevine phenology (RMSE = 4-14 days), which drove the dynamic of host susceptibility, and the use of weather forecasts as model inputs contributed to reliably predict the reference infection risk (88% balanced accuracy). We did a pioneering effort to homogenize the methodology to deliver decision support to Italian farmers, by involving plant protection services in the DSS definition, to foster a further adoption of IPM practices.
2022 SEP 1
WOS:000812284900005
journalArticle
100
JOURNAL OF ANIMAL SCIENCE
DOI 10.1093/jas/skac132
6
Jacobs
Marc
Remus
Aline
Gaillard
Charlotte
Menendez
Hector M.
Tedeschi
Luis O.
Neethirajan
Suresh
Ellis
Jennifer L.
ASAS-NANP symposium: mathematical modeling in animal nutrition: limitations and potential next steps for modeling and modelers in the animal sciences
The hype of artificial intelligence is at an end, revealing to a larger audience the inherent dependencies and limitations of modeling as a human process. Technology is good, but data and humans are essential in enabling a more sustainable role for models in the animal sciences ecosystem.The field of animal science, and especially animal nutrition, relies heavily on modeling to accomplish its day-to-day objectives. New data streams ("big data") and the exponential increase in computing power have allowed the appearance of "new" modeling methodologies, under the umbrella of artificial intelligence (AI). However, many of these modeling methodologies have been around for decades. According to Gartner, technological innovation follows five distinct phases: technology trigger, peak of inflated expectations, trough of disillusionment, slope of enlightenment, and plateau of productivity. The appearance of AI certainly elicited much hype within agriculture leading to overpromised plug-and-play solutions in a field heavily dependent on custom solutions. The threat of failure can become real when advertising a disruptive innovation as sustainable. This does not mean that we need to abandon AI models. What is most necessary is to demystify the field and place a lesser emphasis on the technology and more on business application. As AI becomes increasingly more powerful and applications start to diverge, new research fields are introduced, and opportunities arise to combine "old" and "new" modeling technologies into hybrids. However, sustainable application is still many years away, and companies and universities alike do well to remain at the forefront. This requires investment in hardware, software, and analytical talent. It also requires a strong connection to the outside world to test, that which does, and does not work in practice and a close view of when the field of agriculture is ready to take its next big steps. Other research fields, such as engineering and automotive, have shown that the application power of AI can be far reaching but only if a realistic view of models as whole is maintained. In this review, we share our view on the current and future limitations of modeling and potential next steps for modelers in the animal sciences. First, we discuss the inherent dependencies and limitations of modeling as a human process. Then, we highlight how models, fueled by AI, can play an enhanced sustainable role in the animal sciences ecosystem. Lastly, we provide recommendations for future animal scientists on how to support themselves, the farmers, and their field, considering the opportunities and challenges the technological innovation brings.Lay Summary Modeling in the animal sciences has received a boost by large-scale adoption of sensor technology, increased computing power, and the further development of artificial intelligence (AI) in the form of machine learning (ML) and deep learning (DL) models. Together with open-source programming languages, extensive modeling libraries, and heavy marketing, modeling reached a larger audience via AI. However, like most technological innovations, AI overpromised. By adopting an almost singular model-centric view to solving business needs, models failed to integrate with existing business processes. Models, especially AI, need data and both need humans. Together, they need room to learn and fail and by offering them as the end-solution to a problem, they are unable to act as sparring partners for all relevant stakeholders. In this article, we highlight fundamental model limitations exemplified via AI, and we offer solutions toward a more sustainable adoption of AI as a catalyst for modeling. This means sharing data and code and placing a more realistic view on models. Universities and industry both play a fundamental role in offering technological prowess and business experience to the future modeler. People, not technology, are the key to a more successful adoption of models.
2022 JUN 1
WOS:000807752200001
journalArticle
19
INTERNATIONAL JOURNAL OF ENVIRONMENTAL RESEARCH AND PUBLIC HEALTH
DOI 10.3390/ijerph19126982
12
Guo
Hua
Gu
Fan
Peng
Yanling
Deng
Xin
Guo
Lili
Does Digital Inclusive Finance Effectively Promote Agricultural Green Development?-A Case Study of China
Agricultural green development is increasingly being discussed in sustainable development. This paper constructs agricultural green development from four dimensions: resource savings, environmental protection, ecological conservation, and quality industrialization. We apply the entropy-weighted Technique for Order Preference by Similarity to an Ideal Solution (TOPSIS) method to measure agricultural green development and employ a panel dataset of provinces in China from 2011-2019. Then, the dynamic spatial Durbin model is adopted to estimate the spatial effect of digital inclusive finance on agricultural green development. The main findings are as follows: (1) digital inclusive finance effectively promotes agricultural green development, and the promotional effect shows temporary and spatial spillover; (2) regional heterogeneity exists in the spatial effect in the short and long term; and (3) education, digital infrastructure, and traditional finance are important factors influencing this spatial effect of digital inclusive finance on agricultural green development.
2022 JUN
WOS:000815920200001
journalArticle
2022
JOURNAL OF ENVIRONMENTAL AND PUBLIC HEALTH
DOI 10.1155/2022/1588638
Wu
Yingli
Ma
Wanying
Rural Workplace Sustainable Development of Smart Rural Governance Workplace Platform for Efficient Enterprise Performances
In the long developmental process, China's agriculture has transformed from organic agriculture to inorganic agriculture. New technologies have made the modernization of agriculture possible. However, most older people who are engaged in agriculture may not completely understand the modernization of agriculture. Based on the limitations of traditional image target detection methods, a deep learning-based pest target detection and recognition method is proposed from a blockchain perspective, to analyze and research agricultural data supervision and governance and explore the effectiveness of deep learning methods in crop pest detection and recognition. The comparative analysis demonstrates that the average precision (AP) of GA-CPN-LAR (global activation-characteristic pyramid network-local activation region) increases by 4.2% compared with other methods. Whether under the Inception or ResNet-50 backbone networks, the AP of GA-CPN-LAR is significantly better than other methods. Compared with the ResNet-50 backbone network, GA-CPN-LAR has higher accuracy and recall rates under Inception. Precision-recall curve measurement shows that the proposed method can significantly reduce the false detection rate and missed detection rate. The GA-CPN-LAR model proposed here has a higher AP value on the MPD dataset than the other target detection methods, which can be increased by 4.2%. Besides, the accuracy and recall of the GA-CPN-LAR method corresponding to two representative pests under the initial feature extractor are higher than the MPD dataset baseline. In addition, the research results of the MPD dataset and AgriPest dataset also show that the pest target detection method based on convolutional neural networks (CNNs) has a good presentation effect and can significantly reduce false detection and missed detection. Moreover, the pest regulation based on blockchain and deep learning comprehensively considers global and local feature extraction and pattern recognition, which positively impacts the conscientization of agricultural data processing and promotes the sustainable development of rural areas.
2022 JUN 3
WOS:000811019000003
journalArticle
51
JOURNAL OF ENVIRONMENTAL QUALITY
DOI 10.1002/jeq2.20377
5
Vibart
Ronaldo
Giltrap
Donna
Saggar
Surinder
Mackay
Alec
Betteridge
Keith
Costall
Des
Rollo
Mike
Draganova
Ina
Review and update of a Nutrient Transfer model used for estimating nitrous oxide emissions from complex grazed landscapes, and implications for nationwide accounting
In New Zealand, nitrous oxide emissions from grazed hill pastures are estimated using different emission factors for urine and dung deposited on different slope classes. Allocation of urine and dung to each slope class needs to consider the distribution of slope classes within a landscape and animal behavior. The Nutrient Transfer (NT) model has recently been incorporated into the New Zealand Agricultural GHG Inventory Model to account for the allocation of excretal nitrogen (N) to each slope class. In this study, the predictive ability of the transfer function within the NT model was explored using urine deposition datasets collected with urine sensor and GPS tracker technology. Data were collected from three paddocks that had areas in low (<12 degrees), medium (12-24 degrees), and high slopes (>24 degrees). The NT model showed a good overall predictive ability for two of the three datasets. However, if the urine emission factors (% of urine N emitted as N2O-N) were to be further disaggregated to assess emissions from all three slope classes or slope gradients, more precise data would be required to accurately represent the range of landscapes found on farms. We have identified the need for more geospatial data on urine deposition and animal location for farms that are topographically out of the range used to develop the model. These new datasets would provide livestock urine deposition on a more continuous basis across slopes (as opposed to broad ranges), a unique opportunity to improve the performance of the NT model.
2022 SEP
WOS:000815614800001
930-940
journalArticle
22
SENSORS
DOI 10.3390/s22134721
13
Sa
Inkyu
Lim
Jong Yoon
Ahn
Ho Seok
MacDonald
Bruce
deepNIR: Datasets for Generating Synthetic NIR Images and Improved Fruit Detection System Using Deep Learning Techniques
This paper presents datasets utilised for synthetic near-infrared (NIR) image generation and bounding-box level fruit detection systems. A high-quality dataset is one of the essential building blocks that can lead to success in model generalisation and the deployment of data-driven deep neural networks. In particular, synthetic data generation tasks often require more training samples than other supervised approaches. Therefore, in this paper, we share the NIR+RGB datasets that are re-processed from two public datasets (i.e., nirscene and SEN12MS), expanded our previous study, deepFruits, and our novel NIR+RGB sweet pepper (capsicum) dataset. We oversampled from the original nirscene dataset at 10, 100, 200, and 400 ratios that yielded a total of 127 k pairs of images. From the SEN12MS satellite multispectral dataset, we selected Summer (45 k) and All seasons (180k) subsets and applied a simple yet important conversion: digital number (DN) to pixel value conversion followed by image standardisation. Our sweet pepper dataset consists of 1615 pairs of NIR+RGB images that were collected from commercial farms. We quantitatively and qualitatively demonstrate that these NIR+RGB datasets are sufficient to be used for synthetic NIR image generation. We achieved Frechet inception distances (FIDs) of 11.36, 26.53, and 40.15 for nirscene1, SEN12MS, and sweet pepper datasets, respectively. In addition, we release manual annotations of 11 fruit bounding boxes that can be exported in various formats using cloud service. Four newly added fruits (blueberry, cherry, kiwi and wheat) compound 11 novel bounding box datasets on top of our previous work presented in the deepFruits project (apple, avocado, capsicum, mango, orange, rockmelon and strawberry). The total number of bounding box instances of the dataset is 162 k and it is ready to use from a cloud service. For the evaluation of the dataset, Yolov5 single stage detector is exploited and reported impressive mean-average-precision, mAP([0.5:0.95]) results of min:0.49, max:0.812. We hope these datasets are useful and serve as a baseline for future studies.
2022 JUL
WOS:000825588200001
journalArticle
19
INTERNATIONAL JOURNAL OF ENVIRONMENTAL RESEARCH AND PUBLIC HEALTH
DOI 10.3390/ijerph19148585
14
Liu
Dan
Gong
Qianwen
Promoting Farmers' Participation in Rural Settlement Environment Improvement Programmes: Evidence from China
A rural settlement environment improvement programme is a livelihood project involving the vital interests of farmers. However, whether farmers should take the main responsibility for improving the rural settlement environment is an open issue. This study constructs an evaluation index system for farmers' participation in rural settlement environment improvement on the basis of policy cognition, participation behaviour, and participation awareness. Using survey data from 909 farmers in eight provinces in China, this study empirically analyses farmers' participation in a rural settlement environment improvement programme. The study's results indicate that farmers have a high awareness of participation, a low level of policy cognition, and low involvement in the action regarding the rural settlement environment improvement. The participation of farmers in the rural settlement environment improvement is generally low and decreasing in the eastern, western, and central regions, in that order. Farmers' participation in rural settlement environment improvement decreases in the order of suburban integration villages, characteristic protection villages, agglomeration and upgrading villages, and relocation and evacuation villages. To increase farmers' participation in rural settlement environment improvement, the government can clarify the tasks in which farmers can participate, and establish an organisation and system to guide farmers' involvement.
2022 JUL
WOS:000832201500001
journalArticle
22
SENSORS
DOI 10.3390/s22145321
14
Riego del Castillo
Virginia
Sanchez-Gonzalez
Lidia
Campazas-Vega
Adrian
Strisciuglio
Nicola
Vision-Based Module for Herding with a Sheepdog Robot
Livestock farming is assisted more and more by technological solutions, such as robots. One of the main problems for shepherds is the control and care of livestock in areas difficult to access where grazing animals are attacked by predators such as the Iberian wolf in the northwest of the Iberian Peninsula. In this paper, we propose a system to automatically generate benchmarks of animal images of different species from iNaturalist API, which is coupled with a vision-based module that allows us to automatically detect predators and distinguish them from other animals. We tested multiple existing object detection models to determine the best one in terms of efficiency and speed, as it is conceived for real-time environments. YOLOv5m achieves the best performance as it can process 64 FPS, achieving an mAP (with IoU of 50%) of 99.49% for a dataset where wolves (predator) or dogs (prey) have to be detected and distinguished. This result meets the requirements of pasture-based livestock farms.
2022 JUL
WOS:000831931800001
journalArticle
19
INTERNATIONAL JOURNAL OF ENVIRONMENTAL RESEARCH AND PUBLIC HEALTH
DOI 10.3390/ijerph19138147
13
Chi
Liang
Han
Shuqing
Huan
Meili
Li
Yajuan
Liu
Jifang
Land Fragmentation, Technology Adoption and Chemical Fertilizer Application: Evidence from China
Although it has been widely recognized that land fragmentation has increased chemical fertilizer application, little is known about the role of technology adoption in mitigating these adverse effects. To empirically examine the relationship between land fragmentation, technology adoption and chemical fertilizer application, we developed a mediation model. We applied our analysis to a survey data set encompassing 1388 farm-level samples collected in 14 Chinese provinces in 2019. Our study demonstrated that land fragmentation can not only directly increase chemical fertilizer application but also indirectly increase it by hindering the adoption of agricultural mechanization technologies (AMT's) and soil testing fertilization technologies (STFT's). Both are recognized as potent drivers of fertilizer use reductions. Moreover, the adoption of information and communications technologies (ICT's) can help mitigate the negative effects of land fragmentation on technology adoption, thus reducing chemical fertilizer application intensity (CFAI). However, the direct effects of land fragmentation on CAFI was unaffected by ICT's. Our findings suggest that ICT's have revolutionized farmer recognition, promotion and adoption of agricultural technologies by increasing awareness and diffusion of agricultural technology information.
2022 JUL
WOS:000822128300001
journalArticle
17
PLOS ONE
DOI 10.1371/journal.pone.0270662
7
Medendorp
John William
Reeves
N. Peter
Sal y Rosas Celi
Victor Giancarlo
Harun-Ar-Rashid
Md
Krupnik
Timothy J.
Lutomia
Anne N.
Pittendrigh
Barry
Bello-Bravo
Julia
Large-scale rollout of extension training in Bangladesh: Challenges and opportunities for gender-inclusive participation
Despite the recognized importance of women's participation in agricultural extension services, research continues to show inequalities in women's participation. Emerging capacities for conducting large-scale extension training using information and communication technologies (ICTs) now afford opportunities for generating the rich datasets needed to analyze situational factors that affect women's participation. Data was recorded from 1,070 video-based agricultural extension training events (131,073 farmers) in four Administrative Divisions of Bangladesh (Rangpur, Dhaka, Khulna, and Rajshahi). The study analyzed the effect of gender of the trainer, time of the day, day of the week, month of the year, Bangladesh Administrative Division, and venue type on (1) the expected number of extension event attendees and (2) the odds of females attending the event conditioned on the total number of attendees. The study revealed strong gender specific training preferences. Several factors that increased total participation, decreased female attendance (e.g., male-led training event held after 3:30 pm in Rangpur). These findings highlight the dilemma faced by extension trainers seeking to maximize attendance at training events while avoiding exacerbating gender inequalities. The study concludes with a discussion of ways to mitigate gender exclusion in extension training by extending data collection processes, incorporating machine learning to understand gender preferences, and applying optimization theory to increase total participation while concurrently improving gender inclusivity.
2022 JUL 8
WOS:000844536800067
journalArticle
844
SCIENCE OF THE TOTAL ENVIRONMENT
DOI 10.1016/j.scitotenv.2022.157075
Ruan
Linlin
Yan
Min
Zhang
Li
Fan
XiangShun
Yang
Haoxiang
Spatial-temporal NDVI pattern of global mangroves: A growing trend during 2000-2018
Mangroves are coastal vegetation with high ecological and economic value that are mainly distributed in tropical and subtropical intertidal zones. In the past, they have been degraded by extensive deforestation for agricultural and aquatic land. In recent years, mangroves have been protected and sustainably used through considerable measures of conservation, restoration and afforestation, but the health trends of mangroves during this process are not clear. To identify the mangrove health conditions and dynamics, we investigated the spatial-temporal trends of global mangroves using the Moderate Resolution Imaging Spectroradiometer (MODIS) normalized difference vegetation index (NDVI) dataset during 2000-2018. The results illustrated that 1) Asian mangroves had the highest NDVI values, especially in Southeast Asia (0.80), while the average NDVI of African mangroves was the lowest (0.67). NDVI values higher than 0.80 were mainly located in Southeast Asia and South America, which accounted for 24.0 % and 7.1 % of the global mangrove area, respectively. 2) Globally, the proportion of mangrove forests that increased significantly (23.6 %, p value < 0.05) was approximately twice as large as the significant decrease (10.7 %, p value < 0.05). Asia, where mangroves are widespread, accounts for nearly half of the world's significant increase (10.8 %) and decrease (4.6 %). Generally, the annual average NDVI for global mangroves exhibited a slow increasing trend from 2000 to 2018 (p value = 0.13). 3) The global mangrove NDVI showed a positive correlation with precipitation (R-prep = 0.79, p value < 0.01) and temperature (R-temp = 0.37, p value < 0.01), while it was inhibited by sea surface salinity (R-sss=-0.45, p value < 0.01) on a scale of 1 degrees of latitude. 4) The results of the overall growth trend of mangroves indicated that global mangrove conservation appeared to achieve initial success, but direct or potential factors, such as salinity stress, natural disasters, small-scale deforestation, construction of coastal facilities, and sea level rise, still threaten the survival of mangroves, leading to a decline in their health status. This study provides information on the health status of mangrove ecosystems and can assist in formulating subsequent conservation and management measures.
2022 OCT 20
WOS:000862857100002
journalArticle
25
ECOLOGY LETTERS
DOI 10.1111/ele.14074
9
Roos
Deon
Caminero-Saldana
Constantino
Elston
David
Mougeot
Francois
Garcia-Ariza
Maria Carmen
Arroyo
Beatriz
Luque-Larena
Juan Jose
Revilla
Francisco Javier Rojo
Lambin
Xavier
From pattern to process? Dual travelling waves, with contrasting propagation speeds, best describe a self-organised spatio-temporal pattern in population growth of a cyclic rodent
The dynamics of cyclic populations distributed in space result from the relative strength of synchronising influences and the limited dispersal of destabilising factors (activators and inhibitors), known to cause multi-annual population cycles. However, while each of these have been well studied in isolation, there is limited empirical evidence of how the processes of synchronisation and activation-inhibition act together, largely owing to the scarcity of datasets with sufficient spatial and temporal scale and resolution. We assessed a variety of models that could be underlying the spatio-temporal pattern, designed to capture both theoretical and empirical understandings of travelling waves using large-scale (>35,000 km(2)), multi-year (2011-2017) field monitoring data on abundances of common vole (Microtus arvalis), a cyclic agricultural rodent pest. We found most support for a pattern formed from the summation of two radial travelling waves with contrasting speeds that together describe population growth rates across the region.
2022 SEP
WOS:000833601800001
1986-1998
journalArticle
12
SCIENTIFIC REPORTS
DOI 10.1038/s41598-022-17454-y
1
Waleed
Mirza
Mubeen
Muhammad
Ahmad
Ashfaq
Habib-ur-Rahman
Muhammad
Amin
Asad
Farid
Hafiz Umar
Hussain
Sajjad
Ali
Mazhar
Qaisrani
Saeed Ahmad
Nasim
Wajid
Javeed
Hafiz Muhammad Rashad
Masood
Nasir
Aziz
Tariq
Mansour
Fatma
EL Sabagh
Ayman
Evaluating the efficiency of coarser to finer resolution multispectral satellites in mapping paddy rice fields using GEE implementation
Timely and accurate estimation of rice-growing areas and forecasting of production can provide crucial information for governments, planners, and decision-makers in formulating policies. While there exists studies focusing on paddy rice mapping, only few have compared multi-scale datasets performance in rice classification. Furthermore, rice mapping of large geographical areas with sufficient accuracy for planning purposes has been a challenge in Pakistan, but recent advancements in Google Earth Engine make it possible to analyze spatial and temporal variations within these areas. The study was carried out over southern Punjab (Pakistan)-a region with 380,400 hectares devoted to rice production in year 2020. Previous studies support the individual capabilities of Sentinel-2, Landsat-8, and Moderate Resolution Imaging Spectroradiometer (MODIS) for paddy rice classification. However, to our knowledge, no study has compared the efficiencies of these three datasets in rice crop classification. Thus, this study primarily focuses on comparing these satellites' data by estimating their potential in rice crop classification using accuracy assessment methods and area estimation. The overall accuracies were found to be 96% for Sentinel-2, 91.7% for Landsat-8, and 82.6% for MODIS. The F1-Scores for derived rice class were 83.8%, 75.5%, and 65.5% for Sentinel-2, Landsat-8, and MODIS, respectively. The rice estimated area corresponded relatively well with the crop statistics report provided by the Department of Agriculture, Punjab, with a mean percentage difference of less than 20% for Sentinel-2 and MODIS and 33% for Landsat-8. The outcomes of this study highlight three points; (a) Rice mapping accuracy improves with increase in spatial resolution, (b) Sentinel-2 efficiently differentiated individual farm level paddy fields while Landsat-8 was not able to do so, and lastly (c) Increase in rice cultivated area was observed using satellite images compared to the government provided statistics.
2022 AUG 1
WOS:000834992200042
journalArticle
19
INTERNATIONAL JOURNAL OF ENVIRONMENTAL RESEARCH AND PUBLIC HEALTH
DOI 10.3390/ijerph19159269
15
He
Shan
Hu
Chenxia
Li
Jianfeng
Wu
Jieyi
Xu
Qian
Lin
Lin
Zhu
Congmou
Li
Yongjun
Zhou
Mengmeng
Zhu
Luyao
Revealing Spatial Patterns of Cultural Ecosystem Services in Four Agricultural Landscapes: A Case Study from Hangzhou, China
Monitoring and mapping agricultural cultural ecosystem services (CES) is essential, especially in areas with a sharp contradiction between agricultural land protection and urban development. Despite research assessing CES increasing exponentially in recent years, our knowledge of the CES of agricultural landscapes is still inadequate. This study used four types of agricultural landscapes in Hangzhou, China, as the study area, analyzed their CES spatial patterns, and explored their societal preferences by integrating the multi-sourced datasets, clustering algorithms, and Maxent model. The results indicated that hot spots of agricultural CES correspond to river valley plains, which were also easily vulnerable to urbanization. Moreover, we found that the CES level of paddy field and dry farmland were higher than tea garden and orchard. Based on the above spatial patterns of supply, demand, and flow of CES, we identified four groups of agricultural land by cluster analysis, distinguishing between significant, unimportant, little used, and potential CES. Further, our results showed that natural and human factors could explain societal preferences. This study can provide a valuable basis for stakeholders to develop balanced strategies by the aforementioned results.
2022 AUG
WOS:000838906400001
journalArticle
12
SCIENTIFIC REPORTS
DOI 10.1038/s41598-022-17826-4
1
Pang
Haitong
Zhang
Yitao
Cai
Weiming
Li
Bin
Song
Ruiyin
A real-time object detection model for orchard pests based on improved YOLOv4 algorithm
Accurate and efficient real-time detection of orchard pests was essential and could improve the economic benefits of the fruit industry. The orchard pest dataset, PestImgData, was built through a series of methods such as web crawler, specimen image collection and data augmentation. PestImgData was composed of two parts, PestImgData-1 and PestImgData-2. It contained 24,796 color images and covered 7 types of orchard pests. Based on the PestImgData and YOLOv4 algorithm, this paper conducted a preliminary study on the real-time object detection of orchard pests from 4 perspectives: transfer learning, activation function, anchor box, and batch normalization. In addition, this paper also visualized the feature learning ability of the detection models. On the basis of the above research, three improvement measures were adopted: the post-processing NMS algorithm was upgraded to DIoU-NMS, the training method was upgraded to 2-time finetuning training and the training data was enhanced. The performance of the improved model, F-D-YOLOv4-PEST, had been effectively improved. The mean average precision of F-D-YOLOv4-PEST was 92.86%, and the detection time of a single picture was 12.22 ms, which could meet the real-time detection requirements. In addition, in the case of high overlap area or high density, F-D-YOLOv4-PEST still maintained good performance. In the testing process of the laboratory and the greenhouse, including the wired network and the wireless network, F-D-YOLOv4-PEST could locate and classify pests as expected. This research could provide technical reference for the intelligent identification of agricultural pests based on deep learning.
2022 AUG 8
WOS:000837764800028
journalArticle
2022
COMPUTATIONAL INTELLIGENCE AND NEUROSCIENCE
DOI 10.1155/2022/9978167
Zhou
Hongyu
Liu
Jinqi
Huang
Fan
Application and Research of Computer Intelligent Technology in Modern Agricultural Machinery Equipment
Every country, including China, is deeply concerned and interested in the topic of agricultural machinery automation. The world's population is growing at an astronomical rate, and as a result, the need of food is also growing at an astronomical rate. Farmers are forced to apply more toxic pesticides since traditional methods are not up to the task of meeting the rising demand. This has a major impact on agricultural practices, and in the long run, the land becomes barren and unproductive. Intelligent technologies such as Internet of Things, wireless communication, and machine learning can help with crop disease and pesticide storage management, as well as water management and irrigation. In this paper, we design and analyze an intelligent system that automatically predicts the agricultural land features for irrigation purpose. Initially, the dataset is collected and preprocessed using normalization. The features are extracted using principal component analysis (PCA). For automatic prediction by the equipment, we propose heterogeneous fuzzy-based artificial neural network (HF-ANN) with genetic quantum spider monkey optimization (GQ-SMO) algorithm. Analyses and comparisons are made between the proposed approach and current methodologies. The findings indicate the effectiveness of the proposed system.
2022 AUG 9
WOS:000843367700017
journalArticle
12
SCIENTIFIC REPORTS
DOI 10.1038/s41598-022-18773-w
1
Menegat
Stefano
Ledo
Alicia
Tirado
Reyes
Greenhouse gas emissions from global production and use of nitrogen synthetic fertilisers in agriculture
The global agri-food system relies on synthetic nitrogen (N) fertilisation to increase crop yields, yet the use of synthetic N fertiliser is unsustainable. In this study we estimate global greenhouse (GHG) emissions due to synthetic N fertiliser manufacture, transportation, and field use in agricultural systems. By developing the largest field-level dataset available on N2O soil emissions we estimate national, regional and global N2O direct emission factors (EFs), while we retrieve from the literature the EFs for indirect N2O soil emissions, and for N fertiliser manufacturing and transportation. We find that the synthetic N fertiliser supply chain was responsible for estimated emissions of 1.13 GtCO(2)e in 2018, representing 10.6% of agricultural emissions and 2.1% of global GHG emissions. Synthetic N fertiliser production accounted for 38.8% of total synthetic N fertiliser-associated emissions, while field emissions accounted for 58.6% and transportation accounted for the remaining 2.6%. The top four emitters together, China, India, USA and EU28 accounted for 62% of the total. Historical trends reveal the great disparity in total and per capita N use in regional food production. Reducing overall production and use of synthetic N fertilisers offers large mitigation potential and in many cases realisable potential to reduce emissions.
2022 AUG 25
WOS:000846214200037
journalArticle
12
SCIENTIFIC REPORTS
DOI 10.1038/s41598-022-18635-5
1
Kittichotsatsawat
Yotsaphat
Tippayawong
Nakorn
Tippayawong
Korrakot Yaibuathet
Prediction of arabica coffee production using artificial neural network and multiple linear regression techniques
Crop yield and its prediction are crucial in agricultural production planning. This study investigates and predicts arabica coffee yield in order to match the market demand, using artificial neural networks (ANN) and multiple linear regression (MLR). Data of six variables, including areas, productivity zones, rainfalls, relative humidity, and minimum and maximum temperature, were collected for the recent 180 months between 2004 and 2018. The predicted yield of the cherry coffee crop continuously increases each year. From the dataset, it was found that the prediction accuracy of the R-2 and RMSE from ANN was 0.9524 and 0.0784 tons, respectively. The ANN model showed potential in determining the cherry coffee yields.
2022 AUG 25
WOS:000846214200058
journalArticle
22
SENSORS
DOI 10.3390/s22176574
17
Sousa
Joaquim J.
Toscano
Piero
Matese
Alessandro
Di Gennaro
Salvatore Filippo
Berton
Andrea
Gatti
Matteo
Poni
Stefano
Padua
Luis
Hruska
Jonas
Morais
Raul
Peres
Emanuel
UAV-Based Hyperspectral Monitoring Using Push-Broom and Snapshot Sensors: A Multisite Assessment for Precision Viticulture Applications
Hyperspectral aerial imagery is becoming increasingly available due to both technology evolution and a somewhat affordable price tag. However, selecting a proper UAV + hyperspectral sensor combo to use in specific contexts is still challenging and lacks proper documental support. While selecting an UAV is more straightforward as it mostly relates with sensor compatibility, autonomy, reliability and cost, a hyperspectral sensor has much more to be considered. This note provides an assessment of two hyperspectral sensors (push-broom and snapshot) regarding practicality and suitability, within a precision viticulture context. The aim is to provide researchers, agronomists, winegrowers and UAV pilots with dependable data collection protocols and methods, enabling them to achieve faster processing techniques and helping to integrate multiple data sources. Furthermore, both the benefits and drawbacks of using each technology within a precision viticulture context are also highlighted. Hyperspectral sensors, UAVs, flight operations, and the processing methodology for each imaging type' datasets are presented through a qualitative and quantitative analysis. For this purpose, four vineyards in two countries were selected as case studies. This supports the extrapolation of both advantages and issues related with the two types of hyperspectral sensors used, in different contexts. Sensors' performance was compared through the evaluation of field operations complexity, processing time and qualitative accuracy of the results, namely the quality of the generated hyperspectral mosaics. The results shown an overall excellent geometrical quality, with no distortions or overlapping faults for both technologies, using the proposed mosaicking process and reconstruction. By resorting to the multi-site assessment, the qualitative and quantitative exchange of information throughout the UAV hyperspectral community is facilitated. In addition, all the major benefits and drawbacks of each hyperspectral sensor regarding its operation and data features are identified. Lastly, the operational complexity in the context of precision agriculture is also presented.
2022 SEP
WOS:000851791300001
journalArticle
22
SENSORS
DOI 10.3390/s22176325
17
Li
Huibin
Guo
Wei
Lu
Guowen
Shi
Yun
Augmentation Method for High Intra-Class Variation Data in Apple Detection
Deep learning is widely used in modern orchard production for various inspection missions, which helps improve the efficiency of orchard operations. In the mission of visual detection during fruit picking, most current lightweight detection models are not yet effective enough to detect multi-type occlusion targets, severely affecting automated fruit-picking efficiency. This study addresses this problem by proposing the pioneering design of a multi-type occlusion apple dataset and an augmentation method of data balance. We divided apple occlusion into eight types and used the proposed method to balance the number of annotation boxes for multi-type occlusion apple targets. Finally, a validation experiment was carried out using five popular lightweight object detection models: yolox-s, yolov5-s, yolov4-s, yolov3-tiny, and efficidentdet-d0. The results show that, using the proposed augmentation method, the average detection precision of the five popular lightweight object detection models improved significantly. Specifically, the precision increased from 0.894 to 0.974, recall increased from 0.845 to 0.972, and mAP0.5 increased from 0.982 to 0.919 for yolox-s. This implies that the proposed augmentation method shows great potential for different fruit detection missions in future orchard applications.
2022 SEP
WOS:000851736900001
journalArticle
22
SENSORS
DOI 10.3390/s22186967
18
Jiang
Shuangshuai
Hao
Jinyu
Li
Han
Zuo
Changzhen
Geng
Xia
Sun
Xiaoyong
Monitoring Wheat Lodging at Various Growth Stages
Lodging is one of the primary factors that reduce wheat yield; therefore, rapid and accurate monitoring of wheat lodging helps to provide data support for crop loss and damage response and the subsequent settlement of agricultural insurance claims. In this study, we aimed to address two problems: (1) calculating the wheat lodging area. Through comparative experiments, the SegFormer-B1 model can achieve a better segmentation effect of wheat lodging plots with a higher prediction rate and a stronger generalization ability. This model has an accuracy of 96.56%, which realizes the accurate extraction of wheat lodging plots and the relatively precise calculation of the wheat lodging area. (2) Analyzing wheat lodging areas from various growth stages. The model established, based on the mixed-stage dataset, generally outperforms those set up based on the single-stage datasets in terms of the segmentation effect. The SegFormer-B1 model established based on the mixed-stage dataset, with its mIoU reaching 89.64%, was applicable to wheat lodging monitoring throughout the whole growth cycle of wheat.
2022 SEP
WOS:000858891700001
journalArticle
22
SENSORS
DOI 10.3390/s22176567
17
da Silva
Leandro Marcos
de Britto Menezes
Henrique Bonini
Luccas
Matheus dos Santos
Mailer
Christian
Roschildt Pinto
Alex Sandro
Boava
Adao
Rodrigues
Mariana
Ferrao
Isadora Garcia
Estrella
Julio Cezar
Jaquie Castelo Branco
Kalinka Regina Lucas
Development of an Efficiency Platform Based on MQTT for UAV Controlling and DoS Attack Detection
Several market sectors are attracted by the potential of unmanned aerial vehicles (UAVs), such as delivery, agriculture, and cinema, among others. UAVs are becoming part of Internet of Things (IoT) networks in the development of autonomous and scalable solutions. However, these vehicles are gradually becoming attractive targets for cyberattacks. This study proposes the development of an efficient platform based on the Message Queuing Telemetry Transport (MQTT) protocol for UAV control and Denial-of-Service (DoS) detection embedded in the UAV system. For the efficiency test, latency, network and memory consumption on the platform were measured, in addition to the correlation between payload and delay time. The results of efficiency tests were collected for the three levels of quality of service (QoS). A strong correlation greater than 90% was found between delay and data size for all QoS levels, showing almost a linear proportion. In DoS detection, the best results were a true positive rate (TPR) of 0.97 with 16 features from the AWID2 dataset using LightGBM with Bayesian optimization and data balancing. Unlike other studies, the built platform shows efficiency for UAV control and guarantees security in the communication with the broker and in the Wi-Fi UAV network.
2022 SEP
WOS:000851714600001
journalArticle
322
JOURNAL OF ENVIRONMENTAL MANAGEMENT
DOI 10.1016/j.jenvman.2022.116046
Latella
M.
Raimondo
T.
Belcore
E.
Salerno
L.
Camporeale
C.
On the integration of LiDAR and field data for riparian biomass estimation
The role of vegetation in supporting life on Earth is widely known. Nevertheless, the relevance of riparian corridors has been overlooked for a long time, leading to a dramatic reduction of vegetated buffers alongside them. Vegetation monitoring systems, including those for biomass estimation, are required to manage riparian corridors properly. Field surveys may support monitoring, but their usefulness is reduced by numerous draw-backs, therefore needing coupling with other data sources. The present work shows how Light Detection And Ranging (LiDAR) datasets can integrate targeted field measurements to estimate above-ground biomass at temperate or boreal latitudes and generate accurate biomass maps over large areas. By referring to the case study of the Orco river (northwest Italy), we defined a technique to reconstruct the geometry of an individual shrub from LiDAR point clouds. We tested the technique by comparing field measurements with Terrestrial and Airborne Laser Scanner data (TLS and ALS, respectively), assessing the former's superiority but the broader range of applicability of the latter. After these preliminary tests, we coupled the presented technique with a literature algorithm for individual tree detection, providing a more generalized procedure for the overall mapping and budgeting of riparian biomass based on ALS data. We applied the procedure to a fluvial bar of the Orco river, achieving a quantitative assessment of the shrub and tree biomass budget for 2019 and 2021 and visualizing the changes that occurred in that period. These results allowed us to shed light on the prevailing natural and anthropogenic processes in the investigated area and provide insights into the strengths and weaknesses of the proposed procedure.
2022 NOV 15
WOS:000860567200004
journalArticle
ENVIRONMENTAL SCIENCE AND POLLUTION RESEARCH
DOI 10.1007/s11356-022-22717-2
Oltramare
Christelle
Weiss
Frederik T.
Staudacher
Philipp
Kibirango
Oscar
Atuhaire
Aggrey
Stamm
Christian
Pesticides monitoring in surface water of a subsistence agricultural catchment in Uganda using passive samplers
Pesticides are intensely used in the agricultural sector worldwide including smallholder farming. Poor pesticide use practices in this agronomic setting are well documented and may impair the quality of water resources. However, empirical data on pesticide occurrence in water bodies of tropical smallholder agriculture is scarce. Many available data are focusing on apolar organochlorine compounds which are globally banned. We address this gap by studying the occurrence of a broad range of more modern pesticides in an agricultural watershed in Uganda. During 2.5 months of the rainy season in 2017, three passive sampler systems were deployed at five locations in River Mayanja to collect 14 days of composite samples. Grab samples were taken from drinking water resources. In these samples, 27 compounds out of 265 organic pesticides including 60 transformation products were detected. In the drinking water resources, we detected eight pesticides and two insecticide transformation products in low concentrations between 1 and 50 ng/L. Also, in the small streams and open fetch ponds, detected concentrations were generally low with a few exceptions for the herbicide 2,4-D and the fungicide carbendazim exceeding 1 ug/L. The widespread occurrence of chlorpyrifos posed the largest risk for macroinvertebrates. The extensive detection of this compound and its transformation product 3,4,5-trichloro-2-pyridinol was unexpected and called for a better understanding of the use and fate of this pesticide.
WOS:000852269700005
journalArticle
840
SCIENCE OF THE TOTAL ENVIRONMENT
DOI 10.1016/j.scitotenv.2022.156478
Hader
John D.
Lane
Taylor
Boxall
Alistair B. A.
MacLeod
Matthew
Di Guardo
Antonio
Enabling forecasts of environmental exposure to chemicals in European agriculture under global change
European agricultural development in the 21st century will be affected by a host of global changes, including climate change, changes in agricultural technologies and practices, and a shift towards a circular economy. The type and quantity of chemicals used, emitted, and cycled through agricultural systems in Europe will change, driven by shifts in the use patterns of pesticides, veterinary pharmaceuticals, reclaimed wastewater used for irrigation, and biosolids. Climate change will also impact the chemical persistence, fate, and transport processes that dictate environmental exposure. Here, we review the literature to identify research that will enable scenario-based forecasting of environmental exposures to organic chemicals in European agriculture under global change. Enabling exposure forecasts requires understanding current and possible future 1.) emissions, 2.) persistence and transformation, and 3.) fate and transport of agricultural chemicals. We discuss current knowledge in these three areas, the impact global change drivers may have on them, and we identify knowledge and data gaps that must be overcome to enable predictive scenario-based forecasts of environmental exposure under global change. Key research gaps identified are: improved understanding of relationships between global change and chemical emissions in agricultural settings; better understanding of environment-microbe interactions in the context of chemical degradation under future conditions; and better methods for downscaling climate change-driven intense precipitation events for chemical fate and transport modelling. We introduce a set of narrative Agricultural Chemical Exposure (ACE) scenarios - augmenting the IPCC's Shared Socio-economic Pathways (SSPs) - as a framework for forecasting chemical exposure in European agriculture. The proposed ACE scenarios cover a plausible range of optimistic to pessimistic 21st century development pathways. Filling the knowledge and data gaps identified within this study and using the ACE scenario approach for chemical exposure forecasting will support stakeholder planning and regulatory intervention strategies to ensure European agricultural practices develop in a sustainable manner.
2022 SEP 20
WOS:000816997600003
journalArticle
70
ENVIRONMENTAL MANAGEMENT
DOI 10.1007/s00267-022-01724-6
6
Datta
Pritha
Behera
Bhagirath
Factors Influencing the Feasibility, Effectiveness, and Sustainability of Farmers' Adaptation Strategies to Climate Change in The Indian Eastern Himalayan Foothills
The rapidly changing climatic conditions are adversely impacting the Indian agricultural sector. Farmers are frequently seen adopting several adaptation measures, which are neither equally efficient nor mutually exclusive. Based on the primary data collected from 300 farming households of the Indian Eastern Himalayan foothills, the present study attempts to examine the efficiency of local farmers' adaptation by developing indices combining the feasibility, effectiveness, and sustainability of the adaptation measures with the scale of actual adoption. Further, by employing multiple linear regression, the study analyzes the internal (psychological) and external (physical and socio-economic) factors influencing higher scores of these indices. Results show that local farmers are well aware of climate change and are responding through implementing at least one and up to seven adaptation measures. Farmers preferred agroforestry, a shift from cereals to low water-intensive commercials, irrigation, and intensification of winter crops as the most efficient. There was, however, a misalignment between the perceived efficiency of adaptation measures and their scale of adoption. Farmers' perceptions of pest infestation, satisfaction with farming, soil characteristics, farm size, remittances, and access to credit were found to be positively and significantly influencing the adaptation indices, while open-mindedness toward changing farming practices and crop-raiding by elephants were found to be negatively and significantly associated with adaptation indices. Lastly, the study made relevant recommendations for improving farmers' efficiency in adopting appropriate adaptation measures and strengthening the "State Action Plan on Climate Change".
2022 DEC
WOS:000859705100002
911-925
journalArticle
2022
COMPUTATIONAL INTELLIGENCE AND NEUROSCIENCE
DOI 10.1155/2022/2854675
Li
Xuelan
Li
Xiao
Jiang
Jiyu
Deep Intelligence-Driven Efficient Forecasting for the Agriculture Economy of Computational Social Systems
In the vision of smart cities, everything is highly connected with the aid of computational intelligence. Therefore, the cyber-physical society has been named a computational social system for a long time. Due to the high relation with vast populations' national livelihood, agriculture will still serve as a core industry in the national economy. As a result, this study focused on an efficient forecasting method for the agriculture economy. In recent years, the conception of deep intelligence has received overall prevalence in academia because of its excellent performance in implementing intelligent information processing tasks. Hence, this paper utilized deep intelligence driven by neural networks and managed to investigate an efficient prediction method for the agriculture economy of computational social systems. To fit the time-series forecasting scene of the long-term development of the agriculture economy, the convolutional neural network model is slightly improved by revising its parallel structure into the recurrent format. Finally, simulations on realistic datasets are carried out to evaluate the proposed forecasting method.
2022 SEP 27
WOS:000868633600001
journalArticle
12
SCIENTIFIC REPORTS
DOI 10.1038/s41598-022-20440-z
1
Li
Chaoqun
Wang
Liejun
Li
Yongming
Transformer and group parallel axial attention co-encoder for medical image segmentation
U-Net has become baseline standard in the medical image segmentation tasks, but it has limitations in explicitly modeling long-term dependencies. Transformer has the ability to capture long-term relevance through its internal self-attention. However, Transformer is committed to modeling the correlation of all elements, but its awareness of local foreground information is not significant. Since medical images are often presented as regional blocks, local information is equally important. In this paper, we propose the GPA-TUNet by considering local and global information synthetically. Specifically, we propose a new attention mechanism to highlight local foreground information, called group parallel axial attention (GPA). Furthermore, we effectively combine GPA with Transformer in encoder part of model. It can not only highlight the foreground information of samples, but also reduce the negative influence of background information on the segmentation results. Meanwhile, we introduced the sMLP block to improve the global modeling capability of network. Sparse connectivity and weight sharing are well achieved by applying it. Extensive experiments on public datasets confirm the excellent performance of our proposed GPA-TUNet. In particular, on Synapse and ACDC datasets, mean DSC(%) reached 80.37% and 90.37% respectively, mean HD95(mm) reached 20.55 and 1.23 respectively.
2022 SEP 27
WOS:000860850600088
journalArticle
22
SENSORS
DOI 10.3390/s22197440
19
Zhang
Jingzong
Cong
Shijie
Zhang
Gen
Ma
Yongjun
Zhang
Yi
Huang
Jianping
Detecting Pest-Infested Forest Damage through Multispectral Satellite Imagery and Improved UNet plus
Plant pests are the primary biological threats to agricultural and forestry production as well as forest ecosystem. Monitoring forest-pest damage via satellite images is crucial for the development of prevention and control strategies. Previous studies utilizing deep learning to monitor pest-infested damage in satellite imagery adopted RGB images, while multispectral imagery and vegetation indices were not used. Multispectral images and vegetation indices contain a wealth of useful information for detecting plant health, which can improve the precision of pest damage detection. The aim of the study is to further improve forest-pest infestation area segmentation by combining multispectral, vegetation indices and RGB information into deep learning. We also propose a new image segmentation method based on UNet++ with attention mechanism module for detecting forest damage induced by bark beetle and aspen leaf miner in Sentinel-2 images. The ResNeSt101 is used as the feature extraction backbone, and the attention mechanism scSE module is introduced in the decoding phase for improving the image segmentation results. We used Sentinel-2 imagery to produce a dataset based on forest health damage data gathered by the Ministry of Forests, Lands, Natural Resource Operations and Rural Development (FLNRORD) in British Columbia (BC), Canada, during aerial overview surveys (AOS) in 2020. The dataset contains the 11 original Sentinel-2 bands and 13 vegetation indices. The experimental results confirmed that the significance of vegetation indices and multispectral data in enhancing the segmentation effect. The results demonstrated that the proposed method exhibits better segmentation quality and more accurate quantitative indices with overall accuracy of 85.11%, in comparison with the state-of-the-art pest area segmentation methods.
2022 OCT
WOS:000867327200001
journalArticle
22
SENSORS
DOI 10.3390/s22197693
19
Pavelka
Karel
Raeva
Paulina
Pavelka
Karel, Jr.
Evaluating the Performance of Airborne and Ground Sensors for Applications in Precision Agriculture: Enhancing the Postprocessing State-of-the-Art Algorithm
The main goals of the following paper are to evaluate the performance of two multispectral airborne sensors and compare their image data with in situ spectral measurements. Moreover, the authors aim to present an enhanced workflow for processing multitemporal image data using both commercial and open-source solutions. The research was provoked by the need for a relevant comparison between airborne and ground sensors for vegetation analysis and monitoring. The research team used an eBee fixed-wing platform and the multiSPEC 4c and Sequoia sensors. The authors carried out field measurements using a handheld spectrometer by Trimble-GreenSeeker. There were two flight campaigns which took place near the village of Tuhan in the Czech Republic. The results from the first campaign were discouraging, showing less possibility in the correlation between the aerial and field data. The second campaign resulted in a very high percentage of correlation between both types of data. The researchers present the image processing steps and their enhanced photogrammetric workflow for multitemporal data which helps experts and nonprofessionals to reduce their processing time.
2022 OCT
WOS:000867150600001
journalArticle
22
SENSORS
DOI 10.3390/s22207707
20
Li
Xia
Su
Junhao
Yue
Zhenchao
Duan
Fangtao
Adaptive Multi-ROI Agricultural Robot Navigation Line Extraction Based on Image Semantic Segmentation
Automated robots are an important part of realizing sustainable food production in smart agriculture. Agricultural robots require a powerful and precise navigation system to be able to perform tasks in the field. Aiming at the problems of complex image background, as well as weed and light interference factors of the visual navigation system in field and greenhouse environments, a Faster-U-net model that retains the advantages of the U-net model feature jump connection is proposed. Based on the U-net model, pruning and optimization were carried out to predict crop ridges. Firstly, a corn dataset was trained to obtain the weight of the corn dataset. Then, the training weight of the obtained corn dataset was used as the pretraining weight for the cucumber, wheat, and tomato datasets, respectively. The three datasets were trained separately. Finally, the navigation line between ridges and the yaw angle of the robot were generated by B-spline curve fitting. The experimental results showed that the parameters of the improved path segmentation model were reduced by 65.86%, and the mPA was 97.39%. The recognition accuracy MIoU of the Faster-U-net model for maize, tomatoes, cucumbers, and wheat was 93.86%, 94.01%, 93.14%, and 89.10%, respectively. The processing speed of the single-core CPU was 22.32 fps/s. The proposed method had strong robustness in predicting rows of different crops. The average angle difference of the navigation line under a ridge environment such as that for corn, tomatoes, cucumbers, or wheat was 0.624 degrees, 0.556 degrees, 0.526 degrees, and 0.999 degrees, respectively. This research can provide technical support and reference for the research and development of intelligent agricultural robot navigation equipment in the field.
2022 OCT
WOS:000873550800001
journalArticle
19
INTERNATIONAL JOURNAL OF ENVIRONMENTAL RESEARCH AND PUBLIC HEALTH
DOI 10.3390/ijerph191911923
19
Li
Lipeng
Sarkar
Apurbo
Zhou
Xi
Ding
Xiuling
Li
Hua
Influence and Action Mechanisms of Governmental Relations Embeddedness for Fostering Green Production Demonstration Household: Evidence from Shaanxi, Sichuan, and Anhui Province, China
As an innovative tactic, the core aspects of green products should be comprehensively demonstrated and firmly promoted to enhance their adoption. For doing so, continuous governmental support and interventions through distinct sets of networking and relationships could be crucial for synthesizing and diffusing the extent of green production demonstration households. Interestingly, the structural relationship between these two has not yet been evaluated comprehensively by the existing literature. Therefore, the study empirically analyzes the impact and mechanism of government relationships embedded in fostering green production demonstration households. The study compiles the empirical data from 963 farmers which were collected from the major tea-producing areas of Shaanxi, Sichuan, and Anhui provinces, China. In order to craft the findings, first we constructed the ordered Probit for benchmark regression analysis. Meanwhile, the Ordinary Standard Error Ordered Probit model, Ordered Logit model, and multivariate linear model were constructed for the robustness test. Third, the Extended Ordered Probit model and Bootstrap mediation effect model were used to test the path diagram. Finally, robustness testing and endogeneity processing test were used to explore the reliability of the findings. The results showed that: (i) Government relationship embedding has a positive effect on fostering green production demonstration households. In particular, factors such as relationships with general government staff, professional and technical personnel, and village cadre are most significant. (ii) Seemingly, the heterogeneity analysis shows that the farmers with large operating scales and low family economic status have a relatively stronger impact. (iii) Further mechanism research results show that government relations are embedded through government identification (policy identification, government trust), improving farmers' behavioral ability (production knowledge reserve, self-efficacy), and strengthening farmers' perceived value of green production (self-interest perception, altruistic values). Therefore, the government should strengthen the interactive mechanism embedded with farm households and extend support for green production demonstration zones. The farmers' information-sharing facilities and platforms should be modernized and highlighted according to the local conditions and long-term targeted strategies.
2022 OCT
WOS:000866810500001
journalArticle
22
SENSORS
DOI 10.3390/s22207778
20
Finochietto
Mariano
Santos
Rodrigo
Ochoa
Sergio F.
Meseguer
Roc
Reducing Operational Expenses of LoRaWAN-Based Internet of Remote Things Applications
LoRaWAN has become the most widely used low-power wide-area network technology to implement monitoring solutions based on the Internet of remote things (IoRT) paradigm. Typically, these solutions interconnect remote sensing areas and data processing infrastructure located in urban centers. The operation expenses of these solutions depend mainly on the traffic sent through the network backhaul, i.e., the link that connects the remote sensing area and the urban area where the data are usually processed and stored. This service is provided by telecommunication companies and represents the main operation cost of IoRT solutions. These expenses usually limit the affordability of IoRT-based systems in developing countries, and also in scenarios where the operational cost is an issue to address. This paper presents an extension to the LoRaWAN protocol, named Node-Aware-LoRaWAN (NA-LoRaWAN), that reduces the traffic in the backhaul, thus decreasing the operational expenses of IoRT-based systems. In order to evaluate the performance of NA-LoRaWAN, it was compared to a regular LoRaWAN implementation. Depending on the network scenario, the proposed extension reduced the traffic through the backhaul in the range of 12-34%. This extension opens several opportunities to use IoRT solutions in application domains with a low operational budget, e.g., precision agriculture, environmental monitoring and natural hazards' early detection.
2022 OCT
WOS:000873616000001
journalArticle
152
Journal of Nutrition
DOI 10.1093/jn/nxac132
10
Haghparast-Bidgoli
Hassan
Harris-Fry
Helen
Kumar
Abhinav
Pradhan
Ronali
Mishra
Naba Kishore
Padhan
Shibananth
Ojha
Amit Kumar
Mishra
Sailendra Narayan
Fivian
Emily
James
Philip
Ferguson
Sarah
Krishnan
Sneha
O'Hearn
Meghan
Palmer
Tom
Koniz-Booher
Peggy
Danton
Heather
Minovi
Sandee
Mohanty
Satyanarayan
Rath
Shibanand
Rath
Suchitra
Nair
Nirmala
Tripathy
Prasanta
Prost
Audrey
Allen
Elizabeth
Skordis
Jolene
Kadiyala
Suneetha
Economic Evaluation of Nutrition-Sensitive Agricultural Interventions to Increase Maternal and Child Dietary Diversity and Nutritional Status in Rural Odisha, India
Background: Economic evaluations of nutrition-sensitive agriculture (NSA) interventions are scarce, limiting assessment of their potential affordability and scalability.Objectives: We conducted cost-consequence analyses of 3 participatory video-based interventions of fortnightly women's group meetings using the following platforms: 1) NSA videos; 2) NSA and nutrition-specific videos; or 3) NSA videos with a nutrition-specific participatory learning and action (PLA) cycle.Methods: Interventions were tested in a 32-mo, 4-arm cluster-randomized controlled trial, Upscaling Participatory Action and Videos for Agriculture and Nutrition (UPAVAN) in the Keonjhar district, Odisha, India. Impacts were evaluated in children aged 0-23 mo and their mothers. We estimated program costs using data collected prospectively from expenditure records of implementing and technical partners and societal costs using expenditure assessment data collected from households with a child aged 0-23 mo and key informant interviews. Costs were adjusted for inflation, discounted, and converted to 2019 US$.Results:Total program costs of each intervention ranged from US$272,121 to US$386,907 Program costs per pregnant woman or mother of a child aged 0-23 mo were US$62 for NSA videos, US$84 for NSA and nutrition-specific videos, and US$78 for NSA videos with PLA (societal costs: US$125, US$143, and US$122, respectively). Substantial shares of total costs were attributable to development and delivery of the videos and PLA (52-69%) and quality assurance (25-41 %). Relative to control, minimum dietary diversity was higher in the children who underwent the interventions incorporating nutrition-specific videos and PLA (adjusted RRs: 1.19 and 1.27; 95% CIs: 1.03-1.37 and 1.11, 1.46, respectively). Relative to control, minimum dietary diversity in mothers was higher in those who underwent NSA video (1.21 [1.01, 1.45]) and NSA with PLA (1.30 [1.10, 1.53]) interventions.Conclusion: NSA videos with PLA can increase both maternal and child dietary diversity and have the lowest cost per unit increase in diet diversity. Building on investments made in developing UPAVAN, cost-efficiency at scale could be increased with less intensive monitoring, reduced startup costs, and integration within existing government programs.
2022
BCI:BCI202200865305
journalArticle
12
SCIENTIFIC REPORTS
DOI 10.1038/s41598-022-19750-z
1
Rajasivaranjan
T.
Anandhi
Aavudai
Patel
N. R.
Irannezhad
Masoud
Srinivas
C., V
Veluswamy
Kumar
Surendran
U.
Raja
P.
Integrated use of regional weather forecasting and crop modeling for water stress assessment on rice yield
This study evaluated the effects of water stress on rice yield over Punjab and Haryana across North India by integrating Weather Research Forecasting (WRF) and Decision Support System for Agrotechnology Transfer (DSSAT) models. Indian Remote Sensing Satellite datasets were used to define land use/land cover in WRF. The accuracy of simulated rainfall and temperature over Punjab and Haryana was evaluated against Tropical Rainfall Measuring Mission and automated weather station data of Indian Space Research Organization, respectively. Data from WRF was used as weather input to DSSAT to simulate rice yield in Punjab and Haryana for 2009 and 2014. After simulated yield has been evaluated against district-level observed yield, the water balance components within the DSSAT model were used to analyze the impact of water stress on rice yield. The correlation (R-2) between the crop water stress factor and the rice yield anomaly at the vegetative and reproductive stage was 0.64 and 0.52 for Haryana and 0.73 and 0.68 for Punjab, respectively. Severe water stress during the flowering to maturity stage inflicted devastating effects on yield. The study concludes that the regional climate simulations can be potentially used for early water stress prediction and its impact on rice yield.
2022 OCT 10
WOS:000865806900029
journalArticle
INTEGRATIVE ZOOLOGY
DOI 10.1111/1749-4877.12683
Dawson
Stuart J.
Kreplins
Tracey L.
Kennedy
Malcolm S.
Renwick
Juanita
Cowan
Mark A.
Fleming
Patricia A.
Land use and dingo baiting are correlated with the density of kangaroos in rangeland systems
Rangelands worldwide have been subject to broadscale modification, such as widespread predator control, introduction of permanent livestock water and altered vegetation to improve grazing. In Australia, these landscape changes have resulted in kangaroos (i.e. large macropods) populations increasing over the past 200 years. Kangaroos are a key contributor to total grazing pressure and in conjunction with livestock and feral herbivores have been linked to land degradation. We used 22 years of aerial survey data to investigate whether the density of 3 macropod species in the southern rangelands of Western Australia was associated with: (i) land use, including type of livestock, total livestock, density of feral goats, type of land tenure, and kangaroo commercial harvest effort; (ii) predator management, including permitted dingo control effort, estimated dingo abundance, and presence of the State Barrier Fence (a dingo exclusion fence); and (iii) environmental variables: ruggedness, rainfall, fractional cover, and total standing dry matter. Red kangaroos (Osphranter rufus) were most abundant in flat, open vegetation, on pastoral land, where area permitted for dingo control was high, and numbers were positively associated with antecedent rainfall with a 12-month delay. Western grey kangaroos (Macropus fuliginosus) were most abundant on flat, agricultural land, but less abundant in areas with high permitted dingo control. Euros (Osphranter robustus) were most abundant in rugged pastoral land with open vegetation, where permitted dingo control was high. While environmental variables are key drivers of landscape productivity and kangaroo populations, anthropogenic factors such as land use and permitted dingo control are strongly associated with kangaroo abundance.
WOS:000866106800001
journalArticle
41
ENVIRONMENTAL TOXICOLOGY AND CHEMISTRY
DOI 10.1002/etc.5479
12
Collins
Jennifer K.
Jackson
Jennifer M.
Application of a Screening-Level Pollinator Risk Assessment Framework to Trisiloxane Polyether Surfactants
Regulatory requirements exist to assess the potential impacts of pesticides on insect pollinators, but "inert," coformulants to pesticide formulations are not included in standard regulatory risk assessments. Some publications in the open literature have suggested that the agricultural uses of "inert" ingredients, including trisiloxane polyether surfactants, may result in adverse effects on pollinators. We conducted a screening-level risk assessment to evaluate the potential risk to insect pollinators, using honey bees (Apis mellifera) as a surrogate, from exposure to three trisiloxane polyether surfactants based on agricultural application scenarios following the current US Environmental Protection Agency (USEPA) guidance. The exposure assessment included data from two sources: (1) use data reported in California's (USA) Pesticide Use Registry (PUR) database for all crops, and (2) an almond orchard residue study conducted using the three trisiloxane polyether surfactants. Honey bee laboratory studies with each of the trisiloxane polyether surfactants reported 50% lethal doses (LD50s) or no adverse effect levels, which were used as the effects inputs to BeeREX. The exposure and toxicity data were combined to estimate potential honey bee risk based on the determination of acute and chronic risk quotients (RQs) for larval and adult life stages. The RQs calculated using both the PUR use rates as well as the application rates and peak measured residues from the almond orchard residue study were below the USEPA acute and chronic levels of concern (acute, 0.4; chronic, 1.0). Based on these results, the use of these three trisiloxane polyether surfactants in agricultural use settings can be considered minimal risk to insect pollinators, and higher tier assessment is unnecessary for the characterization of risk. Environ Toxicol Chem 2022;00:1-11. (c) 2022 The Authors. Environmental Toxicology and Chemistry published by Wiley Periodicals LLC on behalf of SETAC.
2022 DEC
WOS:000870286700001
3084-3094
journalArticle
9
SCIENTIFIC DATA
DOI 10.1038/s41597-022-01761-0
1
Cheng
Minghan
Jiao
Xiyun
Shi
Lei
Penuelas
Josep
Kumar
Lalit
Nie
Chenwei
Wu
Tianao
Liu
Kaihua
Wu
Wenbin
Jin
Xiuliang
High-resolution crop yield and water productivity dataset generated using random forest and remote sensing
Accurate and high-resolution crop yield and crop water productivity (CWP) datasets are required to understand and predict spatiotemporal variation in agricultural production capacity; however, datasets for maize and wheat, two key staple dryland crops in China, are currently lacking. In this study, we generated and evaluated a long-term data series, at 1-km resolution of crop yield and CWP for maize and wheat across China, based on the multiple remotely sensed indicators and random forest algorithm. Results showed that MOD16 products are an accurate alternative to eddy covariance flux tower data to describe crop evapotranspiration (maize and wheat RMSE: 4.42 and 3.81 mm/8d, respectively) and the proposed yield estimation model showed accuracy at local (maize and wheat rRMSE: 26.81 and 21.80%, respectively) and regional (maize and wheat rRMSE: 15.36 and 17.17%, respectively) scales. Our analyses, which showed spatiotemporal patterns of maize and wheat yields and CWP across China, can be used to optimize agricultural production strategies in the context of maintaining food security.
2022 OCT 21
WOS:000871048600001
journalArticle
19
INTERNATIONAL JOURNAL OF ENVIRONMENTAL RESEARCH AND PUBLIC HEALTH
DOI 10.3390/ijerph192214870
22
Yu
Yuanhe
Lin
Jinkuo
Zhou
Peixiang
Zheng
Shuwei
Li
Zijun
Cultivated Land Input Behavior of Different Types of Rural Households and Its Impact on Cultivated Land-Use Efficiency: A Case Study of the Yimeng Mountain Area, China
Analyzing cultivated land input behavior (CLIB) at the scale of rural households links with cultivated land-use efficiency (CLUE), this study examined the Yimeng Mountain area in northern China, supported by field survey data from 737 rural households. This research systematically analyzed the characteristics of CLIB of different types of rural households, measured the CLUE of different types of rural households by using a data envelopment analysis (DEA) model, and explored the influence of CLIB on CLUE based on the Tobit regression model. The results show (1) significant differences in the characteristics of the CLIB of different types of rural households in the Yimeng Mountain area. Among them, the highest land, labor, and capital inputs were I part-time rural households (I PTRH), followed by full-time rural households (FTRH). In contrast, II part-time rural households (II PTRH) and non-agricultural rural households (NARH) had higher levels of non-agricultural employment; however, their input levels gradually declined. (2) The CLUE of the sample rural households was generally low and had considerable potential for improvement. Regarding the types of rural households, as the degree of part-time employment increased, the CLUE showed an inverted U-shaped trend of first increased and then decreased, namely, I PTRH > FTRH > II PTRH > NARH. This finding indicates that appropriate part-time employment could help to promote investment in agricultural production and improve the CLUE. (3) The CLIB of rural households had significant effects on CLUE; the literacy of the agricultural labor force, yield-increasing input per unit area, per capita household income, share of agricultural income, operation scale of cultivated land, effective irrigation rate of cultivated land, and soil and water conservation rate of cultivated land had positive effects on improving CLUE. Even so, there was still significant heterogeneity in the degree of influence of different rural household types. The study concluded with some policy recommendations from the perspective of different rural household types to provide references for optimizing farming inputs and improving CLUE.
2022 NOV
WOS:000887183100001
journalArticle
19
INTERNATIONAL JOURNAL OF ENVIRONMENTAL RESEARCH AND PUBLIC HEALTH
DOI 10.3390/ijerph192113866
21
Pan
Yi
Yuan
Qiqi
Ma
Jinsong
Wang
Lachun
Improved Daily Spatial Precipitation Estimation by Merging Multi-Source Precipitation Data Based on the Geographically Weighted Regression Method: A Case Study of Taihu Lake Basin, China
Accurately estimating the spatial and temporal distribution of precipitation is crucial for hydrological modeling. However, precipitation products based on a single source have their advantages and disadvantages. How to effectively combine the advantages of different precipitation datasets has become an important topic in developing high-quality precipitation products internationally in recent years. This paper uses the measured precipitation data of Multi-Source Weighted-Ensemble Precipitation (MSWEP) and in situ rainfall observation in the Taihu Lake Basin, as well as the longitude, latitude, elevation, slope, aspect, surface roughness, distance to the coastline, and land use and land cover data, and adopts a two-step method to achieve precipitation fusion: (1) downscaling the MSWEP source precipitation field using the bilinear interpolation method and (2) using the geographically weighted regression (GWR) method and tri-cube function weighting method to achieve fusion. Considering geographical and human activities factors, the spatial and temporal distribution of precipitation errors in MSWEP is detected. The fusion of MSWEP and gauge observation precipitation is realized. The results show that the method in this paper significantly improves the spatial resolution and accuracy of precipitation data in the Taihu Lake Basin.
2022 NOV
WOS:000881258200001
journalArticle
22
SENSORS
DOI 10.3390/s22218418
21
Ogawa
Satoshi
Yamamoto
Kyosuke
Uno
Kenichi
Nguyen Cong Thuan
Togami
Takashi
Shindo
Soji
Optimal Water Level Management for Mitigating GHG Emissions through Water-Conserving Irrigation in An Giang Province, Vietnam
Rational water and fertilizer management approaches and technologies could improve water use efficiency and fertilizer use efficiency in paddy rice cultivation. A promising water-conserving technology for paddy rice farming is the alternate wetting and drying irrigation system, established by the International Rice Research Institute. However, the strategy has still not been widely adopted, because water level measurement is challenging work and sometimes leads to a decrease in the rice yield. For the easy implementation of alternate wetting and drying among farmers, we analyzed a dataset obtained from a farmer's water management study carried out over a three-year period with three cropping seasons at six locations (n = 82) in An Giang Province, Southern Vietnam. We observed a significant relationship between specific water level management and the rice yield and greenhouse gas emissions during different growth periods. The average water level during the crop period was an important factor in increasing the rice yield and reducing greenhouse gas emissions. The average water level at 2 days after nitrogen fertilization also showed a potential to increase the rice yield. The greenhouse gas emissions were reduced when the number of days of non-flooded soil use was increased by 1 day during the crop period. The results offer insights demonstrating that farmers' implementation of multiple drainage during whole crop period and nitrogen fertilization period has the potential to contribute to both the rice yield increase and reduction in greenhouse gas emissions from rice cultivation.
2022 NOV
WOS:000883577800001
journalArticle
22
SENSORS
DOI 10.3390/s22228911
22
Lee
Saebom
Choi
Gyuho
Park
Hyun-Cheol
Choi
Chang
Automatic Classification Service System for Citrus Pest Recognition Based on Deep Learning
Plant diseases are a major cause of reduction in agricultural output, which leads to severe economic losses and unstable food supply. The citrus plant is an economically important fruit crop grown and produced worldwide. However, citrus plants are easily affected by various factors, such as climate change, pests, and diseases, resulting in reduced yield and quality. Advances in computer vision in recent years have been widely used for plant disease detection and classification, providing opportunities for early disease detection, and resulting in improvements in agriculture. Particularly, the early and accurate detection of citrus diseases, which are vulnerable to pests, is very important to prevent the spread of pests and reduce crop damage. Research on citrus pest disease is ongoing, but it is difficult to apply research results to cultivation owing to a lack of datasets for research and limited types of pests. In this study, we built a dataset by self-collecting a total of 20,000 citrus pest images, including fruits and leaves, from actual cultivation sites. The constructed dataset was trained, verified, and tested using a model that had undergone five transfer learning steps. All models used in the experiment had an average accuracy of 97% or more and an average f1 score of 96% or more. We built a web application server using the EfficientNet-b0 model, which exhibited the best performance among the five learning models. The built web application tested citrus pest disease using image samples collected from websites other than the self-collected image samples and prepared data, and both samples correctly classified the disease. The citrus pest automatic diagnosis web system using the model proposed in this study plays a useful auxiliary role in recognizing and classifying citrus diseases. This can, in turn, help improve the overall quality of citrus fruits.
2022 NOV
WOS:000887660500001
journalArticle
22
SENSORS
DOI 10.3390/s22218256
21
Dac
Hai Ho
Gonzalez Viejo
Claudia
Lipovetzky
Nir
Tongson
Eden
Dunshea
Frank R.
Fuentes
Sigfredo
Livestock Identification Using Deep Learning for Traceability
Farm livestock identification and welfare assessment using non-invasive digital technology have gained interest in agriculture in the last decade, especially for accurate traceability. This study aimed to develop a face recognition system for dairy farm cows using advanced deep-learning models and computer vision techniques. This approach is non-invasive and potentially applicable to other farm animals of importance for identification and welfare assessment. The video analysis pipeline follows standard human face recognition systems made of four significant steps: (i) face detection, (ii) face cropping, (iii) face encoding, and (iv) face lookup. Three deep learning (DL) models were used within the analysis pipeline: (i) face detector, (ii) landmark predictor, and (iii) face encoder. All DL models were finetuned through transfer learning on a dairy cow dataset collected from a robotic dairy farm located in the Dookie campus at The University of Melbourne, Australia. Results showed that the accuracy across videos from 89 different dairy cows achieved an overall accuracy of 84%. The computer program developed may be deployed on edge devices, and it was tested on NVIDIA Jetson Nano board with a camera stream. Furthermore, it could be integrated into welfare assessment previously developed by our research group.
2022 NOV
WOS:000882185500001
journalArticle
19
INTERNATIONAL JOURNAL OF ENVIRONMENTAL RESEARCH AND PUBLIC HEALTH
DOI 10.3390/ijerph192316159
23
Tang
Ying
Chen
Menghan
The Impact Mechanism and Spillover Effect of Digital Rural Construction on the Efficiency of Green Transformation for Cultivated Land Use in China
Under the context of digital economy, agricultural production will be promoted by implementing the strategy of digital rural construction and giving full play to the role of digital factor productivity. This study systematically explains the mechanism of how digital rural construction affects the efficiency of green transformation for cultivated land use. The panel data of 30 provinces in China from 2011 to 2020 are analyzed through two-way fixed effect, spatial Dubin model and other methods, so as to better understand the impact of digital rural construction on the efficiency of green transformation for cultivated land use and its spillover effect. It is discovered in the study that digital rural construction is effective in enhancing the efficiency of green transformation for regional cultivated land use, and that this promoting effect stands multiple robustness tests. According to the heterogeneity analysis, the promoting effect of digital rural construction is more significant in the eastern region and among the samples with high green transformation efficiency of cultivated land use. In addition to improving the efficiency of green transformation for cultivated land use in the region, digital rural construction can also produce a positive spatial spillover effect to a significant extent. On this basis, the targeted policy recommendations are made in this paper. The first one is to improve the efficiency of green transformation for cultivated land use by accelerating the process of digital rural construction. The second one is to pay close attention to the differences in the process of digital rural construction. The third one is to better understand the "welfare sharing" characteristics of digital rural construction. The last one is to establish a mechanism of regional cooperation.
2022 DEC
WOS:000896521700001
journalArticle
194
ENVIRONMENTAL MONITORING AND ASSESSMENT
DOI 10.1007/s10661-022-10532-8
12
Swain
Sabyasachi
Mishra
Surendra Kumar
Pandey
Ashish
Dayal
Deen
Assessment of drought trends and variabilities over the agriculture-dominated Marathwada Region, India
Drought is considered among the most perilous events with catastrophic consequences, particularly from the agro-economic point of view. These consequences are expected to exacerbate under the increasing meteorological aberrations due to changing climate, which necessitates investigating drought variabilities. This study presents a thorough spatiotemporal assessment of drought trends and variabilities over the agriculture-dominated Marathwada Region, Maharashtra, India. The precipitation data is extracted from the India Meteorological Department (IMD) gridded product, whereas actual evapotranspiration (ET) and Evaporative Stress Index (ESI) are obtained from Global Land Evaporation Amsterdam Model (GLEAM) datasets. Standardized Precipitation Index (SPI) is used to characterize drought occurrences at multiple time frames, whereas non-parametric tests, i.e., modified Mann-Kendall (MMK) and Sen's slope (SS) tests, are employed to detect trends. The results reveal the region to be prone to droughts, and SPI at a longer time frame (i.e., 12-monthly moving frame) can capture drought occurrences better than the shorter time frames, which can be attributed to the lesser randomness in the time series in the longer frame. A mix of positive/negative trends of SPI series are found for the monsoonal months; however, they are relatively more concentrated towards negative Z(MMK). Hence, the Marathwada Region can be inferred to have exhibited a relatively increased tendency towards drought occurrences. The seasonal differences in mean values and trends of rainfall, ET, and ESI are discussed in detail. Since the Marathwada Region has a monsoon-dominated climate with high agricultural importance, the information reported in this study will help in devising water management strategies to minimize the repercussions of droughts.
2022 DEC
WOS:000873717300005
journalArticle
194
ENVIRONMENTAL MONITORING AND ASSESSMENT
DOI 10.1007/s10661-022-10534-6
12
Swain
Sabyasachi
Mishra
Surendra Kumar
Pandey
Ashish
Dayal
Deen
Srivastava
Prashant Kumar
Appraisal of historical trends in maximum and minimum temperature using multiple non-parametric techniques over the agriculture-dominated Narmada Basin, India
In this study, the long-term trends in climatological parameters, viz., maximum temperature (T-MAX) and minimum temperature (T-MIN), are determined over 68 years (i.e., June 1951 to May 2019) using the gridded observation datasets (1 degrees x 1 degrees spatial resolution) of India Meteorological Department over the Narmada river basin, India. Multiple non-parametric techniques, viz., modified Mann-Kendall (MMK), Sen's slope (SS), and Spearman's rho (SR) tests, are used to determine monthly, seasonal, and annual trends over individual grids. The trends are also analyzed for the climatic variables spatially averaged over the entire basin to draw general conclusions on historical climate change. The results reveal a significant spatiotemporal variation in trends of T-MAX and T-MIN over the basin. In general, both the parameters are found to be increasing. Furthermore, the hottest months (April and May) have become hotter, and the coldest month (January) has become colder, implying a higher probability of increasing temperature extremes. Furthermore, the entire duration of 68 years is divided into two epochs of 34 years, i.e., 1951-1984 and 1985-2018, and the trend analysis of T-MAX and T-MIN is also carried out epoch-wise to better understand/assess the signals of climate change in recent years. In general, a relatively higher warming trend was observed in the latter epoch. As a majority of the basin area is dominated by agricultural lands, the implications of the temperature trends and their impacts on agriculture are succinctly discussed. The information reported in this study will be helpful for proper planning and management of water resources over the basin under the changing climatic conditions.
2022 DEC
WOS:000868388400004
journalArticle
22
SENSORS
DOI 10.3390/s22239270
23
Liu
Xiangpeng
Wang
Danning
Li
Yani
Guan
Xiqiang
Qin
Chengjin
Detection of Green Asparagus Using Improved Mask R-CNN for Automatic Harvesting
Advancements in deep learning and computer vision have led to the discovery of numerous effective solutions to challenging problems in the field of agricultural automation. With the aim to improve the detection precision in the autonomous harvesting process of green asparagus, in this article, we proposed the DA-Mask RCNN model, which utilizes the depth information in the region proposal network. Firstly, the deep residual network and feature pyramid network were combined to form the backbone network. Secondly, the DA-Mask RCNN model added a depth filter to aid the softmax function in anchor classification. Afterwards, the region proposals were further processed by the detection head unit. The training and test images were mainly acquired from different regions in the basin of the Yangtze River. During the capturing process, various weather and illumination conditions were taken into account, including sunny weather, sunny but overshadowed conditions, cloudy weather, and daytime greenhouse conditions as well as nighttime greenhouse conditions. Performance experiments, comparison experiments, and ablation experiments were carried out using the five constructed datasets to verify the effectiveness of the proposed model. Precision, recall, and F1-score values were applied to evaluate the performances of different approaches. The overall experimental results demonstrate that the balance of the precision and speed of the proposed DA-Mask RCNN model outperform those of existing algorithms.
2022 DEC
WOS:000896435000001
journalArticle
194
ENVIRONMENTAL MONITORING AND ASSESSMENT
DOI 10.1007/s10661-022-10509-7
12
Kuleli
Tuncay
Bayazit
Seyma
Land cover change detection in the Turkish coastal zone based on 28-year (1990-2018) Corine data
In this research, land cover changes in the coastal region of Turkey were analyzed using the Corine dataset between 1990 and 2018. Changes in each period were analyzed by using the rate of change and the annual rate of change, the transition matrix of net changes, and the transition probability matrix. In order to predict land cover change trends and to determine future land cover change probabilities, a combination of Markov and cellular automata models was used. It was determined that the highest increase in each study period was in artificial surfaces and the highest decrease was in the forest and the semi-natural area. The total forest areas were converted to the other land cover type in the first study period amounting to 2479.32 km(2). Also, it was decreased and transformed by about 62.47 km(2), 118.82 km(2), and 203.09 km(2) of the forest area that existed in the second, third, and fourth periods respectively. The results indicate that the probabilities of the increasing area will be covered by artificial surfaces and agricultural areas. It is estimated that the rate of 57% in 1990, the initial year of the forest areas, will decrease to 53.4% in 2034 and to 53% in 2050. Also, the rate of 2.1% in 1990, the initial year of the artificial surfaces, will increase to 4.5% in 2034 and to 5.0% in 2050. It is seen that more artificial surfaces will be needed in the Turkish coastal region due to the increasing population and number of tourists. It is important to evaluate and investigate the coastal areas where more artificial areas are expected to be needed within the scope of the coastal area management plans to be prepared at the national scale.
2022 DEC
WOS:000862561100001
journalArticle
19
INTERNATIONAL JOURNAL OF ENVIRONMENTAL RESEARCH AND PUBLIC HEALTH
DOI 10.3390/ijerph192316046
23
Dai
Shubing
Ma
Yulei
Zhang
Kuandi
Land Degradation Caused by Construction Activity: Investigation, Cause and Control Measures
The rapid expansion of construction land has been a common phenomenon worldwide, which resulted in the loss of high-quality arable land and severe land degradation. Here, a statistical analysis, together with a field investigation, was carried out in China to address the challenges. This study has gathered data on the reduction of land amount and quality caused by construction activities and has collected the relevant policies to control land deterioration caused by those activities. The increasing amount of farmland and open space are occupied by construction use. The annual growth of construction land from 2001 to 2017 was 43.64 x 10(4) hm(2), with an annual average of about 38 x 10(4) hm(2) of cultivated land being converted to construction land in China. Construction activities usually cause a deterioration of the physico-chemical properties in and around construction site soils. The organic matter of post-construction soil was lower than the pre-construction by 257.4 similar to 879.8%. A lack of strong economic incentives for developers, limited effectiveness of measures to control land degradation, and weak requirements and enforcement of relevant laws and regulations allow land degradation from construction activities to remain at a significant level. For more efficiency and success, the study proposes effective measures to control the hazards that occur so widely in China.
2022 DEC
WOS:000896160700001
journalArticle
22
SENSORS
DOI 10.3390/s22239469
23
Cai
Hao
Song
Zhiguang
Xu
Jianlong
Xiong
Zhi
Xie
Yuanquan
CUDM: A Combined UAV Detection Model Based on Video Abnormal Behavior
The widespread use of unmanned aerial vehicles (UAVs) has brought many benefits, particularly for military and civil applications. For example, UAVs can be used in communication, ecological surveys, agriculture, and logistics to improve efficiency and reduce the required workforce. However, the malicious use of UAVs can significantly endanger public safety and pose many challenges to society. Therefore, detecting malicious UAVs is an important and urgent issue that needs to be addressed. In this study, a combined UAV detection model (CUDM) based on analyzing video abnormal behavior is proposed. CUDM uses abnormal behavior detection models to improve the traditional object detection process. The work of CUDM can be divided into two stages. In the first stage, our model cuts the video into images and uses the abnormal behavior detection model to remove a large number of useless images, improving the efficiency and real-time detection of suspicious targets. In the second stage, CUDM works to identify whether the suspicious target is a UAV or not. Besides, CUDM relies only on ordinary equipment such as surveillance cameras, avoiding the use of expensive equipment such as radars. A self-made UAV dataset was constructed to verify the reliability of CUDM. The results show that CUDM not only maintains the same accuracy as state-of-the-art object detection models but also reduces the workload by 32%. Moreover, it can detect malicious UAVs in real-time.
2022 DEC
WOS:000897524600001
journalArticle
195
ENVIRONMENTAL MONITORING AND ASSESSMENT
DOI 10.1007/s10661-022-10557-z
1
Koley
Swadhina
Jeganathan
C.
Evaluating the climatic and socio-economic influences on the agricultural drought vulnerability in Jharkhand
Environmental hazards like drought lead to degrading food production and adversely impact the agro-economy. This study investigates the contributions of different climatic and socio-economic variables to agricultural drought in Jharkhand. The three primary criteria, i.e., exposure (E), sensitivity (S), and adaptive capacity (AC), responsible for agricultural drought vulnerability, were examined to identify the drought-prone areas. Long-term (1958-2020) gridded climatic datasets obtained from the Terra-climate global dataset, MODIS vegetation index dataset (MOD13Q1) for the years 2001-2020, different soil parameters obtained from the ISRIC global soil database and state agricultural portal of Jharkhand, and different socio-economic datasets obtained from census data (2011) provided by Govt. of India, were utilized for this study. Analytic Hierarchy Process (AHP) was used to estimate the weighted contribution of the indicator variables falling under each criterion (E, S, and AC), and three criteria index maps were generated. These separate maps were further integrated to generate the final vulnerability index map. Finally, the study area was categorized into different zones based on the drought vulnerability index value ranging from 0 to 1, according to the severity of the drought. It was observed that about 4.05%, 28.12%, and 37.07% of the total geographical area is very highly, highly, and moderately vulnerable to agricultural drought, respectively. Amongst the three primary criteria, exposure showed a significant positive correlation (R = 0.61), and sensitivity showed a strong positive correlation (R = 0.55) with vulnerability. The adaptive capacity was negatively correlated (R = -0.75) with the vulnerability. However, putting equal weights to the variables to calculate the vulnerability, the exposure and sensitivity indicators showed a significant positive correlation with the vulnerability, with an R-value of 0.82 and 0.79, respectively. In contrast, the adaptive capacity showed a negative correlation with the vulnerability with R = -0.75.
2023 JAN
WOS:000871077800005
journalArticle
36
Ecological Indicators
DOI 10.1016/j.ecolind.2013.01.017
Cotter
M.
Berkhoff
K.
Gibreel
T.
Ghorbani
A.
Golbon
R.
Nuppenau
E.-A.
Sauerborn
J.
Designing a sustainable land use scenario based on a combination of ecological assessments and economic optimization
2014
Scopus
https://www.scopus.com/inward/record.uri?eid=2-s2.0-84889079469&doi=10.1016%2fj.ecolind.2013.01.017&partnerID=40&md5=f72e03849c609d567cde5f10c096afff
779-787
journalArticle
140
Soil and Tillage Research
DOI 10.1016/j.still.2014.02.004
Mota
J.C.A.
Alves
C.V.O.
Freire
A.G.
de Assis Júnior
R.N.
Uni and multivariate analyses of soil physical quality indicators of a Cambisol from Apodi Plateau - CE, Brazil
2014
Scopus
https://www.scopus.com/inward/record.uri?eid=2-s2.0-84896335340&doi=10.1016%2fj.still.2014.02.004&partnerID=40&md5=9b086a8270160c50a1fd5b5e3bcdd3b8
66-73
journalArticle
78
Journal of Wildlife Management
DOI 10.1002/jwmg.677
3
Kniowski
A.B.
Gehrt
S.D.
Home range and habitat selection of the Indiana bat in an agricultural landscape
2014
Scopus
https://www.scopus.com/inward/record.uri?eid=2-s2.0-84898058045&doi=10.1002%2fjwmg.677&partnerID=40&md5=927bd66ea13ec49ca5e3fd4c98bf0289
503-512
journalArticle
57
Transactions of the ASABE
DOI 10.13031/trans.57.10079
1
Moore
K.D.
Young
E.
Gurell
C.
Wojcik
M.D.
Martin
R.S.
Bingham
G.E.
Pfeiffer
R.L.
Prueger
J.H.
Hatfield
J.L.
Ammonia measurements and emissions from a california dairy using point and remote sensors
2014
Scopus
https://www.scopus.com/inward/record.uri?eid=2-s2.0-84898639183&doi=10.13031%2ftrans.57.10079&partnerID=40&md5=4118b3c49f8ff26528c21237ffcdbc89
181-198
journalArticle
230-231
Geoderma
DOI 10.1016/j.geoderma.2014.04.019
Askari
M.S.
Holden
N.M.
Indices for quantitative evaluation of soil quality under grassland management
2014
Scopus
https://www.scopus.com/inward/record.uri?eid=2-s2.0-84899845470&doi=10.1016%2fj.geoderma.2014.04.019&partnerID=40&md5=11bd8e1a6fdba8ff0f6559747730bdb2
131-142
journalArticle
64
Acta Agriculturae Scandinavica Section B: Soil and Plant Science
DOI 10.1080/09064710.2014.901407
3
Luo
Y.
Zhao
X.
Andrén
O.
Soil organic carbon in relation to cultivation in arable and greenhouse cropping systems in Lanzhou, NW China
2014
Scopus
https://www.scopus.com/inward/record.uri?eid=2-s2.0-84900336566&doi=10.1080%2f09064710.2014.901407&partnerID=40&md5=84e9f01a378297b96ac025ed6bd9d538
203-210
journalArticle
13
Vadose Zone Journal
DOI 10.2136/vzj2013.09.0167
7
De Troyer
I.
Merckx
R.
Amery
F.
Smolders
E.
Factors controlling the dissolved organic matter concentration in pore waters of agricultural soils
2014
Scopus
https://www.scopus.com/inward/record.uri?eid=2-s2.0-84904060122&doi=10.2136%2fvzj2013.09.0167&partnerID=40&md5=7b0eb8085b4ed6ce1e7e4873e2f698c5
journalArticle
143
Soil and Tillage Research
DOI 10.1016/j.still.2014.02.006
Kuncoro
P.H.
Koga
K.
Satta
N.
Muto
Y.
A study on the effect of compaction on transport properties of soil gas and water I: Relative gas diffusivity, air permeability, and saturated hydraulic conductivity
2014
Scopus
https://www.scopus.com/inward/record.uri?eid=2-s2.0-84904796308&doi=10.1016%2fj.still.2014.02.006&partnerID=40&md5=718e2201018511d735c97348b26bab81
172-179
journalArticle
47
Ecological Indicators
DOI 10.1016/j.ecolind.2014.05.019
Guo
S.
Shen
G.Q.
Chen
Z.-M.
Yu
R.
Embodied cultivated land use in China 1987-2007
2014
Scopus
https://www.scopus.com/inward/record.uri?eid=2-s2.0-84909946377&doi=10.1016%2fj.ecolind.2014.05.019&partnerID=40&md5=873f89016d47516441cfab55d83324ba
198-209
journalArticle
48
Silva Fennica
DOI 10.14214/sf.1207
4
Tikkanen
O.-P.
Chernyakova
I.A.
Past human population history affects current forest landscape structure of Vodlozero National Park, Northwest Russia
2014
Scopus
https://www.scopus.com/inward/record.uri?eid=2-s2.0-84916244558&doi=10.14214%2fsf.1207&partnerID=40&md5=5fc869ffd54c1feb41a7050d9304093d
journalArticle
214-215
Geoderma
DOI 10.1016/j.geoderma.2013.09.022
Debaene
G.
Niedźwiecki
J.
Pecio
A.
Zurek
A.
Effect of the number of calibration samples on the prediction of several soil properties at the farm-scale
2014
Scopus
https://www.scopus.com/inward/record.uri?eid=2-s2.0-84888206009&doi=10.1016%2fj.geoderma.2013.09.022&partnerID=40&md5=49161142ac010bc7366e648fa5bdd68d
114-125
journalArticle
1
Information Processing in Agriculture
DOI 10.1016/j.inpa.2014.06.002
1
Kulicki
P.
Trypuz
R.
Trójczak
R.
Wierzbicki
J.
Woźniak
A.
Semantic representation of proved and disproved statements extracted from scientific papers: Meat science case study
2014
Scopus
https://www.scopus.com/inward/record.uri?eid=2-s2.0-85016824103&doi=10.1016%2fj.inpa.2014.06.002&partnerID=40&md5=c785a24b398d1cd0b27482b308eb89e8
66-72
journalArticle
72
Environmental Earth Sciences
DOI 10.1007/s12665-014-3353-z
11
de Paul Obade
V.
Lal
R.
Soil quality evaluation under different land management practices
2014
Scopus
https://www.scopus.com/inward/record.uri?eid=2-s2.0-84920708155&doi=10.1007%2fs12665-014-3353-z&partnerID=40&md5=15f3c513e555ccf2f0addaf35404ddf6
4531-4549
journalArticle
263
Geoderma
DOI 10.1016/j.geoderma.2015.03.010
Winowiecki
L.
Vågen
T.-G.
Huising
J.
Effects of land cover on ecosystem services in Tanzania: A spatial assessment of soil organic carbon
2014
Scopus
https://www.scopus.com/inward/record.uri?eid=2-s2.0-84946472291&doi=10.1016%2fj.geoderma.2015.03.010&partnerID=40&md5=4291dab40d707791707c18ed0901f62e
274-283
journalArticle
61
Forest Science
DOI 10.5849/forsci.13-071
1
Zhou
X.
Schoeneberger
M.M.
Brandle
J.R.
Awada
T.N.
Chu
J.
Martin
D.L.
Li
J.
Li
Y.
Mize
C.W.
Analyzing the uncertainties in use of forest-derived biomass equations for open-grown trees in agricultural land
2015
Scopus
https://www.scopus.com/inward/record.uri?eid=2-s2.0-84922810360&doi=10.5849%2fforsci.13-071&partnerID=40&md5=85e0efef2d602db1893c43932444cc43
144-161
journalArticle
18
International Food and Agribusiness Management Review
1
Ross
K.L.
Zereyesus
Y.A.
Shanoyan
A.
Amanor-Boadu
V.
The health effects of women empowerment: Recent evidence from northern Ghana
2015
Scopus
https://www.scopus.com/inward/record.uri?eid=2-s2.0-84923043952&partnerID=40&md5=40fd183faca94b9e00d24dea8f04a00b
127-144
journalArticle
7
Agris On-line Papers in Economics and Informatics
DOI 10.7160/aol.2015.070106
1
Řezník
T.
Lukas
V.
Charvát
K.
Horáková
S.
Charvát
K.
Towards farm-oriented open data in Europe: The scope and pilots of the European project "foodie"
2015
Scopus
https://www.scopus.com/inward/record.uri?eid=2-s2.0-84928389007&doi=10.7160%2faol.2015.070106&partnerID=40&md5=cddf4e5e89b93fae2da75c0a30afc515
51-58
journalArticle
8
International Journal of Agricultural and Biological Engineering
DOI 10.3965/j.ijabe.20150803.950
3
Mittelstet
A.R.
Storm
D.E.
Stoecker
A.L.
Using swat and empirical relationship to simulate crop yields and salinity levels in the North Fork River Basin
2015
Scopus
https://www.scopus.com/inward/record.uri?eid=2-s2.0-84928791639&doi=10.3965%2fj.ijabe.20150803.950&partnerID=40&md5=854878e0c019f88edc59454c4638e241
1-15
journalArticle
58
Transactions of the ASABE
DOI 10.13031/trans.58.10892
2
Endale
D.M.
Schomberg
H.H.
Fisher
D.S.
Jenkins
M.B.
Curve numbers from conventional and no-till cropping: A 39-year dataset from a small Georgia Piedmont watershed
2015
Scopus
https://www.scopus.com/inward/record.uri?eid=2-s2.0-84929175817&doi=10.13031%2ftrans.58.10892&partnerID=40&md5=130f2ae21ea1a81224f5b3e380603680
379-391
journalArticle
8
Advance Journal of Food Science and Technology
DOI 10.19026/ajfst.8.1555
7
Zhou
L.
The impact of RMB exchange rate on agricultural food prices in emerging market
2015
Scopus
https://www.scopus.com/inward/record.uri?eid=2-s2.0-84936939481&doi=10.19026%2fajfst.8.1555&partnerID=40&md5=64cc98e976dc76c0abfa3300fc0c749d
505-510
journalArticle
58
Transactions of the ASABE
DOI 10.13031/trans.58.11105
4
Vadas
P.A.
Good
L.W.
Panuska
J.C.
Busch
D.L.
Larson
R.A.
A new model for phosphorus loss in runoff from outdoor cattle lots
2015
Scopus
https://www.scopus.com/inward/record.uri?eid=2-s2.0-84941296191&doi=10.13031%2ftrans.58.11105&partnerID=40&md5=bf35e9ee25fd138579a7a53021e98f3f
1035-1045
journalArticle
53
Soil Research
DOI 10.1071/SR15100
8
Liddicoat
C.
Maschmedt
D.
Clifford
D.
Searle
R.
Herrmann
T.
Macdonald
L.M.
Baldock
J.
Predictive mapping of soil organic carbon stocks in South Australia's agricultural zone
2015
Scopus
https://www.scopus.com/inward/record.uri?eid=2-s2.0-84946553648&doi=10.1071%2fSR15100&partnerID=40&md5=8627b247c750eb957b19139a94282398
956-973
journalArticle
53
Soil Research
DOI 10.1071/SR14268
8
Kidd
D.
Webb
M.
Malone
B.
Minasny
B.
McBratney
A.
Eighty-metre resolution 3D soil-attribute maps for Tasmania, Australia
2015
Scopus
https://www.scopus.com/inward/record.uri?eid=2-s2.0-84946574750&doi=10.1071%2fSR14268&partnerID=40&md5=9c3871c88f52063483d7245f330c3b47
932-955
journalArticle
58
Transactions of the ASABE
DOI 10.13031/trans.58.10968
6
Brown-Brandl
T.M.
Eigenberg
R.A.
Determination of minimum meal interval and analysis of feeding behavior in shaded and open-lot feedlot heifers
2015
Scopus
https://www.scopus.com/inward/record.uri?eid=2-s2.0-84953889321&doi=10.13031%2ftrans.58.10968&partnerID=40&md5=5be319affe91f1fbfc5eb54b20be712c
1833-1839
journalArticle
8
International Journal of Agricultural and Biological Engineering
DOI 10.3965/j.ijabe.20150806.1312
6
Shi
L.
Duan
Q.G.
Si
H.P.
Qiao
H.B.
Zhang
J.J.
Ma
X.M.
Approach of hybrid soft computing for agricultural data classification
2015
Scopus
https://www.scopus.com/inward/record.uri?eid=2-s2.0-84962006668&doi=10.3965%2fj.ijabe.20150806.1312&partnerID=40&md5=108fc8d52914f65a3f30c6a2c47542d8
54-61
journalArticle
200
Agricultural and Forest Meteorology
DOI 10.1016/j.agrformet.2014.09.016
Ruane
A.C.
Goldberg
R.
Chryssanthacopoulos
J.
Climate forcing datasets for agricultural modeling: Merged products for gap-filling and historical climate series estimation
2015
Scopus
https://www.scopus.com/inward/record.uri?eid=2-s2.0-84908516700&doi=10.1016%2fj.agrformet.2014.09.016&partnerID=40&md5=bd5768170d14e5e692eadb2af411bdeb
233-248
journalArticle
7
China Agricultural Economic Review
DOI 10.1108/CAER-05-2014-0052
1
Zhang
D.
Chen
C.
Sheng
Y.
Public investment in agricultural R&D and extension: An analysis of the effects on Australian broadacre farming productivity
2015
Scopus
https://www.scopus.com/inward/record.uri?eid=2-s2.0-84921407271&doi=10.1108%2fCAER-05-2014-0052&partnerID=40&md5=bb850f1bc097cf2568bb5a31b29fe774
86-101
journalArticle
150
Agricultural Water Management
DOI 10.1016/j.agwat.2014.11.008
Valverde
P.
de Carvalho
M.
Serralheiro
R.
Maia
R.
Ramos
V.
Oliveira
B.
Climate change impacts on rainfed agriculture in the Guadiana river basin (Portugal)
2015
Scopus
https://www.scopus.com/inward/record.uri?eid=2-s2.0-84916918904&doi=10.1016%2fj.agwat.2014.11.008&partnerID=40&md5=1d95c00c4b9b23f101b2e9209e25e16c
35-45
journalArticle
150
Agricultural Water Management
DOI 10.1016/j.agwat.2014.12.008
Turunen
M.
Warsta
L.
Paasonen-Kivekäs
M.
Nurminen
J.
Alakukku
L.
Myllys
M.
Koivusalo
H.
Effects of terrain slope on long-term and seasonal water balances in clayey, subsurface drained agricultural fields in high latitude conditions
2015
Scopus
https://www.scopus.com/inward/record.uri?eid=2-s2.0-84922612171&doi=10.1016%2fj.agwat.2014.12.008&partnerID=40&md5=f6dc0a9cd5d9e68ef95ee918950a712c
139-151
journalArticle
113
Computers and Electronics in Agriculture
DOI 10.1016/j.compag.2015.01.009
Wang
Y.
Wang
Y.
Wang
J.
Yuan
Y.
Zhang
Z.
An ontology-based approach to integration of hilly citrus production knowledge
2015
Scopus
https://www.scopus.com/inward/record.uri?eid=2-s2.0-84922382440&doi=10.1016%2fj.compag.2015.01.009&partnerID=40&md5=7438d8187c06e7a94c631fa78b3ffc81
24-43
journalArticle
73
Environmental Earth Sciences
DOI 10.1007/s12665-014-3642-6
7
Paul
D.
Choudhary
B.
Gupta
T.
Jose
M.T.
Spatial distribution and the extent of heavy metal and hexavalent chromium pollution in agricultural soils from Jajmau, India
2015
Scopus
https://www.scopus.com/inward/record.uri?eid=2-s2.0-84924733803&doi=10.1007%2fs12665-014-3642-6&partnerID=40&md5=9dd662164c237190e50f13176b91783c
3565-3577
journalArticle
154
Agricultural Water Management
DOI 10.1016/j.agwat.2015.02.011
De Jong van Lier
Q.
Wendroth
O.
van Dam
J.C.
Prediction of winter wheat yield with the SWAP model using pedotransfer functions: An evaluation of sensitivity, parameterization and prediction accuracy
2015
Scopus
https://www.scopus.com/inward/record.uri?eid=2-s2.0-84925835145&doi=10.1016%2fj.agwat.2015.02.011&partnerID=40&md5=cd7954b8025fef067a99f7e11107b3ab
29-42
journalArticle
162
Remote Sensing of Environment
DOI 10.1016/j.rse.2015.01.024
Gaber
A.
Soliman
F.
Koch
M.
El-Baz
F.
Using full-polarimetric SAR data to characterize the surface sediments in desert areas: A case study in El-Gallaba Plain, Egypt
2015
Scopus
https://www.scopus.com/inward/record.uri?eid=2-s2.0-84923246664&doi=10.1016%2fj.rse.2015.01.024&partnerID=40&md5=68cbbea7066a51ffa8a50c975a71ed8c
11-28
journalArticle
92
American Journal of Potato Research
DOI 10.1007/s12230-015-9435-y
3
Navarro
F.M.
Rak
K.T.
Banks
E.
Bowen
B.D.
Higgins
C.
Palta
J.P.
Strategies for Selecting Stable Common Scab Resistant Clones in a Potato Breeding Program
2015
Scopus
https://www.scopus.com/inward/record.uri?eid=2-s2.0-84931577893&doi=10.1007%2fs12230-015-9435-y&partnerID=40&md5=7f552d1adc6bad06b37d30ab0dcb6b53
326-338
journalArticle
150
Soil and Tillage Research
DOI 10.1016/j.still.2015.01.013
Awe
G.O.
Reichert
J.M.
Wendroth
O.O.
Temporal variability and covariance structures of soil temperature in a sugarcane field under different management practices in southern Brazil
2015
Scopus
https://www.scopus.com/inward/record.uri?eid=2-s2.0-84922427004&doi=10.1016%2fj.still.2015.01.013&partnerID=40&md5=47ba4e186cea5767c9fb4ecff51a6066
93-106
journalArticle
7
IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
DOI 10.1109/JSTARS.2013.2260727
1
IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
ISSN 2151-1535
T. F. Stepinski
P. Netzel
J. Jasiewicz
Remote sensing
Geospatial analysis
Visualization
Databases
Servers
Computerized maps
Context
GeoWeb services
Histograms
land cover datasets
pattern-based similarity
LandEx—A GeoWeb Tool for Query and Retrieval of Spatial Patterns in Land Cover Datasets
The vast amount of data collected by satellites via remote sensing is a valuable resource, however, it lacks machine search capabilities. In particular, large land cover datasets, such as the 30-m/cell NLCD 2006 covering the entire conterminous United States, are rarely analyzed as a whole due to the lack of tools beyond the basic statistics and SQL queries. Consequently, the NLCD is underutilized relative to its potential. We address this issue by introducing LandEx-a GeoWeb application for real time, content-based exploration and mining of land cover patterns in large datasets. By combining the functionality of online computerized maps with the power of the pattern recognition algorithm, LandEx provides an easy to use visual search engine for the entire extent of the NLCD at its full resolution. The user selects a pattern of interest (a query) and the tool produces a similarity map indicating the spatial distribution of locations having patterns of land cover similar to that in the query. Pattern-based query and retrieval addresses the issue of structural similarity between landscapes. The core of the method is the similarity function between two patterns which is based on 2D land cover class/clump size histograms and the Jensen-Shannon divergence. The search relies on exhaustive evaluation using an overlapping sliding window approach. LandEx is implemented using Free Open Source Software (FOSS) software and adheres to the Open Geospatial Consortium (OGC) standards. The wait time for an answer to a query is only several seconds due to the high level of system optimization. The methodology and implementation of LandEx are described in detail and illustrative examples of its application to different domains, including agriculture, forestry, and urbanization are given.
Jan. 2014
257-266
journalArticle
4
IEEE Robotics and Automation Letters
DOI 10.1109/LRA.2019.2894468
2
IEEE Robotics and Automation Letters
ISSN 2377-3766
C. Potena
R. Khanna
J. Nieto
R. Siegwart
D. Nardi
A. Pretto
Agriculture
Visualization
Standards
Three-dimensional displays
Image reconstruction
Mapping
Multi-Robot Systems
Robotics in Agriculture and Forestry
Simultaneous localization and mapping
AgriColMap: Aerial-Ground Collaborative 3D Mapping for Precision Farming
The combination of aerial survey capabilities of unmanned aerial vehicles (UAVs) with targeted intervention abilities of agricultural unmanned ground vehicles (UGVs) can significantly improve the effectiveness of robotic systems applied to precision agriculture. In this context, building and updating a common map of the field is an essential but challenging task. The maps built using robots of different types show differences in size, resolution, and scale, the associated geolocation data may be inaccurate and biased while the repetitiveness of both visual appearance and geometric structures found within agricultural contexts render classical map merging techniques ineffective. In this letter, we propose AgriColMap, a novel map registration pipeline that leverages a grid-based multimodal environment representation, which includes a vegetation index map and a digital surface model. We cast the data association problem between maps built from UAVs and UGVs as a multimodal, large displacement dense optical flow estimation. The dominant, coherent flows, selected using a voting scheme, are used as point-to-point correspondences to infer a preliminary nonrigid alignment between the maps. A final refinement is then performed, by exploiting only meaningful parts of the registered maps. We evaluate our system using real-world data for three fields with different crop species. The results show that our method outperforms several state-of-the-art map registration and matching techniques by a large margin, and has a higher tolerance to large initial misalignments. We release an implementation of the proposed approach along with the acquired datasets with this letter.
April 2019
1085-1092
journalArticle
A. Mukherjee
S. Misra
N. S. Raghuwanshi
S. Mitra
Monitoring
Agriculture
Wireless sensor networks
Cloud computing
Internet of Things
Servers
Agricultural Internet of Things (IoT)
green computing
multilayer perceptron (MLP)
payload compression
Blind Entity Identification for Agricultural IoT Deployments
Integration of various technologies to an Internet of Things (IoT) framework share the common goals of a consistent and structured data format that can be applied to any device, given the vast application scope of IoT. Additional goals include minimizing channel traffic and system energy consumption. In this paper, we propose to dismiss the requirement of certain seemingly crucial identifier fields from packets arriving through various sensor nodes in an agricultural IoT deployment. The proposed approach reduces packet size, thereby reducing channel traffic and energy consumption, as well as retaining the capability of identifying these originating nodes. We propose a method of a blind agricultural IoT node and sensor identification, which can be sourced and operated from a master node as well as a remote server. Additionally, this scheme has the capability of detecting the radio link quality between the master and slave nodes in a rudimentary form, as well as identifying the sensor nodes. We successfully trained and tested various multilayer perceptron-based models for blind identification, in real-time, using our implemented agricultural IoT implementation. The effect of changes in learning rate and momentum of the optimizer on the accuracy of classification is also studied. The projected cumulative energy savings across the network architecture, of our scheme, in conjunction with TCP/IP header compression techniques, are substantial. For a 100 node deployment using a combination of the proposed blind identification reduced sampling strategies over regular IPv4-based TCP/IP connection, an estimated annual saving of ≈99% is projected.
April 2019
3156-3163
6
IEEE Internet of Things Journal
DOI 10.1109/JIOT.2018.2879454
2
IEEE Internet of Things Journal
ISSN 2327-4662
journalArticle
8
IEEE Access
DOI 10.1109/ACCESS.2020.3025035
IEEE Access
ISSN 2169-3536
F. Cen
X. Zhao
W. Li
F. Zhu
Convolutional neural networks
Principal component analysis
Training
Task analysis
Robustness
Faces
image classification
Dictionaries
Image coding
occlusion
principal component analysis
SDBE
Classification of Occluded Images for Large-Scale Datasets With Numerous Occlusion Patterns
Large-scale image datasets with numerous occlusion patterns prevail in real applications. The classification scheme based on subspace decomposition-based estimation with squared $l_{2}$ -norm regularization (SDBE_L2) has shown promising performance for the classification of partially occluded images. For the large-scale image datasets with numerous occlusion patterns, it however suffers from a high labor intensity in acquiring extra image pairs and a large consumption of computational resources in the training stage. To reduce the labor intensity, this paper enumerates several useful types of extra image pairs to guide the collection of extra images and introduces an intra-class random pairing method to semi-automatically form the extra image pairs. To alleviate the consumption of computational resources, this paper proposes two dictionary compression approaches: 1) uncentered PCA-based single partition compression (UPSPC), which compresses the dictionary to a size not larger than twice the column vector length without affecting the classification accuracy, and 2) uncentered PCA-based intra-class partition compression (UPIPC), which can further shrink the occlusion error dictionary (or class dictionary) when it has a small number of occlusion classes (or image classes). The proposed approaches are based on the property of SDBE_L2 being invariant to the uncentered PCA of sub-dictionaries. The extensive experiments on the Caltech-101 dataset and Oxford-102 flower dataset demonstrate the enumerated examples and the intra-class random pairing method facilitate acquiring the extra images and forming the extra image pairs only with a small loss in the classification accuracy. The experimental results on a large-scale occluded image dataset synthesized from the ILSVRC 2012 classification dataset with numerous occlusion patterns show that the proposed dictionary compression approaches reduce the dictionary size by over 11 times and shorten the training time by more than 39 times without loss in the classification accuracy.
2020
170883-170897
journalArticle
7
IEEE Access
DOI 10.1109/ACCESS.2019.2899940
IEEE Access
ISSN 2169-3536
L. Zhang
G. Gui
A. M. Khattak
M. Wang
W. Gao
J. Jia
Feature extraction
Agriculture
Task analysis
Detectors
automated robot
cascaded convolutional networks
Face detection
Fruit detection
real-time
Sorting
Multi-Task Cascaded Convolutional Networks Based Intelligent Fruit Detection for Designing Automated Robot
Effective and efficient fruit detection is considered crucial for designing automated robot (AuRo) for yield estimation, disease control, harvesting, sorting, and grading. Several fruit detection schemes for designing AuRo have been developed during the last decades. However, conventional fruit detection methods are deficient in the real-time response, accuracy, and extensibility. This paper proposes an improved multi-task cascaded convolutional network-based intelligent fruit detection method. This method has the capability to make the AuRo work in real time with high accuracy. Moreover, based on the relationship between the diversity samples of the dataset and the parameters of neural networks’ evolution, this paper presents an improved augmented method, a procedure that is based on image fusion to improve the detector performance. The experiment results demonstrated that the proposed detector performed immaculately both in terms of accuracy and time–cost. Furthermore, the extensive experiment also demonstrated that the proposed technique has the capacity and good portability to work with other akin objects conveniently.
2019
56028-56038
journalArticle
3
IEEE Robotics and Automation Letters
DOI 10.1109/LRA.2018.2849498
4
IEEE Robotics and Automation Letters
ISSN 2377-3766
P. A. Dias
A. Tabb
H. Medeiros
Image color analysis
Image resolution
Training
Agriculture
Image segmentation
Task analysis
precision agriculture
Semantics
Bloom intensity estimation
flower detection
semantic segmentation networks
Multispecies Fruit Flower Detection Using a Refined Semantic Segmentation Network
In fruit production, critical crop management decisions are guided by bloom intensity, i.e., the number of flowers present in an orchard. Despite its importance, bloom intensity is still typically estimated by means of human visual inspection. Existing automated computer vision systems for flower identification are based on hand-engineered techniques that work only under specific conditions and with limited performance. This letter proposes an automated technique for flower identification that is robust to uncontrolled environments and applicable to different flower species. Our method relies on an end-to-end residual convolutional neural network (CNN) that represents the state-of-the-art in semantic segmentation. To enhance its sensitivity to flowers, we fine-tune this network using a single dataset of apple flower images. Since CNNs tend to produce coarse segmentations, we employ a refinement method to better distinguish between individual flower instances. Without any preprocessing or dataset-specific training, experimental results on images of apple, peach, and pear flowers, acquired under different conditions demonstrate the robustness and broad applicability of our method.
Oct. 2018
3003-3010
journalArticle
9
IEEE Access
DOI 10.1109/ACCESS.2021.3112272
IEEE Access
ISSN 2169-3536
Y. Nakayama
Task analysis
Sensors
Data privacy
Resource management
Costs
Crowdsensing
Crowdsourcing
mobile applications
mobile communication
mobile computing
Privacy
Horizontal Integrated Framework for Mobile Crowdsensing
Mobile crowdsensing is a promising paradigm to leverage the power of people to collect large-scale spatially distributed data. This concept has been intensely studied to efficiently and securely complete sensing tasks at lower cost. The development of a unified platform designed to provide various types of sensing applications is among the major approaches to economical crowdsourcing. However, existing previous frameworks were not optimized for shared use among multiple organizers because they were largely vertically integrated systems. Security and user trust and confidence is also a significant issue a crowdsensing frameworks, given the potential security concerns. Therefore, in this study, we propose a network-side task allocation (NeSTA) framework to address the existing problems in mobile crowdsensing. The proposed framework enables the horizontal integration of sensing applications, in which mobile networks mediate communication among organizers and participants, significantly reducing the installation cost of individual applications. Privacy preservation is achieved by task distribution and allocation procedures, where the participants were obscured by organizers. The validity of the proposed NeSTA was confirmed by simulations with an analytical model using an open dataset. The results show that the proposed method exhibited computational efficiency over two orders of magnitude greater than the conventional approach. This advantage originates from the reduction of problem size by dividing the original problem into subproblems.
2021
127630-127643
journalArticle
15
IEEE Geoscience and Remote Sensing Letters
DOI 10.1109/LGRS.2017.2789120
3
IEEE Geoscience and Remote Sensing Letters
ISSN 1558-0571
I. Del’Arco Sanches
R. Q. Feitosa
P. M. Achanccaray Diaz
M. Dias Soares
A. J. Barreto Luiz
B. Schultz
L. E. Pinheiro Maurano
remote sensing
synthetic aperture radar (SAR)
Artificial satellites
Earth
Remote sensing
Soil
Cotton
Databases
Agricultural mapping/monitoring
double cropping systems
free available database
tropical agriculture
Campo Verde Database: Seeking to Improve Agricultural Remote Sensing of Tropical Areas
In tropical/subtropical regions, the favorable climate associated with the use of agricultural technologies, such as no tillage, minimum cultivation, irrigation, early varieties, desiccants, flowering inducing, and crop rotation, makes agriculture highly dynamic. In this letter, we present the Campo Verde agricultural database. The purpose of creating and sharing these data is to foster advancement of remote sensing technology in areas of tropical agriculture, primarily the development and testing of methods for crop recognition and agricultural mapping. Campo Verde is a municipality of Mato Grosso state, localized in the Cerrado (Brazilian Savanna) biome, in central west Brazil. Soybean, maize, and cotton are the primary crops cultivated in this region. Double cropping systems are widely adopted in this area. There is also livestock and forestry production. Our database provides the land-use classes for 513 fields by month for one Brazilian crop year (between October 2015 and July 2016). This information was gathered during two field campaigns in Campo Verde (December 2015 and May 2016) and by visual interpretation of a time series of Landsat-8/Operational Land Imager (OLI) images using an experienced interpreter. A set of 14 preprocessed synthetic aperture radar Sentinel-1 and 15 Landsat-8/OLI mosaic images is also made available. It is important to promote the use of radar data for tropical agricultural applications, especially because the use of optical remote sensing in these regions is hindered by the high frequency of cloud cover. To demonstrate the utility of our database, results of an experiment conducted using the Sentinel-1 data set are presented.
March 2018
369-373
journalArticle
7
IEEE Access
DOI 10.1109/ACCESS.2019.2942158
IEEE Access
ISSN 2169-3536
N. Li
X. Zhang
C. Zhang
H. Guo
Z. Sun
X. Wu
Feature extraction
Robots
Agriculture
convolutional neural networks
Image segmentation
Computational modeling
Visualization
Soil
crop recognition
Precision agriculture
visual attention
weed control
Real-Time Crop Recognition in Transplanted Fields With Prominent Weed Growth: A Visual-Attention-Based Approach
Crop recognition is one of the key processes for robotic weeding in precision agriculture, which remains an open problem due to the unstructured field environment and the wide variety of plant species. It becomes especially challenging when the weeds are prominent and overlap with the crop plants. This paper presents a novel method for recognizing crop plants of field images with a high weed presence. This method segments crop plants from overlapped weeds based on the visual attention mechanism of the human visual system using a convolutional neural network. The network utilizes ResNet-10 as backbone, while introducing side outputs and short connections for multi-scale feature fusion. The Adaptive Affinity Fields method is adopted to improve the segmentation at object boundaries and for fine structures. To train and test the network, a field image dataset has been created which consists of 788 color images with manually segmented annotations. The images are captured under challenging conditions with extremely high weed pressure. The experimental results show that the proposed method can accurately segment crops from weeds and soil, with mean absolute errors less than 0.005 and F-measure scores exceeding 97%. In terms of efficiency, the proposed method can process up to 169 images per second when accelerated by a NVIDIA RTX 2080Ti graphics processing unit (GPU), and operate at approximately 5.6 Hz in a Jetson TX2 embedded computer. The results indicate that the proposed method has the potential to provide an efficient solution for recognizing crop plants, even in the presence of severe weed growth. The code and the dataset are available at https://github.com/ZhangXG001/Real-Time-Crop-Recognition.
2019
185310-185321
journalArticle
8
IEEE Access
DOI 10.1109/ACCESS.2020.3022763
IEEE Access
ISSN 2169-3536
S. S. L. Chukkapalli
S. Mittal
M. Gupta
M. Abdelsalam
A. Joshi
R. Sandhu
K. Joshi
artificial intelligence
Agriculture
Ecosystems
Computer science
Cloud computing
precision agriculture
Sensors
Cooperative smart farming
cyber-physical systems
Ontologies
ontology
Ontologies and Artificial Intelligence Systems for the Cooperative Smart Farming Ecosystem
Cyber-Physical Systems (CPS) and Internet of Thing (IoT) generate large amounts of data spurring the rise of Artificial Intelligence (AI) based smart applications. Driven by rapid advancements in technologies that support smart devices, agriculture and farming sector is shifting towards IoT connected ecosystem to balance the increase in demand for food supply. As the number of smart farms reach critical mass, it is now possible to include AI assisted systems at a cooperative (co-op) farming level. Today, in the United States alone there are about 1,871 co-ops serving 1,890,057 member farmers. Hence, such advanced technologies and infrastructure when incorporated in the co-op farming ecosystem can immensely benefit small member farmers who operate and maintain these independent co-op entities. In this paper, we develop a connected cooperative ecosystem which defines sensors and their communication among different entities along with cloud supported co-op hub. We develop member farm and co-op ontologies to capture data and various interactions that happen between shared resources, member farms, and the co-op that are stored in the cloud. These can then help generate AI supported insights for farmers and the cooperative. Several co-op farming use case scenarios have been discussed to demonstrate the functioning of our smart cooperative ecosystem. Finally, the paper describes various AI applications that can be deployed at the co-op level to aid member farmers.
2020
164045-164064
journalArticle
12
IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
DOI 10.1109/JSTARS.2019.2918947
8
IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
ISSN 2151-1535
A. Davitt
G. Schumann
C. Forgotson
K. C. McDonald
Microwave radiometry
Soil moisture
Earth
Ocean temperature
Land surface
soil moisture (SM)
Flood monitoring
freeze-thaw (FT)
National Oceanic and Atmospheric Administration (NOAA)
North Dakota Agricultural Weather Network (NDAWN)
Red River of the North Basin (RRB)
Rivers
soil moisture active–passive (SMAP)
U.S. Geological Survey (USGS)
US Government agencies
The Utility of SMAP Soil Moisture and Freeze-Thaw Datasets as Precursors to Spring-Melt Flood Conditions: A Case Study in the Red River of the North Basin
We evaluated NASA soil moisture active-passive (SMAP) soil moisture (SM) and freeze-thaw (FT) datasets for the utility to identify FT and SM conditions as precursors to a 2017 spring-melt flood event in the Red River of the North Basin. SMAP FT and SM datasets were analyzed at basin-scale and at specific North Dakota Agricultural Weather Network (NDAWN), National Oceanic and Atmospheric Administration (NOAA), and Red River of the North U.S. Geological Survey (USGS) stations prior to and during the observed flood. Results indicate that SMAP FT dataset had better agreement with NDAWN and NOAA air temperature measurements than with soil temperature. SMAP FT and SM were able to observe FT states and saturated soil conditions at basin-level and significant increases in SM content up to five days before USGS gauge height increase and the manifestation of the flood event. A Spearman's rank (Rs) cross-correlation coefficient lag function was applied to SMAP SM and USGS river gauge heights and the strength of the relationship varied by location and lead time. Downstream locations near and in the flood area (North Grand Forks, Oslo, North Drayton) displayed moderate to strong relationships at 1-, 3-, and 4-day lead times (Rs = 0.67, 0.84, 0.71; p <; .05), respectively. Pembina had the strongest relationship (4-day lead time; Rs = 0.88; p<; .05), well during the flood event recorded. This study suggests that SMAP SM and FT datasets can potentially provide useful information on surface state conditions to spring-melt floods in the Red River of the North Basin.
Aug. 2019
2848-2861
journalArticle
30
IEEE Transactions on Image Processing
DOI 10.1109/TIP.2021.3082297
IEEE Transactions on Image Processing
ISSN 1941-0042
P. Zhu
T. Peng
D. Du
H. Yu
L. Zhang
Q. Hu
Image resolution
Agriculture
Animals
Drones
Animal counting
Annotations
drone
graph regularized flow attention network
multi-granularity loss
Optical losses
Wildlife
Graph Regularized Flow Attention Network for Video Animal Counting From Drones
In this paper, we propose a large-scale video based animal counting dataset collected by drones (AnimalDrone) for agriculture and wildlife protection. The dataset consists of two subsets, i.e., PartA captured on site by drones and PartB collected from the Internet, with rich annotations of more than 4 million objects in 53, 644 frames and corresponding attributes in terms of density, altitude and view. Moreover, we develop a new graph regularized flow attention network (GFAN) to perform density map estimation in dense crowds of video clips with arbitrary crowd density, perspective, and flight altitude. Specifically, our GFAN method leverages optical flow to warp the multi-scale feature maps in sequential frames to exploit the temporal relations, and then combines the enhanced features to predict the density maps. Moreover, we introduce the multi-granularity loss function including pixel-wise density loss and region-wise count loss to enforce the network to concentrate on discriminative features for different scales of objects. Meanwhile, the graph regularizer is imposed on the density maps of multiple consecutive frames to maintain temporal coherency. Extensive experiments are conducted to demonstrate the effectiveness of the proposed method, compared with several state-of-the-art counting algorithms. The AnimalDrone dataset is available at https://github.com/VisDrone/AnimalDrone.
2021
5339-5351
journalArticle
19
IEEE Sensors Journal
DOI 10.1109/JSEN.2019.2935812
23
IEEE Sensors Journal
ISSN 1558-1748
D. Shadrin
A. Menshchikov
D. Ermilov
A. Somov
computer vision
artificial intelligence
Agriculture
machine learning
Artificial intelligence
Graphics processing units
Sensors
Meteorology
Containers
embedded sensing
Embedded systems
smart agriculture
Smart sensing
Designing Future Precision Agriculture: Detection of Seeds Germination Using Artificial Intelligence on a Low-Power Embedded System
Artificial Intelligence (AI) has been recently applied to a number of sensing scenarios for realizing the prediction, control and/or recognition tasks. However, its integration to embedded systems is still limited. We propose a low-power sensing system with the AI on board with a special focus on the application in agriculture. For this reason we designed a Convolutional Neural Network (CNN) which achieves 83% of average Intersection over Union (IoU) score on the test dataset and 97% of seeds recognition accuracy on the validation dataset. The proposed solution is able to perform the seeds recognition, and germination detection through the images processing. For training the CNN we collect a dataset of images of seed germination process at different stages. The entire system is assessed in an industrial facility. The experimental results demonstrate that the proposed system opens up wide vista for smart applications in the context of Internet of Things requiring the intelligent and autonomous operation from ‘things’.
1 Dec.1, 2019
11573-11582
journalArticle
14
IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
DOI 10.1109/JSTARS.2021.3073965
IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
ISSN 2151-1535
G. Weikmann
C. Paris
L. Bruzzone
multispectral images
Deep learning
Training
Agriculture
Time series analysis
Task analysis
Benchmark testing
Benchmark
crop type mapping
Data mining
multitemporal deep learning
Sentinel-2 dataset
time series (TSs)
TimeSen2Crop
TimeSen2Crop: A Million Labeled Samples Dataset of Sentinel 2 Image Time Series for Crop-Type Classification
This article presents TimeSen2Crop, a pixel-based dataset made up of more than 1 million samples of Sentinel 2 time series (TSs) associated to 16 crop types. This dataset, publicly available, aims to contribute to the worldwide research related to the supervised classification of TSs of Sentinel 2 data for crop type mapping. TimeSen2Crop includes atmospherically corrected images and reports the snow, shadows, and clouds information per labeled unit. The provided TSs represent an agronomic year (i.e., period from one year's harvest to the next one for agricultural commodity) ranging from September 2017 to August 2018. To generate the dataset, the publicly available Austrian crop type map based on farmer's declarations has been considered. To ensure the selection of reliable labeled units from the map (i.e., pure pixels correctly associated to their labels), an automatic procedure for the extraction of the training set based on a multitemporal deep learning model has been defined. TimeSen2Crop also includes a TS of Sentinel 2 images acquired in the following agronomic year (i.e., from September 2018 to August 2019). These data are provided with the aim of attract more research activities for solving a typical challenge of the crop type mapping task: adapting multitemporal deep learning models to different year (domain adaptation). The design of the dataset is described along with a benchmark comparison of deep learning models for crop type mapping.
2021
4699-4708
journalArticle
7
IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
DOI 10.1109/JSTARS.2014.2349945
8
IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
ISSN 2151-1535
M. Chellasamy
R. T. Zielinski
M. H. Greve
Feature extraction
Agriculture
Remote sensing
Accuracy
Neural networks
Vegetation mapping
neural classifier
Crop discrimination
endorsement theory (ET)
multitemporal datasets
Springs
WorldView-2 (WV2)
A Multievidence Approach for Crop Discrimination Using Multitemporal WorldView-2 Imagery
Despite using multiple input datasets for effective crop classification, it is important to select an appropriate method that efficiently integrates these multiple datasets to produce accurate classification results. In this paper, we present an endorsement theory-based crop classification approach that considers the qualitative information, in terms of prediction probabilities, from different input datasets and integrates them efficiently to produce final classification results. Three different input datasets are used in this study: 1) spectral; 2) texture; and 3) indices from multitemporal (spring, early summer) WorldView-2 multispectral imagery. A multilayer perceptron classifier is trained with the multitemporal datasets separately using a backpropagation learning algorithm, and prediction probabilities are produced for each pixel as evidence against each crop class. An integration rule based on endorsement theory is applied to these multiple evidence by considering their individual contribution, and the most probable class of a pixel is identified. Integration of the three multidate datasets by the proposed method is found to produce higher overall classification accuracy (91.2%) when compared to conventional winner-takes-all approach (89%). In order to determine which individual dataset is more useful for crop discrimination, the dataset's performance is compared using evidence and contributions produced in the proposed integration method for four selected crops, for both single- and multidate. The results of this analyses showed that seasonal textures information outperformed both spectral and indices. To verify this finding, results of individual dataset classification are examined. The highest overall classification accuracy of 88.8% is achieved by the use of multidate texture, where multidate spectral and indices resulted in 86.3% and 84.4%, respectively.
Aug. 2014
3491-3501
journalArticle
13
IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
DOI 10.1109/JSTARS.2020.2995577
IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
ISSN 2151-1535
Y. Song
J. Wang
J. Shang
Estimation
Monitoring
Agriculture
Biological system modeling
Remote sensing
Vegetation mapping
Three-dimensional displays
gap fraction
leaf area index (LAI)
point cloud data
unmanned aerial vehicle (UAV)
winter wheat
Estimating Effective Leaf Area Index of Winter Wheat Using Simulated Observation on Unmanned Aerial Vehicle-Based Point Cloud Data
Within-field variation of leaf area index (LAI) plays an essential role in field crop monitoring and yield forecasting. Although unmanned aerial vehicle (UAV)-based optical remote sensing method can overcome the spatial and temporal resolution limitations associated with satellite imagery for fine-scale within-field LAI estimation of field crops, image correction and calibration of UAV data are very challenging. In this study, a physical-based method was proposed to automatically calculate crop effective LAI (LAIe) using UAV-based 3-D point cloud data. Regular high spatial resolution RGB images were used to generate point cloud data for the study area. The proposed method, simulated observation of point cloud (SOPC), was designed to obtain the 3-D spatial distribution of vegetation and bare ground points and calculate the gap fraction and LAIe from a UAV-based 3-D point cloud dataset at vertical, 57.5°, and multiview angle of a winter wheat field in London, Ontario, Canada. Results revealed that the derived LAIe using the SOPC multiview angle method correlates well with the LAIe derived from ground digital hemispherical photography, R2 = 0.76. The root mean square error and mean absolute error for the entire experiment period from May 11 to May 27 were 0.19 and 0.14, respectively. The newly proposed method performs well for LAIe estimation during the main leaf development stages (BBCH 20-39) of the growth cycle. This method has the potential to become an alternative approach for crop LAIe estimation without the need for ground-based reference measurements, hence save time and money.
2020
2874-2887
journalArticle
11
IEEE Access
DOI 10.1109/ACCESS.2023.3240100
IEEE Access
ISSN 2169-3536
A. Ahmad
A. E. Gamal
D. Saraswat
Crops
Feature extraction
Deep learning
Computer architecture
Diseases
Training
Plants
image classification
Image classification
disease identification
generalization
Toward Generalization of Deep Learning-Based Plant Disease Identification Under Controlled and Field Conditions
Identifying corn diseases under field conditions is crucial for implementing effective disease management systems. Deep learning (DL)-based plant disease identification using deep neural networks (DNN) has been successfully implemented in recent years. Recent work suggests DL models trained on lab-acquired image data do not generalize to similar accuracy levels for identifying diseases in the field. Additionally, most studies have not evaluated the generalizability of DL models for identifying plant diseases from various datasets and diverse imaging conditions. This study evaluates how well DL models generalize across different datasets and environmental conditions for identifying plant diseases using five datasets consisting of foliar disease images in corn: namely PlantVillage, PlantDoc, Digipathos, northern leaf blight (NLB) dataset, and a custom acquired CD&S dataset. Multiple DL-based image classification models were trained and evaluated using different dataset combinations. Transfer learning was utilized using five different pre-trained DNN architectures: InceptionV3, ResNet50, VGG16, DesneNet169, and Xception, for conducting four different experiments. After training the models, images for distinct corn diseases from different datasets were used as testing data for evaluating the generalization ability of each DL model. It was observed that the DenseNet169 model performed the best. The highest generalization accuracy of 81.60% was observed when the DenseNet169 model was trained using red, green, blue, and alpha (RGBA) images from CD&S corn disease dataset with removed backgrounds. In addition, 77.50% to 80.33% accuracy was achieved for the PlantVillage dataset when combined with field-acquired images from either the PlantDoc or the CD&S dataset. The results suggest that background removal using RGBA images from CD&S dataset or augmentation of field and lab data improves the generalization performance of DL models and could be used for developing field-deployable disease management systems.
2023
9042-9057
journalArticle
60
IEEE Transactions on Geoscience and Remote Sensing
DOI 10.1109/TGRS.2022.3182425
IEEE Transactions on Geoscience and Remote Sensing
ISSN 1558-0644
J. Zhao
Y. Qu
S. Ninomiya
W. Guo
Image color analysis
Cameras
Hyperspectral imaging
Spatial resolution
Superresolution
Image reconstruction
super-resolution
Abundance map
camera response function (CRF)
endmember
hyperspectral image (HSI)
Imaging
unsupervised deep learning
Endmember-Assisted Camera Response Function Learning, Toward Improving Hyperspectral Image Super-Resolution Performance
The camera response function (CRF) that projects hyperspectral radiance to the corresponding RGB images is important for most hyperspectral image super-resolution (HSI-SR) models. In contrast to most studies that focus on improving HSI-SR performance through new architectures, we aim to prevent the model performance drop by learning the CRF of any given HSIs and RGB image from the same scene in an unsupervised manner, independent of the HSI-SR network. Accordingly, we first decompose the given RGB image into endmembers and an abundance map using the Dirichlet autoencoder architecture. Thereafter, a linear CRF learning network is optimized to project the reference HSIs to the RGB image that can be similarly decomposed like the given RGB, assuming that objects in both images share the same endmembers and abundance map. The quality of the RGB images generated from the learned CRFs is compared with that of the corresponding ground-truth images based on the true CRFs of two consumer-level cameras Nikon 700D and Canon 500D. We demonstrate that the effectively learned CRFs can prevent significant performance drop in three popular HSI-SR models on RGB images from different categories of standard datasets of CAVE, ICVL, Chikusei, Cuprite, Salinas, and KSC. The successfully learned CRF using the method proposed in this study would largely promote a wider implementation of HSI-SR models since tremendous performance drop can be prevented practically.
2022
1-14
journalArticle
Z. Shi
M. Xu
Q. Pan
Agriculture
Forestry
Psychology
constrained LSTM network
Decision making
Internet
linear least squares
Product design
Quality assessment
Trajectory prediction
trajectory segmentation
4-D Flight Trajectory Prediction With Constrained LSTM Network
The increasing aviation activities pose a challenge to ensure a safe and orderly flight. Trajectory prediction is one of the most important forecasting tasks in Air Traffic Management. Accurate prediction is reasonable for safe and orderly flight tasks in civil aviation monitoring. Points of interests play an important role in most land traffic prediction algorithms due to their abilities in positioning and marking. Compared with land traffic, the sparse way-points and shared airways make it difficult for flight trajectory prediction. A constrained Long Short-Term Memory network for flight trajectory prediction is proposed in this paper. According to the dynamic characteristics of the aircraft, we propose three kinds of constraints to climbing, cruising, and descending/approaching phases, in particular, they are Top of climb, Way-points, and Runway direction, correspondingly. Our model is able to keep long-term dependencies with dynamic physical constraints. Density-Based Spatial Clustering of Applications with Noise and Linear Least Squares are used in data segmentation and preprocessing. Sliding windows help maintain the continuity of trajectory. Four-dimensional spatial-temporal trajectory set consisting of spatial position and timestamps is used to prove the efficiency of our approach. Multiple ADS-B ground stations contribute to our experimental dataset. The widely used Long Short-Term Memory network, Markov Model, weighted Markov Model, Support Vector Machine, and Kalman Filter are used for comparison. Quantitative analysis demonstrates that our model outperforms the above-mentioned state-of-the-art models, and lays a good foundation for decision-making in different scenarios.
Nov. 2021
7242-7255
22
IEEE Transactions on Intelligent Transportation Systems
DOI 10.1109/TITS.2020.3004807
11
IEEE Transactions on Intelligent Transportation Systems
ISSN 1558-0016
journalArticle
5
IEEE Robotics and Automation Letters
DOI 10.1109/LRA.2020.2965061
2
IEEE Robotics and Automation Letters
ISSN 2377-3766
N. Häni
P. Roy
V. Isler
Vegetation
Training
Image segmentation
Benchmark testing
object detection
Agricultural automation
robotics in agriculture and forestry
Yield estimation
Labeling
segmentation and categorization
MinneApple: A Benchmark Dataset for Apple Detection and Segmentation
In this work, we present a new dataset to advance the state-of-the-art in fruit detection, segmentation, and counting in orchard environments. While there has been significant recent interest in solving these problems, the lack of a unified dataset has made it difficult to compare results. We hope to enable direct comparisons by providing a large variety of high-resolution images acquired in orchards, together with human annotations of the fruit on trees. The fruits are labeled using polygonal masks for each object instance to aid in precise object detection, localization, and segmentation. Additionally, we provide data for patch-based counting of clustered fruits. Our dataset contains over 41'0000 annotated object instances in 1000 images. We present a detailed overview of the dataset together with baseline performance analysis for bounding box detection, segmentation, and fruit counting as well as representative results for yield estimation. We make this dataset publicly available and host a CodaLab challenge to encourage a comparison of results on a common dataset. To download the data and learn more about the MinneApple dataset, please see the project website: http://rsn.cs.umn.edu/index.php/MinneApple. Up to date information is available online.
April 2020
852-858
journalArticle
10
IEEE Access
DOI 10.1109/ACCESS.2022.3215497
IEEE Access
ISSN 2169-3536
H. Phan
A. Ahmad
D. Saraswat
Monitoring
deep learning
Deep learning
Image color analysis
Diseases
Agriculture
Image segmentation
Vegetation mapping
Plants
image classification
Testing
corn leaf disease identification
field conditions
SLIC segmentation
Identification of Foliar Disease Regions on Corn Leaves Using SLIC Segmentation and Deep Learning Under Uniform Background and Field Conditions
Plant diseases lead to severe losses in crop yield worldwide. The conventional approach for diagnosing diseases relies on manual scouting. In recent years, advances in convolutional neural networks have motivated the use of deep learning-based computer vision for automatically identifying plant diseases. Although image classification techniques are commonly used for analyzing agricultural data, their use for accurately identifying diseased regions corresponding to different disease types on individual plant leaves is limited. In this study, Simple Linear Iterative Clustering (SLIC) segmentation was used on corn leaf images from the PlantVillage and CD&S datasets to create super-pixels, a cluster of pixels representing a region of interest on a corn leaf. The VGG16, ResNet50, DenseNet121, Xception, and InceptionV3, pre-trained deep learning models were utilized to identify diseased regions corresponding to five super-pixel classes (healthy, northern leaf blight (NLB), gray leaf spot (GLS), common rust, and background) for the PlantVillage dataset and four super-pixel classes (NLB, GLS, northern leaf spot, and background) for the CD&S dataset, on corn leaves. After setting the spatial proximity value (sigma) for SLIC segmentation to five, a total of 100 models were trained by using different numbers of segments per image (five and fifteen) in the SLIC algorithm for both datasets and choosing training: testing split ratios of 90:10, 80:20, 70:30, 60:40, and 50:50 for each of the five models. The highest overall testing accuracy of 97.77% was observed after training the DenseNet121 model to identify super-pixels created from the CD&S dataset, belonging to the four classes created using a sigma value of five, five segments per image, and an 80:20 training: testing split ratio. Web and mobile applications were developed to identify diseased regions on corn leaves using the best deep learning model as the classifier. The results suggest that SLIC segmentation on corn leaf images helps accurately identify diseased regions. This research demonstrates the potential of image-based scouting as an efficient alternative to manual scouting for disease monitoring.
2022
111985-111995
journalArticle
G. Xiao
W. Xiang
S. Peng
H. Chen
J. Guo
Z. Gong
Task analysis
Adaptation models
Semantics
Big Data
Cognition
Prototypes
Reliability
NI-UDA: Graph Contrastive Domain Adaptation for Nonshared-and-Imbalanced Unsupervised Domain Adaptation
With the technology development, information networks continuously generate a large amount of integrated labeled Big Data. Some types of labeled data in real scenes are scarce and difficult to obtain, such as some aerospace data. It is important to address the problem of nonshared and imbalanced unsupervised domain adaptation (NI-UDA) from the labeled Big Data with nonshared and long-tail distribution to unlabeled specified small and imbalanced space applications, where nonshared classes mean the label space out of the target domain. Previous methods proposed to integrate the semantic knowledge of Big Data to help the unsupervised domain adaptation for sparse data. However, they have the challenges of limited effect of knowledge sharing for long-tail Big Data and the imbalanced domain adaptation. To solve them, our goal is to leverage priori hierarchy knowledge to enhance domain contrastive aligned feature representation with graph reasoning. Our method consists of hierarchy graph reasoning (HGR) layer and K-positive contrastive domain adaptation (K-CDA). Our HGR contributes to learn direct semantic patterns for sparse classes by hierarchy attention in self-attention, nonlinear mapping, and graph normalization. For alleviating imbalanced domain adaptation, we proposed K-CDA, which explores k-positive instances for each class to every mini-batch with contrastive learning to align imbalanced feature representations. Compared with the previous contrastive UDA, our K-CDA alleviates the problems of large memory consumption and high computational cost. Experiments on three benchmark datasets shows our methods consistently improve the state-of-the-art contrastive UDA algorithms.
Dec. 2022
5105-5117
58
IEEE Transactions on Aerospace and Electronic Systems
DOI 10.1109/TAES.2022.3182636
6
IEEE Transactions on Aerospace and Electronic Systems
ISSN 1557-9603
journalArticle
8
IEEE Access
DOI 10.1109/ACCESS.2020.3013005
IEEE Access
ISSN 2169-3536
X. Zhang
Z. Cao
W. Dong
Monitoring
artificial intelligence
Agriculture
Production
Cloud computing
Internet of Things
Servers
smart agriculture
blockchain
edge computing
Edge computing
The Agricultural Internet of Things
virtual/augmented reality
Overview of Edge Computing in the Agricultural Internet of Things: Key Technologies, Applications, Challenges
The application of the Internet of Things in agricultural development usually occurs via a monitoring network that consists of a large number of sensor nodes, thus gradually transforming agriculture from a human-oriented and single-machine-centric production model to an information- and software-centric production model. Due to the large area coverage of agriculture and the variety of production objects, if all farmland perception information is gathered into the cloud server, the server will exert greater pressure on the network, which reduces the speed of response to event processing. This problem may be perfectly solved by the recent emergence of Edge computing, which can share the load of the cloud server and reduce the delay. Edge computing has prospects in agricultural applications, such as pest identification, safety traceability of agricultural products, unmanned agricultural machinery, agricultural technology promotion, and intelligent management. The application of the Agricultural Internet of Things integrates artificial intelligence, the Internet of Things, and blockchain and Virtual/Augmented Reality technologies. This paper primarily reviews the application of Edge computing in the Agricultural Internet of Things and investigates the combination of Edge computing and Artificial Intelligence, blockchain and Virtual/Augmented reality technology. The challenges of Edge computing task allocation, data processing, privacy protection and security, and service stability in agriculture are reviewed. The future development direction of Edge computing in the Agricultural Internet of Things is predicted.
2020
141748-141761
journalArticle
30
IEEE Transactions on Image Processing
DOI 10.1109/TIP.2021.3049334
IEEE Transactions on Image Processing
ISSN 1941-0042
X. Liu
W. Min
S. Mei
L. Wang
S. Jiang
Feature extraction
Diseases
Agriculture
Plants (biology)
Visualization
feature aggregation
fine-grained visual classification
Image recognition
Medical diagnosis
Plant disease recognition
reweighting approach
Plant Disease Recognition: A Large-Scale Benchmark Dataset and a Visual Region and Loss Reweighting Approach
Plant disease diagnosis is very critical for agriculture due to its importance for increasing crop production. Recent advances in image processing offer us a new way to solve this issue via visual plant disease analysis. However, there are few works in this area, not to mention systematic researches. In this paper, we systematically investigate the problem of visual plant disease recognition for plant disease diagnosis. Compared with other types of images, plant disease images generally exhibit randomly distributed lesions, diverse symptoms and complex backgrounds, and thus are hard to capture discriminative information. To facilitate the plant disease recognition research, we construct a new large-scale plant disease dataset with 271 plant disease categories and 220,592 images. Based on this dataset, we tackle plant disease recognition via reweighting both visual regions and loss to emphasize diseased parts. We first compute the weights of all the divided patches from each image based on the cluster distribution of these patches to indicate the discriminative level of each patch. Then we allocate the weight to each loss for each patch-label pair during weakly-supervised training to enable discriminative disease part learning. We finally extract patch features from the network trained with loss reweighting, and utilize the LSTM network to encode the weighed patch feature sequence into a comprehensive feature representation. Extensive evaluations on this dataset and another public dataset demonstrate the advantage of the proposed method. We expect this research will further the agenda of plant disease recognition in the community of image processing.
2021
2003-2015
journalArticle
8
IEEE Access
DOI 10.1109/ACCESS.2020.3028595
IEEE Access
ISSN 2169-3536
N. Deepa
M. Z. Khan
B. Prabadevi
D. R. Vincent P.M.
P. K. R. Maddikunta
T. R. Gadekallu
Agriculture
Correlation
Soil
Mathematical model
Decision making
grey correlation method
Linear programming
Mahalanobis Taguchi System (MTS)
Measurement
multiclass
objective function
Multiclass Model for Agriculture Development Using Multivariate Statistical Method
Mahalanobis taguchi system (MTS) is a multi-variate statistical method extensively used for feature selection and binary classification problems. The calculation of orthogonal array and signal-to-noise ratio in MTS makes the algorithm complicated when more number of factors are involved in the classification problem. Also the decision is based on the accuracy of normal and abnormal observations of the dataset. In this paper, a multiclass model using Improved Mahalanobis Taguchi System (IMTS) is proposed based on normal observations and Mahalanobis distance for agriculture development. Twenty-six input factors relevant to crop cultivation have been identified and clustered into six main factors for the development of the model. The multiclass model is developed with the consideration of the relative importance of the factors. An objective function is defined for the classification of three crops, namely paddy, sugarcane and groundnut. The classification results are verified against the results obtained from the agriculture experts working in the field. The proposed classifier provides 100% accuracy, recall, precision and 0% error rate when compared with other traditional classifier models.
2020
183749-183758
journalArticle
3
IEEE Robotics and Automation Letters
DOI 10.1109/LRA.2018.2848305
4
IEEE Robotics and Automation Letters
ISSN 2377-3766
P. Bosilj
T. Duckett
G. Cielniak
Feature extraction
Robots
Object detection
Agriculture
Shape
Vegetation mapping
Morphology
Histograms
segmentation and categorization
agricultural automation
field robots
Analysis of Morphology-Based Features for Classification of Crop and Weeds in Precision Agriculture
Determining the types of vegetation present in an image is a core step in many precision agriculture tasks. In this letter, we focus on pixel-based approaches for classification of crops versus weeds, especially for complex cases involving overlapping plants and partial occlusion. We examine the benefits of multiscale and content-driven morphology-based descriptors called attribute profiles. These are compared to the state-of-the-art keypoint descriptors with a fixed neighborhood previously used in precision agriculture, namely histograms of oriented gradients and local binary patterns. The proposed classification technique is especially advantageous when coupled with morphology-based segmentation on a max-tree structure, as the same representation can be reused for feature extraction. The robustness of the approach is demonstrated by an experimental evaluation on two datasets with different crop types, while being able to provide descriptors at a higher resolution. The proposed approach compared favorably to the state-of-the-art approaches without an increase in computational complexity, while being able to provide descriptors at a higher resolution.
Oct. 2018
2950-2956
journalArticle
9
IEEE Access
DOI 10.1109/ACCESS.2021.3057912
IEEE Access
ISSN 2169-3536
S. Shorewala
A. Ashfaque
R. Sidharth
U. Verma
computer vision
deep learning
Deep learning
neural networks
Training
Agriculture
convolutional neural networks
Image segmentation
segmentation
machine learning
Artificial intelligence
precision agriculture
Vegetation mapping
Object segmentation
artificial neural networks
Autonomous robots
crops
ResNet
semi-supervised learning
unsupervised learning
weeds
Weed Density and Distribution Estimation for Precision Agriculture Using Semi-Supervised Learning
Uncontrolled growth of weeds can severely affect the crop yield and quality. Unrestricted use of herbicide for weed removal alters biodiversity and cause environmental pollution. Instead, identifying weed-infested regions can aid selective chemical treatment of these regions. Advances in analyzing farm images have resulted in solutions to identify weed plants. However, a majority of these approaches are based on supervised learning methods which requires huge amount of manually annotated images. As a result, these supervised approaches are economically infeasible for the individual farmer because of the wide variety of plant species being cultivated. In this paper, we propose a deep learning-based semi-supervised approach for robust estimation of weed density and distribution across farmlands using only limited color images acquired from autonomous robots. This weed density and distribution can be useful in a site-specific weed management system for selective treatment of infected areas using autonomous robots. In this work, the foreground vegetation pixels containing crops and weeds are first identified using a Convolutional Neural Network (CNN) based unsupervised segmentation. Subsequently, the weed infected regions are identified using a fine-tuned CNN, eliminating the need for designing hand-crafted features. The approach is validated on two datasets of different crop/weed species (1) Crop Weed Field Image Dataset (CWFID), which consists of carrot plant images and the (2) Sugar Beets dataset. The proposed method is able to localize weed-infested regions a maximum recall of 0.99 and estimate weed density with a maximum accuracy of 82.13%. Hence, the proposed approach is shown to generalize to different plant species without the need for extensive labeled data.
2021
27971-27986
journalArticle
9
IEEE Access
DOI 10.1109/ACCESS.2021.3108003
IEEE Access
ISSN 2169-3536
M. Das
A. Bais
Feature extraction
deep learning
Deep learning
Image color analysis
Agriculture
Image segmentation
Semantics
Soil
canola
flea beetle damage
leave damage
semantic segmentation
Weed segmentation
DeepVeg: Deep Learning Model for Segmentation of Weed, Canola, and Canola Flea Beetle Damage
Farmers around the world face the challenge of growing more food for the increasing world population. On top of that, external threats such as pests (weeds and insects) pose a threat to crop production and it is necessary to take early steps to reduce the risk. This paper presents semantic segmentation of canola field images collected under natural conditions. The dataset contains four unbalanced classes; background, crop, weeds, and damages in the crop. The damages to the crop leaves are small round shaped and share the same texture and colour as whitish stones from the background. We propose, DeepVeg, a deep learning segmentation model that focuses on the smallest (damage) class without affecting other classes to solve the class imbalance issue. Early stage canola field image dataset is utilized for training and testing the proposed model. Evaluation results show that the proposed method outperforms the benchmark deep learning models and effectively addresses the weed and damaged canola plants segmentation problem. The DeepVeg model demonstrates a superior mean intersection over union score greater than 0.76 and accuracy above 0.97 for four class segmentation. The model also shows robustness in detecting unlabelled, newly grown weeds and canola and is also able to distinguish the similar rounded structured canola plant and weed with small amounts of data for model training, which is suitable for early stage damage and weed segmentation.
2021
119367-119380
journalArticle
8
IEEE Access
DOI 10.1109/ACCESS.2020.3009977
IEEE Access
ISSN 2169-3536
Y. Liu
Y. Yang
W. Jing
Microwave radiometry
Soil measurements
Soil moisture
Synthetic aperture radar
Sensors
Meteorology
Satellite broadcasting
Gap-filling
satellite retrieved soil moisture
the essential climate variable soil moisture
the soil moisture active passive soil moisture
Potential Applicability of SMAP in ECV Soil Moisture Gap-Filling: A Case Study in Europe
The Essential Climate Variable (ECV) soil moisture (SM) datasets, originated from the European Space Agency, have revealed great potential for application in hydrology and agriculture. Hence, it is essential to continuously enhance the data quality and spatial completeness to satisfy the increasing scientific research requirements. In this study, we explore the potential possibility of Soil Moisture Active Passive (SMAP) datasets in filling the gaps of ECV SM. The comprehensive assessment results show that: (1) The data missing percent of gap-filled ECV decreases 20% on average, which can be one step closer to generate a seamlessly covered global land surface SM product with favorable quality. (2) Compared to the original ECV, the gap-filled ECV products express similar good response to the in-situ measurements, suggesting that the SMAP SM products could be taken to efficiently fill the gaps and consistently maintain favorable accuracy at the same time. (3) Compared to the in-situ measurements, the original ECV SM products demonstrate extremely high probability density peak percentages. Fortunately, this eminent high value could be effectively rectified through gap-filling progress using SMAP. Overall, this study conducts objective and detailed evaluation on the performance of applying SMAP to fill the gaps of ECV, and is expected to act as a valuable reference in ECV SM gap-filling method.
2020
133114-133127
journalArticle
Y. Saito
P. Raksincharoensak
Advanced driver assistance systems
Collision avoidance
Human computer interaction
Human factors
human–machine cooperation
Predictive control
proactive safety
Safety
Senior citizens
shared control
Shared Control in Risk Predictive Braking Maneuver for Preventing Collisions With Pedestrians
Ensuring a safe mobility for elderly drivers is one of the important issues to be addressed for supporting the daily life of elderly. Shared control of a risk predictive braking maneuver attempts to manage the potential risk of crashing with respect to hazards that cannot be seen by the driver. The assistance system performs a partial deceleration maneuver to achieve a referenced velocity in uncertain situations, such as one in which an unobserved pedestrian might initiate a road crossing. This paper presents the following: first, an analysis of hazard-anticipatory driving for an expert driver; second, a detailed description of risk predictive control; third, the effectiveness and limitations of risk predictive control obtained through a numerical simulation; fourth, the framework of the driver assistance system; and fifth, experimental data for evaluation of proactive safety performance. Specifically, three questions will be investigated: How would expert drivers drive in uncertain situations?; How can a reference velocity be determined?; and How can a system be designed so that the relationship between the human and the machine is complementary? Based on this framework, this paper discusses a shared control system that dynamically shares control authority between the elderly driver and the ADAS.
Dec. 2016
314-324
1
IEEE Transactions on Intelligent Vehicles
DOI 10.1109/TIV.2017.2700210
4
IEEE Transactions on Intelligent Vehicles
ISSN 2379-8904
journalArticle
7
IEEE Access
DOI 10.1109/ACCESS.2019.2958831
IEEE Access
ISSN 2169-3536
D. Wang
Y. Fu
G. Yang
X. Yang
D. Liang
C. Zhou
N. Zhang
H. Wu
D. Zhang
Feature extraction
Image color analysis
Training
Image segmentation
fully convolutional network
field conditions
Adhesives
Corner detection
Ear
Harris corner detection
wheat-ear adhesion
Wheat-ear counting
Combined Use of FCN and Harris Corner Detection for Counting Wheat Ears in Field Conditions
Accurate counting of wheat ears in field conditions is vital to predict yield and for crop breeding. To quickly and accurately obtain the number of wheat ears in a field, we propose herein a method to count wheat ears based on fully convolutional network (FCN) and Harris corner detection. The technical procedure consists essentially of 1) constructing a dataset of wheat-ear images from acquired red-green-blue (RGB) images; 2) training a FCN as the wheat-ear segmentation model by using the constructed image dataset; 3) preparing testing images and inputting them into the segmentation model to get the initial segmentation results; 4) binarizing the initial segmentation by using the Otsu algorithm (to facilitate subsequent processing); and 5) applying Harris corner detection after extracting the wheat-ear skeleton to obtain the number of wheat ears in the images. The segmentation results show that the proposed FCN-based segmentation model segments wheat ears with an average accuracy of 0.984 and at low computational cost. An average of only 0.033 s is required to segment a $256\times 256$ -pixel wheat-ear image. Moreover, the segmentation result is improved by nearly 10% compared with the previous segmentation methods under conditions of wheat-ear occlusion, leaf occlusion, uneven illumination, and soil disturbance. Subsequently, the proposed counting method achieves good results, with an average accuracy of 0.974, a coefficient of determination (R2) of 0.983, and a root mean square error (RMSE) of 14.043. These metrics are all improved by 10% compared with the previous methods. These results show that the proposed method accurately counts wheat ears even under conditions of wheat-ear adhesion. Furthermore, the results provide an important technique for studying wheat phenotyping.
2019
178930-178941
journalArticle
J. Chen
K. H. Low
Y. Yao
P. Jaillet
Predictive models
Prediction algorithms
Roads
Robot sensing systems
Active learning
adaptive sampling
Data integration
decentralized active sensing
decentralized/distributed data fusion
distributed consensus filtering
environmental sensing and monitoring
Gaussian process
log-Gaussian process
mobility demand prediction
relational Gaussian process
spatiotemporal modeling
traffic flow forecasting
Vehicles
vehicular sensor network
Gaussian Process Decentralized Data Fusion and Active Sensing for Spatiotemporal Traffic Modeling and Prediction in Mobility-on-Demand Systems
Mobility-on-demand (MoD) systems have recently emerged as a promising paradigm of one-way vehicle sharing for sustainable personal urban mobility in densely populated cities. We assume the capability of a MoD system to be enhanced by deploying robotic shared vehicles that can autonomously cruise the streets to be hailed by users. A key challenge of the MoD system is that of real-time, fine-grained mobility demand and traffic flow sensing and prediction. This paper presents novel Gaussian process (GP) decentralized data fusion and active sensing algorithms for real-time, fine-grained traffic modeling and prediction with a fleet of MoD vehicles. The predictive performance of our decentralized data fusion algorithms are theoretically guaranteed to be equivalent to that of sophisticated centralized sparse GP approximations. We derive consensus filtering variants requiring only local communication between neighboring vehicles. We theoretically guarantee the performance of our decentralized active sensing algorithms. When they are used to gather informative data for mobility demand prediction, they can achieve a dual effect of fleet rebalancing to service mobility demands. Empirical evaluation on real-world datasets shows that our algorithms are significantly more time-efficient and scalable in the size of data and fleet while achieving predictive performance comparable to that of state-of-the-art algorithms. Note to Practitioners-Knowing, understanding, and predicting spatiotemporally varying traffic phenomena in real time has become increasingly important to the goal of achieving smooth-flowing, congestion-free traffic in densely populated urban cities, which motivates our work here. This paper addresses the following fundamental problem of data fusion and active sensing: How can a fleet of autonomous robotic vehicles or mobile probes actively cruise a road network to gather and assimilate the most informative data for predicting a spatiotemporally varying traffic phenomenon like a mobility demand pattern or traffic flow? Existing centralized solutions are poorly suited because they suffer from a single point of failure and incur huge communication, space, and time overheads with large data and fleet. This paper proposes novel efficient and scalable decentralized data fusion and active sensing algorithms with theoretical performance guarantees. The practical applicability of our algorithms is not restricted to traffic monitoring [1]-[4]; they can be used in other environmental sensing applications such as mineral prospecting [5], precision agriculture, monitoring of ocean/freshwater phenomena (e.g., plankton bloom) [6]-[9], forest ecosystems, pollution (e.g., oil spill), or contamination. Note that the decentralized data fusion component of our algorithms can also be used for static sensors and passive mobile probes and, interestingly, adapted to parallel implementations to be run on a cluster of machines for achieving efficient and scalable probabilistic prediction (i.e., with predictive uncertainty) with large data. Empirical results show that our algorithms can perform well with two datasets featuring real-world traffic phenomena in the densely-populated urban city of Singapore. A limitation of our algorithms is that the decentralized data fusion components assume independence between multiple traffic phenomena while the decentralized active sensing components only work for a single traffic phenomenon. So, in our future work, we will generalize our algorithms to perform active sensing of multiple traffic phenomena and remove the assumption of independence between them.
July 2015
901-921
12
IEEE Transactions on Automation Science and Engineering
DOI 10.1109/TASE.2015.2422852
3
IEEE Transactions on Automation Science and Engineering
ISSN 1558-3783
journalArticle
19
IEEE Geoscience and Remote Sensing Letters
DOI 10.1109/LGRS.2021.3129607
IEEE Geoscience and Remote Sensing Letters
ISSN 1558-0571
Z. Hong
F. Yang
H. Pan
R. Zhou
Y. Zhang
Y. Han
J. Wang
S. Yang
P. Chen
X. Tong
J. Liu
Deep learning
Training
Image segmentation
Task analysis
Image edge detection
Object segmentation
Unmanned aerial vehicles
Roads
unmanned aerial vehicle (UAV)
semantic segmentation
highway crack
U-Net
Highway Crack Segmentation From Unmanned Aerial Vehicle Images Using Deep Learning
Highway crack segmentation is a critical task for highway infrastructure monitoring and maintenance. While imagery from unmanned aerial vehicles (UAVs) is applied to the task of highway crack segmentation, it has great prospects in terms of speed and range. However, it is difficult to accurately identify road cracks from UAV remote sensing images, because the cracks are very narrow and small, often containing only a few pixels. To improve the segmentation of road cracks in UAV images, this study proposed an improved identification technique based on the U-Net architecture enhanced with a convolutional block attention module, an improved encoder, and the strategy of fusing long and short skip connections. A public road crack dataset was relabelled for network training and a UAV remote sensing road crack dataset containing 1157 images was used to verify the generalization ability of the enhanced network model. Results showed that the proposed method could effectively predict highway cracks in UAV images, with mean intersection over union (mIoU) of 77.47% and crack accuracy of 68.38%, which was better than the traditional U-Net model and some traditional semantic segmentation models. The proposed network is trained quickly by public dataset and can predict the road cracks on the new UAV images with high crack accuracy. This study provides an effective solution for the need to quickly grasp the damage status of roads over a wide area in the case of earthquake and other natural disasters. The highway crack segmentation benchmark dataset has been open sourced at: https://github.com/zhhongsh/UAV-Benchmark-Dataset-for-Highway-Crack-Segmentation.
2022
1-5
journalArticle
9
IEEE Access
DOI 10.1109/ACCESS.2021.3096828
IEEE Access
ISSN 2169-3536
D. D. Uyeh
B. I. Bassey
R. Mallipeddi
S. Asem-Hiablie
M. Amaizu
S. Woo
Y. Ha
T. Park
Monitoring
Temperature sensors
reinforcement learning
Sensors
Green products
Sensor systems
smart agriculture
Data quality
environmental monitoring
greenhouse
Sensor placement
temperature & relative humidity
Temperature measurement
A Reinforcement Learning Approach for Optimal Placement of Sensors in Protected Cultivation Systems
Optimal placement of sensors in protected cultivation systems to maximize monitoring and control capabilities can guide effective decision-making toward achieving the highest levels of productivity and other desirable outcomes. Reinforcement learning, unlike conventional machine learning methods such as supervised learning does not require large, labeled datasets thereby providing opportunities for more efficient and unbiased design optimization. With the objective of determining the optimal locations of sensors in a greenhouse, a multi-arm bandit problem was formulated using the Beta distribution and solved by the Thompson sampling algorithm. A total of 56 two-in-one sensors designed to measure both internal air temperature and relative humidity were installed at a vertical distance of 1 m and a horizontal distance of 3m apart in a greenhouse used to cultivate strawberries. Data was collected over a period of seven months covering four major seasons, February (winter), March, April, and May (spring), June and July (summer), and October (autumn) and analyzed separately. Results showed unique patterns for sensor selection for temperature and relative humidity during the different months. Furthermore, temperature and relative humidity each had different optimal location selections suggesting that two-in-one sensors might not be ideal in these cases. The use of reinforcement learning to design optimal sensor placement in this study aided in identifying 10 optimal sensor locations for monitoring and controlling temperature and relative humidity.
2021
100781-100800
journalArticle
8
IEEE Internet of Things Journal
DOI 10.1109/JIOT.2021.3072908
16
IEEE Internet of Things Journal
ISSN 2327-4662
G. Nagasubramanian
R. K. Sakthivel
R. Patan
M. Sankayya
M. Daneshmand
A. H. Gandomi
Diseases
Agriculture
Support vector machines
Internet of Things
Internet of Things (IoT)
6G mobile communication
crop and leaf diseases
ensemble support vector machine (SVM)
Ensemble Classification and IoT-Based Pattern Recognition for Crop Disease Monitoring System
Internet of Things (IoT) in the agriculture field provides crops-oriented data sharing and automatic farming solutions under single network coverage. The components of IoT collect the observable data from different plants at different points. The data gathered through IoT components, such as sensors and cameras, can be used to be manipulated for a better farming-oriented decision-making process. This work proposes a system that observes the crops' growth and leaf diseases continuously for advising farmers in need. To provide analytical statistics on plant growth and disease patterns, the proposed framework uses machine learning (ML) techniques, such as support vector machine (SVM) and convolutional neural network (CNN). This framework produces efficient crop condition notifications to terminal IoT components which are assisting in irrigation, nutrition planning, and environmental compliance related to the farming lands. In this regard, this work proposes ensemble classification and pattern recognition for crop monitoring system (ECPRC) to identify plant diseases at the early stages. The proposed ECPRC uses ensemble nonlinear SVM (ENSVM) for detecting leaf and crop diseases. In addition, this work performs comparative analysis between various ML techniques, such as SVM, CNN, naïve Bayes, and K-nearest neighbors. In this experimental section, the results show that the proposed ECPRC system works optimally compared to the other systems.
15 Aug.15, 2021
12847-12854
journalArticle
10
IEEE Access
DOI 10.1109/ACCESS.2022.3166844
IEEE Access
ISSN 2169-3536
S. P. Sone
J. Lehtomäki
Z. Khan
K. Umebayashi
Z. Javed
neural networks
Time series analysis
Wireless communication
Aggregated interference
DFS
Forecasting
Interference
LSTM
Meteorological radar
radar
Radar
Radar tracking
real network data
spectrum sharing
time series forecasting
WLAN
Proactive Radar Protection System in Shared Spectrum via Forecasting Secondary User Power Levels
Spectrum sharing in radar bands with interference forecasting for enhanced radar protection can help design proactive resource allocation solutions which can achieve high data rates for wireless communication networks on one hand and help protect the incumbent radar systems. We consider radar spectrum sharing in 5.6GHz where a weather radar operates as a primary system and the dominant secondary system is an enterprise network consisting of access points (APs) in a university campus. Our work models transmit the power of the APs as a time series with multinomial distribution based on real collected data. The aggregated interference due to the transmissions from the APs at the radar is forecasted using a long short-term memory (LSTM) based neural network. Monte Carlo dropout is utilized to generate prediction intervals that capture the uncertainties in the interference from the APs. Finally, by using both average and upper limits of predicted interference time series a cloud-assisted efficient sharing and radar protection algorithm is proposed. Tracking the rotating radar is not required in the proposed system. The results show that the proposed efficient sharing and radar protection system ensures better radar protection and increased throughput for wireless communication users.
2022
40367-40380
journalArticle
9
IEEE Access
DOI 10.1109/ACCESS.2021.3062845
IEEE Access
ISSN 2169-3536
X. Yang
M. Li
H. Yu
M. Wang
D. Xu
C. Sun
Production
Blockchain
Smart contracts
Supply chains
Safety
agricultural products
Agricultural products
Memory
on-chain and off-chain
traceability
A Trusted Blockchain-Based Traceability System for Fruit and Vegetable Agricultural Products
Traditional traceability system has problems of centralized management, opaque information, untrustworthy data, and easy generation of information islands. To solve the above problems, this paper designs a traceability system based on blockchain technology for storage and query of product information in supply chain of agricultural products. Leveraging the characteristics of decentralization, tamper-proof and traceability of blockchain technology, the transparency and credibility of traceability information increased. A dual storage structure of “database + blockchain” on-chain and off-chain traceability information is constructed to reduce load pressure of the chain and realize efficient information query. Blockchain technology combined with cryptography is proposed to realize the safe sharing of private information in the blockchain network. In addition, we design a reputation-based smart contract to incentivize network nodes to upload traceability data. Furthermore, we provide performance analysis and practical application, the results show that our system improves the query efficiency and the security of private information, guarantees the authenticity and reliability of data in supply chain management, and meets actual application requirements.
2021
36282-36293
journalArticle
10
IEEE Access
DOI 10.1109/ACCESS.2022.3192406
IEEE Access
ISSN 2169-3536
G. Dai
L. Hu
J. Fan
S. Yan
R. Li
Convolutional neural networks
Data models
Feature extraction
convolutional neural network
Object detection
Agriculture
Computational modeling
Classification algorithms
hyperparametric optimization
mosaic
spatial pyramid pooling
sprouting potato recognition
A Deep Learning-Based Object Detection Scheme by Improving YOLOv5 for Sprouted Potatoes Datasets
Detecting and eliminating sprouted potatoes is a basic measure before potato storage, which can effectively improve the quality of potatoes before storage and reduce economic losses due to potato spoilage and decay. In this paper, we propose an improved YOLOv5-based sprouted potato detection model for detecting and grading sprouted potatoes in complex scenarios. By replacing Conv with CrossConv in the C3 module, the feature similarity loss problem of the fusion process is improved, and the feature representation is enhanced. SPP is improved using fast spatial pyramid pooling to reduce feature fusion parameters and speed up feature fusion. The 9-Mosaic data augmentation algorithm improves the model generalization ability; the anchor points are reconstructed using the genetic algorithm $k$ -means to enhance small target features, and then multi-scale training and hyperparameter evolution mechanisms are used to improve the accuracy. The experimental results show that the improved model has 90.14% recognition accuracy and 88.1% mAP, and the mAP is 4.6%, 7.5%, and 12.4% higher compared with SSD, YOLOv5, and YOLOv4, respectively. In summary, the improved YOLOv5 model, with good detection accuracy and effectiveness, can meet the requirements of rapid grading in automatic potato sorting lines.
2022
85416-85428
journalArticle
14
IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
DOI 10.1109/JSTARS.2020.3036802
IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
ISSN 2151-1535
M. Amani
B. Brisco
S. Mahdavi
A. Ghorbanian
A. Moghimi
E. R. DeLancey
M. Merchant
R. Jahncke
L. Fedorchuk
A. Mui
T. Fisette
M. Kakooei
S. A. Ahmadi
B. Leblon
A. LaRocque
Monitoring
Synthetic aperture radar
Artificial satellites
Earth
Remote sensing
Big data
Biodiversity
Canada
Google Earth Engine
Landsat
remote sensing (RS)
wetlands
Wetlands
Evaluation of the Landsat-Based Canadian Wetland Inventory Map Using Multiple Sources: Challenges of Large-Scale Wetland Classification Using Remote Sensing
The first Canadian wetland inventory (CWI) map, which was based on Landsat data, was produced in 2019 using the Google Earth Engine (GEE) big data processing platform. The proposed GEE-based method to create the preliminary CWI map proved to be a cost, time, and computationally efficient approach. Although the initial effort to produce the CWI map was valuable with a 71% overall accuracy (OA), there were several inevitable limitations (e.g., low-quality samples for the training and validation of the map). Therefore, it was important to comprehensively investigate those limitations and develop effective solutions to improve the accuracy of the Landsat-based CWI (L-CWI) map. Over the past year, the L-CWI map was shared with several governmental, academic, environmental nonprofit, and industrial organizations. Subsequently, valuable feedback was received on the accuracy of this product by comparing it with various in situ data, photo-interpreted reference samples, land cover/land use maps, and high-resolution aerial images. It was generally observed that the accuracy of the L-CWI map was lower relative to the other available products. For example, the average OA in four Canadian provinces using in situ data was 60%. Moreover, including reliable in situ data, using an object-based classification method, and adding more optical and synthetic aperture radar datasets were identified as the main practical solutions to improve the CWI map in the future. Finally, limitations and solutions discussed in this study are applicable to any large-scale wetland mapping using remote sensing methods, especially to CWI generation using optical satellite data in GEE.
2021
32-52
journalArticle
9
IEEE Access
DOI 10.1109/ACCESS.2021.3132486
IEEE Access
ISSN 2169-3536
X. Yang
Y. Luo
M. Li
Z. Yang
C. Sun
W. Li
Convolutional neural networks
Feature extraction
deep learning
Deep learning
Insects
Task analysis
image processing
Convolution
attention mechanism
Image recognition
Insect recognition
Recognizing Pests in Field-Based Images by Combining Spatial and Channel Attention Mechanism
Large scale pest recognition is one of crucial components in pest management in outdoor conditions, which is much more difficult than common object recognition because of the variational image acquisition direction, location, pest size and complex image background. To overcome the challenges, this study proposes a CNN model by combining spatial attention mechanism and channel attention mechanism to realize accurate pest location and recognition in field images. The proposed model consists of two major parts. Firstly, the module Spatial Transformer Networks (STN) is incorporated into a Convolutional Neural Network (CNN) architecture to provide image cropping out and scale-normalization of the appropriate region, which can simplify the subsequent classification task. The second one is called Improved Split-Attention Networks that is used to enable feature-map attention across feature-map groups. The proposed model is evaluated on three different datasets: Li’s dataset (10 species), proposed dataset (58 species) and IP102 dataset (102 species), achieving the classification accuracies of 96.78%, 96.50% and 73.29%, respectively. Comparisons with five traditional CNN models and three attention-related state-of-the-art deep learning models show that the current method outperforms these previous models. Besides, to verify the robustness of this proposed model on different image resolutions, six datasets with different image resolutions are constructed and all accuracies exceed 92% with the image resolution of $400\times 267$ pixels reaching the optimal performance. All results show that the proposed method provides a reliable solution to recognize insect pest in field and support precision plant protection in agriculture production.
2021
162448-162458
journalArticle
8
IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
DOI 10.1109/JSTARS.2015.2417832
11
IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
ISSN 2151-1535
A. Pacheco
H. McNairn
A. Mahmoodi
C. Champagne
Y. H. Kerr
Soil measurements
Soil moisture
Agriculture
soil moisture
Moisture measurement
monitoring
brightness temperature
Brightness temperature
land surface
passive microwave remote sensing
Passive microwave remote sensing
Soil texture
surface texture
The Impact of National Land Cover and Soils Data on SMOS Soil Moisture Retrieval Over Canadian Agricultural Landscapes
To ensure sustainable agriculture production, the availability of water in the right quantity and at the right time is critical, with extremes in availability resulting in severe impacts on the agricultural sector. Delivery of timely and accurate soil moisture data can play a vital role in monitoring the status of available water reserves for this sector. Passive microwave sensors, such as the Soil Moisture and Ocean Salinity (SMOS), are well suited for monitoring vast landscapes given their all-weather capabilities, large spatial footprint, frequent revisit, and the sensitivity of microwave emissions to the soil dielectric. This study examines the impact of exploiting Canadian soil and land cover datasets in the retrieval of soil moisture from SMOS over an agricultural area in the province of Manitoba (Canada). Results demonstrate that global datasets that are integrated within the current SMOS processor perform adequately when field measured soil moisture is compared to estimates of soil moisture by SMOS (R2 of 0.70 (p <; .01) and root-mean-square error (RMSE) of 7.15% with a negative (dry) bias of -0.05%). Overall, this study showed that ingesting high-quality national datasets into the SMOS soil moisture retrieval algorithm did not fully resolve the underestimation of soil moisture, suggesting that further investigation is required to understand this bias. Also, several approaches were evaluated to improve statistical field-derived soil moisture representation in the validation of SMOS soil moisture retrieval and it is clear that good representation of soil moisture as a function of soil textures is crucial to accurately validate SMOS soil moisture products.
Nov. 2015
5281-5293
journalArticle
11
IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
DOI 10.1109/JSTARS.2018.2834383
7
IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
ISSN 2151-1535
K. Guan
Z. Li
L. N. Rao
F. Gao
D. Xie
N. T. Hien
Z. Zeng
Agriculture
Earth
Remote sensing
Production
Satellites
agriculture
MODIS
Optical sensors
Landsat
Advanced Land Observing Satellite 2 (ALOS-2)
crop yield
image fusion
moderate resolution imaging spectroradiometer (MODIS)
paddy rice
Viet Nam
Mapping Paddy Rice Area and Yields Over Thai Binh Province in Viet Nam From MODIS, Landsat, and ALOS-2/PALSAR-2
This study uses multiple satellite datasets to map paddy rice areas and yields for the Thai Binh Province, Viet Nam, over the summer growing season of 2015. The major datasets used are: first, surface reflectance and vegetation indices (VI) by fusing the optical observations from the Landsat sensors and the MODerate Resolution Imaging Spectroradiometer; and second, the L-band radar data from the PALSAR-2 sensor onboard the Advanced Land Observing Satellite 2. We find that although the fused VI time series are not necessarily beneficial for paddy rice mapping, the fusion datasets reduce observational gaps and allow us to better identify peak VI values and derive their empirical relationships with crop-cutting yield data (R2 = 0.4 for all the rice types, and R2 = 0.69 for the dominant rice type -58% of all the sampled fields). The L-band radar data have slightly lower performance in rice mapping than the optical satellite data, while it has much less contribution to yield estimation than the optical data. Furthermore, our study suggests the geolocation errors of satellite images be taken into account when selecting small sample are as for crop cutting. This practice will ensure the representativeness of crop-cutting sample areas with regard to satellite observations and thus better linkages between field data and satellite pixels for yield modeling. We also highlight the need of crop-cutting data from multiple years and/or at different regions to account for the spatial and temporal variations of harvest index to improve the spatially explicit rice yield estimates through satellite observations.
July 2018
2238-2252
journalArticle
6
IEEE Robotics and Automation Letters
DOI 10.1109/LRA.2021.3062337
2
IEEE Robotics and Automation Letters
ISSN 2377-3766
X. Kan
T. C. Thayer
S. Carpin
K. Karydis
Robots
Agriculture
Task analysis
Robot kinematics
Base stations
Planning
robotics and automation in agriculture and forestry
scheduling and coordination
Stochastic processes
task and motion planning
Task Planning on Stochastic Aisle Graphs for Precision Agriculture
This work addresses task planning under uncertainty for precision agriculture applications whereby task costs are uncertain and the gain of completing a task is proportional to resource consumption (such as water consumption in precision irrigation). The goal is to complete all tasks while prioritizing those that are more urgent, and subject to diverse budget thresholds and stochastic costs for tasks. To describe agriculture-related environments that incorporate stochastic costs to complete tasks, a new Stochastic-Vertex-Cost Aisle Graph (SAG) is introduced. Then, a task allocation algorithm, termed Next-Best-Action Planning (NBA-P), is proposed. NBA-P utilizes the underlying structure enabled by SAG, and tackles the task planning problem by simultaneously determining the optimal tasks to perform and an optimal time to exit (i.e. return to a base station), at run-time. The proposed approach is tested with both simulated data and real-world experimental datasets collected in a commercial vineyard, in both single- and multi-robot scenarios. In all cases, NBA-P outperforms other evaluated methods in terms of return per visited vertex, wasted resources resulting from aborted tasks (i.e. when a budget threshold is exceeded), and total visited vertices.
April 2021
3287-3294
journalArticle
60
IEEE Transactions on Geoscience and Remote Sensing
DOI 10.1109/TGRS.2022.3158644
IEEE Transactions on Geoscience and Remote Sensing
ISSN 1558-0644
J. Jiang
Q. Zhang
W. Wang
Y. Wu
H. Zheng
X. Yao
Y. Zhu
W. Cao
T. Cheng
Remote sensing
machine learning
Calibration
Reflectivity
Satellite broadcasting
Autonomous aerial vehicles
Cubist
nitrogen
Nitrogen
radiometric correction
Radiometry
Sentinel-2
unmanned aerial vehicles (UAVs)
MACA: A Relative Radiometric Correction Method for Multiflight Unmanned Aerial Vehicle Images Based on Concurrent Satellite Imagery
Unmanned aerial vehicle (UAV) offers an unprecedented observing potential with ultrahigh spatial and temporal resolutions and high flexibility. However, it remains difficult to solve the radiometric inconsistency of multiflight UAV imagery. This study proposed a relative radiometric correction method for multiflight UAV images based on concurrent satellite imagery (MACA) consisting of two steps, i.e., cross-sensor spectral fitting (CSF) and fine-resolution spectral calibration (FSC). In CSF, relationships of multiflight UAV reflectance and the concurrent satellite reflectance were established for generating the fine-resolution reference imagery. Subsequently, a relative radiometric correction model was constructed in the FSC step to correct multiflight UAV imagery. The performance of MACA was evaluated using multiflight UAV datasets acquired on six cropland sites and a concurrent Sentinel-2 image. Compared with four typical or state-of-the-art relative correction methods, the correction using MACA yielded better consistency between UAV and Sentinel-2 data, regardless of individual spectral bands ( $\text{R}^{2} =0.79$ –0.86, root mean square error (RMSE) $=0.004$ –0.019) or vegetation indices (VIs) ( $\text{R}^{2} =0.80$ –0.86, RMSE $=0.024$ –0.054). Moreover, the prediction of plant nitrogen accumulation (PNA) based on the MACA-corrected UAV data had the highest accuracy and showed the spatial variation most significantly within and between fields for all sites. The results demonstrated that MACA was more robust in reducing spectral mismatch across sensors and eliminating the subjective error of pseudo-invariant features (PIFs) selection. MACA has the potential to be used to cross-calibrate multisensor data into a consistent standard, which will benefit multisensor synergies.
2022
1-14
journalArticle
10
IEEE Access
DOI 10.1109/ACCESS.2022.3165583
IEEE Access
ISSN 2169-3536
V. K. Gajjar
A. K. Nambisan
K. L. Kosbar
Convolutional neural networks
Feature extraction
convolutional neural networks
Support vector machines
transfer learning
Transfer learning
Plants (biology)
Training data
plant identification
Measurement
imbalanced dataset
Leaf dataset
Plant Identification in a Combined-Imbalanced Leaf Dataset
Plant identification has applications in ethnopharmacology and agriculture. Since leaves are one of a distinguishable feature of a plant, they are routinely used for identification. Recent developments in deep learning have made it possible to accurately identify the majority of samples in five publicly available leaf datasets. However, each dataset captures the images in a highly controlled environment. This paper evaluates the performance of EfficientNet and several other convolutional neural network (CNN) architectures when applied to a combination of the LeafSnap, Middle European Woody Plants 2014, Flavia, Swedish, and Folio datasets. To normalize the impact of imbalance resulting from combining the original datasets, we used oversampling, undersampling, and transfer learning techniques to construct an end-to-end CNN classifier. We placed greater emphasis on metrics appropriate for a diverse-imbalanced dataset rather than stressing high performance on any one of the original datasets. A model from EfficientNet’s family of CNN models achieved a highly accurate F-score of 0.9861 on the combined dataset.
2022
37882-37891
journalArticle
10
IEEE Access
DOI 10.1109/ACCESS.2022.3199926
IEEE Access
ISSN 2169-3536
P. Sahu
A. P. Singh
A. Chug
D. Singh
Crops
Diseases
Agriculture
Hyperspectral imaging
Machine learning
classification
Classification
Vegetation mapping
Databases
banana
diseases
hyperspectral
imaging
ripeness
Systematics
A Systematic Literature Review of Machine Learning Techniques Deployed in Agriculture: A Case Study of Banana Crop
Agricultural productivity is the asset on which the world’s economy thoroughly relies. This is one of the major causes that disease identification in fruits and plants occupies a salient role in farming space, as having disease disorders in them is obvious. There is a need to carry genuine supervision to avoid crucial consequences in vegetation; otherwise, corresponding vegetation standards, quantity, and productiveness gets affected. At present, a recognition system is required in the food handling industries to uplift the effectiveness of productivity to cope with demand in the community. The study has been carried out to perform a systematic literature review of research papers that deployed machine learning (ML) techniques in agriculture, applicable to the banana plant and fruit production. Thus; it could help upcoming researchers in their endeavors to identify the level and kind of research done so far. The authors investigated the problems related to banana crops such as disease classification, chilling injuries detection, ripeness, moisture content, etc. Moreover, the authors have also reviewed the deployed frameworks based on ML, sources of data collection, and the comprehensive results achieved for each study. Furthermore, ML architectures/techniques were evaluated using a range of performance measures. It has been observed that some studies used the PlantVillage dataset, a few have used Godliver and Scotnelson dataset, and the rest were based on either real-field image acquisition or on limited private datasets. Hence, more datasets are needed to be acquired to enhance the disease identification process and to handle the other kind of problems (e.g. chilling injuries detection, ripeness, etc.) present in the crops. Furthermore, the authors have also carried out a comparison of popular ML techniques like support vector machines, convolutional neural networks, regression, etc. to make differences in their performance. In this study, several research gaps are addressed, allowing for increased transparency in identifying different diseases even before symptoms arise and also for monitoring the above-mentioned problems related to crops.
2022
87333-87360
journalArticle
7
IEEE Access
DOI 10.1109/ACCESS.2019.2939787
IEEE Access
ISSN 2169-3536
T. Zhou
W. Shi
X. Liu
F. Tao
Z. Qian
R. Zhang
Data models
Monitoring
Indexes
Big Data
Internet of Things (IoT)
Safety
Vehicles
big data
Car-hailing
geographical information science (GIS)
points of interest (POI)
potentially dangerous area
Trajectory
trajectory data
A Novel Approach for Online Car-Hailing Monitoring Using Spatiotemporal Big Data
Car-hailing service has increasingly become popular and fundamentally changed the way people travel in the era of sharing economy. Although such service brings convenience to people's lives, it also causes safety and property concerns. Many studies have been conducted to access the efficiency and effectiveness of car-hailing, but little has been done on its safety monitoring. However, with the rapid development of information technologies such as Internet of Things (IoT), Geographical Information Science (GIS) and automatic monitoring, a more advantageous approach than the current simple drivers screening and testing is feasible. A new model including five indexes i.e. region dangerous index, offset distance of the origin-destination, real-time speed under traffic conditions, vehicle travel time and passenger information, is therefore proposed in this paper based on big data mining of the historical vehicle GPS trajectory data. Experiments were conducted to validate the model in the Gangzha District of Nantong City, China. Several other types of data were used in the experiments, e.g. points of interest (POI), road network data and urban image. The results showed that the proposed model effectively monitored the vehicle when it was driving in a “potentially dangerous area”. In addition, the model could accurately identify the driver's abnormal driving behaviors, such as bypass and abnormal stop. The prediction accuracy of the experiments was 92.06%, among which the discrimination accuracy of the abnormal stop was 100% and that of the detour was 90.57%. All these validate the applicability of the model for future management systems for car-hailing services.
2019
128936-128947
journalArticle
21
IEEE Sensors Journal
DOI 10.1109/JSEN.2020.3048593
16
IEEE Sensors Journal
ISSN 1558-1748
R. Saha
A. Chakraborty
S. Misra
S. K. Das
C. Chatterjee
Computer architecture
Wireless sensor networks
Cloud computing
Sensors
Temperature measurement
correlation
distributed learning
edge intelligence
Intelligent sensors
sensor cloud
Sensor virtualization
Virtualization
DLSense: Distributed Learning-Based Smart Virtual Sensing for Precision Agriculture
This work presents the design of an efficient edge-empowered sensor-cloud architecture equipped with a smart virtual sensing scheme for precision agriculture. Traditionally, in agricultural sensor-cloud, sensor nodes send raw sensed data periodically to the cloud, resulting in higher latency and higher energy and bandwidth consumption. The environment-dependent nature of agricultural parameters also limits the serviceability of sensor-cloud in regions with damaged or unemployed sensors. Moreover, agricultural sensor-cloud suffers from privacy issues due to the sharing of sensitive farming data across third-party service providers. To address these drawbacks, we first propose a modified sensor-cloud architecture using edge devices as the middleware layer for sensor virtualization, thereby reducing service provisioning latency and resource consumption. Next, we propose DLSense, a novel intelligent virtualization scheme to aid in the design of virtual sensors in the absence of working sensor nodes in a region. DLSense utilizes correlation theory and distributed learning in the edge devices to predict sensor data and enables the sharing of information of the trained models instead of raw sensed data, thus imparting privacy. Finally, we evaluate the performance of the DLSense scheme through extensive simulations and an experimental case study of an agricultural application. Results demonstrate that our proposed scheme reduces latency and service cost by 81% and 66%, respectively, and increases service availability by 39% compared to the state-of-the-art methods.
15 Aug.15, 2021
17556-17563
journalArticle
9
IEEE Access
DOI 10.1109/ACCESS.2021.3115258
IEEE Access
ISSN 2169-3536
R. Bertoglio
C. Corbo
F. M. Renga
M. Matteucci
Agriculture
Climate change
precision agriculture
Digital agriculture
Databases
Agriculture 4.0
bibliometrics
Bibliometrics
climate-smart agriculture
digital agriculture
Global navigation satellite system
literature review
Precision engineering
The Digital Agricultural Revolution: A Bibliometric Analysis Literature Review
The application of digital technologies in agriculture can improve traditional practices to adapt to climate change, reduce Greenhouse Gases (GHG) emissions, and promote a sustainable intensification for food security. Some authors argued that we are experiencing a Digital Agricultural Revolution (DAR) that will boost sustainable farming. This study aims to find evidence of the ongoing DAR process and clarify its roots, what it means, and where it is heading. We investigated the scientific literature with bibliometric analysis tools to produce an objective and reproducible literature review. We retrieved 4995 articles by querying the Web of Science database in the timespan 2012-2019, and we analyzed the obtained dataset to answer three specific research questions: i) what is the spectrum of the DAR-related terminology?; ii) what are the key articles and the most influential journals, institutions, and countries?; iii) what are the main research streams and the emerging topics? By grouping the authors’ keywords reported on publications, we identified five main research streams: Climate-Smart Agriculture (CSA), Site-Specific Management (SSM), Remote Sensing (RS), Internet of Things (IoT), and Artificial Intelligence (AI). To provide a broad overview of each of these topics, we analyzed relevant review articles, and we present here the main achievements and the ongoing challenges. Finally, we showed the trending topics of the last three years (2017, 2018, 2019).
2021
134762-134782
journalArticle
X. Yang
L. Shu
J. Chen
M. A. Ferrag
J. Wu
E. Nurellari
K. Huang
Agriculture
Production
Security
Internet of Things
security
Privacy
smart agriculture
agricultural automation
Agricultural artificial intelligence
agricultural Internet of Things
Information technology
Loss measurement
A Survey on Smart Agriculture: Development Modes, Technologies, and Security and Privacy Challenges
With the deep combination of both modern information technology and traditional agriculture, the era of agriculture 4.0, which takes the form of smart agriculture, has come. Smart agriculture provides solutions for agricultural intelligence and automation. However, information security issues cannot be ignored with the development of agriculture brought by modern information technology. In this paper, three typical development modes of smart agriculture (precision agriculture, facility agriculture, and order agriculture) are presented. Then, 7 key technologies and 11 key applications are derived from the above modes. Based on the above technologies and applications, 6 security and privacy countermeasures (authentication and access control, privacy-preserving, blockchain-based solutions for data integrity, cryptography and key management, physical countermeasures, and intrusion detection systems) are summarized and discussed. Moreover, the security challenges of smart agriculture are analyzed and organized into two aspects: 1) agricultural production, and 2) information technology. Most current research projects have not taken agricultural equipment as potential security threats. Therefore, we did some additional experiments based on solar insecticidal lamps Internet of Things, and the results indicate that agricultural equipment has an impact on agricultural security. Finally, more technologies (5 G communication, fog computing, Internet of Everything, renewable energy management system, software defined network, virtual reality, augmented reality, and cyber security datasets for smart agriculture) are described as the future research directions of smart agriculture.
February 2021
273-302
8
IEEE/CAA Journal of Automatica Sinica
DOI 10.1109/JAS.2020.1003536
2
IEEE/CAA Journal of Automatica Sinica
ISSN 2329-9274
journalArticle
13
IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
DOI 10.1109/JSTARS.2020.3016135
IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
ISSN 2151-1535
J. Jiang
Q. Zhang
X. Yao
Y. Tian
Y. Zhu
W. Cao
T. Cheng
Crops
Monitoring
Agriculture
Spatial resolution
Sensors
Reflectivity
image fusion
heterogeneity
spatiotemporal fusion
Spatiotemporal phenomena
subfield monitoring
HISTIF: A New Spatiotemporal Image Fusion Method for High-Resolution Monitoring of Crops at the Subfield Level
Satellite-based time-series crop monitoring at the subfield level is essential to the efficient implementation of precision crop management. Existing spatiotemporal image fusion techniques can be helpful, but they were often proposed to generate medium-resolution images. This study proposed a high-resolution spatiotemporal image fusion method (HISTIF) consisting of filtering for cross-scale spatial matching (FCSM) and multiplicative modulation of temporal change (MMTC). In FCSM, we considered both point spread function effect and geo-registration errors between fine and coarse resolution images. Subsequently, MMTC used pixel-based multiplicative factors to estimate the temporal change between reference and prediction dates without image classification. The performance of HISTIF was evaluated using both simulated and real datasets with one from real Gaofen-1 (GF-1) and simulated Landsat-like/Sentinel-like images, and the other from real GF-1 and real Landsat/Sentinel-2 data on two sites. HISTIF was compared with the existing methods spatial and temporal adaptive reflectance fusion model (STARFM), FSDAF, and Fit-FC. The results demonstrated that HISTIF produced substantial reduction in the fusion error from cross-scale spatial mismatch and accurate reconstruction in spatial details within fields, regardless of simulated or real data. The images predicted by STARFM exhibited pronounced blocky artifacts. While the images predicted by HISTIF and Fit-FC both showed clear within-field variability patterns, HISTIF was able to reduce the spectral distortion more significantly than Fit-FC. Furthermore, HISTIF exhibited the most stable performance across sensors. The findings suggest that HISTIF could be beneficial for the frequent and detailed monitoring of crop growth at the subfield level.
2020
4607-4626
journalArticle
D. Puthal
X. Wu
N. Surya
R. Ranjan
J. Chen
Real-time systems
Encryption
Sensors
Big data
Big data stream
data confidentiality
data integrity
data security
selective encryption
SEEN: A Selective Encryption Method to Ensure Confidentiality for Big Sensing Data Streams
Resource constrained sensing devices are being used widely to build and deploy self-organizing wireless sensor networks for a variety of critical applications such as smart cities, smart health, precision agriculture and industrial control systems. Many such devices sense the deployed environment and generate a variety of data and send them to the server for analysis as data streams. A Data Stream Manager (DSM) at the server collects the data streams (often called big data) to perform real time analysis and decision-making for these critical applications. A malicious adversary may access or tamper with the data in transit. One of the challenging tasks in such applications is to assure the trustworthiness of the collected data so that any decisions are made on the processing of correct data. Assuring high data trustworthiness requires that the system satisfies two key security properties: confidentiality and integrity. To ensure the confidentiality of collected data, we need to prevent sensitive information from reaching the wrong people by ensuring that the right people are getting it. Sensed data are always associated with different sensitivity levels based on the sensitivity of emerging applications or the sensed data types or the sensing devices. For example, a temperature in a precision agriculture application may not be as sensitive as monitored data in smart health. Providing multilevel data confidentiality along with data integrity for big sensing data streams in the context of near real time analytics is a challenging problem. In this paper, we propose a Selective Encryption (SEEN) method to secure big sensing data streams that satisfies the desired multiple levels of confidentiality and data integrity. Our method is based on two key concepts: common shared keys that are initialized and updated by DSM without requiring retransmission, and a seamless key refreshment process without interrupting the data stream encryption/decryption. Theoretical analyses and experimental results of our SEEN method show that it can significantly improve the efficiency and buffer usage at DSM without compromising the confidentiality and integrity of the data streams.
1 Sept. 2019
379-392
5
IEEE Transactions on Big Data
DOI 10.1109/TBDATA.2017.2702172
3
IEEE Transactions on Big Data
ISSN 2332-7790
journalArticle
60
IEEE Transactions on Geoscience and Remote Sensing
DOI 10.1109/TGRS.2021.3093041
IEEE Transactions on Geoscience and Remote Sensing
ISSN 1558-0644
D. Wang
D. Zhang
G. Yang
B. Xu
Y. Luo
X. Yang
Feature extraction
Deep learning
Agriculture
Image segmentation
Semantics
Adhesives
Ear
Field conditions
fully convolutional neural network (FCNN)
regression convolutional neural network (RCNN)
wheat ears counting
SSRNet: In-Field Counting Wheat Ears Using Multi-Stage Convolutional Neural Network
Fast and accurate counting of wheat ears in field conditions is a key element for determining wheat yield. To obtain the number of wheat ears in a field, we propose a new counting algorithm based on computer vision. This algorithm counts wheat ears in remote images through semantic segmentation regression network (SSRNet). SSRNet is a multistage convolutional neural network that we propose to achieve counting problems through regression. In SSRNet, first, the original image is cropped to increase the amount of data. This method effectively solves the small sample dataset. Next, based on the cropping results, we build a fully convolutional neural network (FCNN) to segment wheat ears in field conditions. FCNN increases the accuracy of wheat ears counting by accurately segmenting wheat ears in a complex background. Then, we build a regression convolutional neural network (RCNN) to count wheat ears based on the segmentation results of FCNN. In RCNN, we propose a new activation function positive rectification linear unit (PrLU) to process the last layer of the fully connected layer, so that RCNN can effectively count the number of wheat ears in the image. Finally, a counting strategy is proposed to count the number of wheat ears in the original image. To verify the counting performance of SSRNet, we compare the counting result of SSRNet with the real value of manual statistics. The results show that the average accuracy (Acc), <inline-formula> <tex-math notation="LaTeX">$R^{2}$ </tex-math></inline-formula>, and root mean squared error (RMSE) of the SSRNet count results on the test set in this article are 0.980, 0.996, and 9.437, respectively. It can be seen from the results that our proposed method can accurately count wheat ears in field conditions. At the same time, the counting time (0.11 s) shows that SSRNet can quickly estimate the number of wheat ears in field conditions. We concluded that this study can provide important technical support for the high-throughput field wheat ears counting task in large-scale phenotyping work.
2022
1-11
journalArticle
Z. Liu
W. Zhang
S. Lin
T. Q. S. Quek
Deep learning
Training
Machine learning
Correlation
Data integration
Cost function
Data compression
Encoding
heterogeneous sensor data
missing data imputation
multimodal data fusion
Heterogeneous Sensor Data Fusion By Deep Multimodal Encoding
Heterogeneous sensor data fusion is a challenging field that has gathered significant interest in recent years. Two of these challenges are learning from data with missing values, and finding shared representations for multimodal data to improve inference and prediction. In this paper, we propose amultimodal data fusion framework, the deep multimodal encoder (DME), based on deep learning techniques for sensor data compression, missing data imputation, and new modality prediction under multimodal scenarios. While traditional methods capture only the intramodal correlations, DME is able to mine both the intramodal correlations in the initial layers and the enhanced intermodal correlations in the deeper layers. In this way, the statistical structure of sensor data may be better exploited for data compression. By incorporating our new objective function, DME shows remarkable ability for missing data imputation tasks in sensor data. The shared multimodal representation learned by DME may be used directly for predicting new modalities. In experiments with a real-world dataset collected from a 40-node agriculture sensor network which contains three modalities, DME can achieve a root mean square error (RMSE) of missing data imputation which is only 20% of the traditional methods like K-nearest neighbors and sparse principal component analysis and the performance is robust to different missing rates. It can also reconstruct temperature modality from humidity and illuminance with an RMSE of 7 °C, directly from a highly compressed (2.1%) shared representation that was learned from incomplete (80% missing) data.
April 2017
479-491
11
IEEE Journal of Selected Topics in Signal Processing
DOI 10.1109/JSTSP.2017.2679538
3
IEEE Journal of Selected Topics in Signal Processing
ISSN 1941-0484
journalArticle
69
IEEE Transactions on Instrumentation and Measurement
DOI 10.1109/TIM.2019.2947125
7
IEEE Transactions on Instrumentation and Measurement
ISSN 1557-9662
D. Shadrin
A. Menshchikov
A. Somov
G. Bornemann
J. Hauslage
M. Fedorov
Monitoring
Artificial intelligence
precision agriculture
Robot sensing systems
embedded sensing
Imaging
Artificial intelligence (AI)
Greenhouses
sensing and control
smart sensing
Enabling Precision Agriculture Through Embedded Sensing With Artificial Intelligence
Artificial intelligence (AI) has smoothly penetrated in a number of monitoring and control applications including agriculture. However, research efforts toward low-power sensing devices with fully functional AI on board are still fragmented. In this article, we present an embedded system enriched with the AI, ensuring the continuous analysis and in situ prediction of the growth dynamics of plant leaves. The embedded solution is grounded on a low-power embedded sensing system with a graphics processing unit (GPU) and is able to run the neural network-based AI on board. We use a recurrent neural network (RNN) called the long short-term memory network (LSTM) as a core of AI in our system. The proposed approach guarantees the system autonomous operation for 180 days using a standard Li-ion battery. We rely on the state-of-the-art mobile graphical chips for “smart” analysis and control of autonomous devices. This pilot study opens up wide vista for a variety of intelligent monitoring applications, especially in the agriculture domain. In addition, we share with the research community the Tomato Growth data set.
July 2020
4103-4113
journalArticle
9
IEEE/CAA Journal of Automatica Sinica
DOI 10.1109/JAS.2021.1004344
3
IEEE/CAA Journal of Automatica Sinica
ISSN 2329-9274
M. A. Ferrag
L. Shu
O. Friha
X. Yang
Agriculture
Machine learning
Cloud computing
Internet of Things
Performance evaluation
smart agriculture
Agriculture 4.0
cyber security
Intrusion detection
intrusion detection system
machine learning approaches
Smart grids
Cyber Security Intrusion Detection for Agriculture 4.0: Machine Learning-Based Solutions, Datasets, and Future Directions
In this paper, we review and analyze intrusion detection systems for Agriculture 4.0 cyber security. Specifically, we present cyber security threats and evaluation metrics used in the performance evaluation of an intrusion detection system for Agriculture 4.0. Then, we evaluate intrusion detection systems according to emerging technologies, including, Cloud computing, Fog/Edge computing, Network virtualization, Autonomous tractors, Drones, Internet of Things, Industrial agriculture, and Smart Grids. Based on the machine learning technique used, we provide a comprehensive classification of intrusion detection systems in each emerging technology. Furthermore, we present public datasets, and the implementation frameworks applied in the performance evaluation of intrusion detection systems for Agriculture 4.0. Finally, we outline challenges and future research directions in cyber security intrusion detection for Agriculture 4.0.
March 2022
407-436
journalArticle
8
IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
DOI 10.1109/JSTARS.2014.2363595
4
IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
ISSN 2151-1535
C. O. Dumitru
S. Cui
G. Schwarz
M. Datcu
Feature extraction
Synthetic aperture radar
synthetic aperture radar (SAR)
Earth
Remote sensing
classification
Semantics
Satellites
feature extraction
Annotation
high-resolution images
indexing
ontologies
querying
semantic catalogs
taxonomies
Taxonomy
TerraSAR-X
Information Content of Very-High-Resolution SAR Images: Semantics, Geospatial Context, and Ontologies
Currently, the amount of collected Earth Observation (EO) data is increasing considerably with a rate of several Terabytes of data per day. As a consequence of this increasing data volume, new concepts for exploration and information retrieval are urgently needed. To this end, we propose to explore satellite image data via an image information mining (IIM) approach in which the main steps are feature extraction, classification, semantic annotation, and interactive query processing. This leads to a new process chain and a robust taxonomy for the retrieved categories capitalizing on human interaction and judgment. We concentrated on land cover categories that can be retrieved from high-resolution synthetic aperture radar (SAR) images of the spaceborne TerraSAR-X instrument, where we annotated different urban areas all over the world and defined a taxonomy element for each prevailing surface cover category. The annotation resulted from a test dataset comprising more than 100 scenes covering diverse areas of Africa, Asia, Europe, the Middle East, and North and South America. The scenes were grouped into several collections with similar source areas and each collection was processed separately in order to discern regional characteristics. In the first processing step, each scene was tiled into patches. Then the features were extracted from each patch by a Gabor filter bank and a support vector machine with relevance feedback classifying the feature sets into user-oriented land cover categories. Finally, the categories were semantically annotated using Google Earth for ground truthing. The annotation followed a multilevel approach that allowed the fusion of information being visible on different resolution levels. The novelty of this paper lies in the fact that a semantic annotation was performed with a large number of high-resolution radar images that allowed the definition of more than 850 surface cover categories. This opens the way toward an automated identification and classification of urban areas, infrastructure (e.g., airports), geographic objects (e.g., mountains), industrial installations, military compounds, vegetation, and agriculture. Applications that may result from this work can be a semantic catalog of urban images to be used in crisis situations or after a disaster. In addition, the proposed taxonomies can become a basis for building a semantic catalog of satellite images. Finally, we defined four powerful types of high-level queries. Querying on such high levels provides new opportunities for users to search an image database for specific parameters or semantic relationships.
April 2015
1635-1650
journalArticle
21
IEEE Sensors Journal
DOI 10.1109/JSEN.2020.3017695
16
IEEE Sensors Journal
ISSN 1558-1748
J. Song
Q. Zhong
W. Wang
C. Su
Z. Tan
Y. Liu
Agriculture
Cloud computing
Security
Sensors
Data privacy
Privacy
data aggregation
Data aggregation
data privacy
data publishing
flexibility
Smart agriculture
FPDP: Flexible Privacy-Preserving Data Publishing Scheme for Smart Agriculture
The development of the Internet of Things (IoT) and 5th generation wireless network (5G) is set to push the smart agriculture to the next level since the massive and real-time data can be collected to monitor the status of crops and livestock, logistics management, and other important information. Recently, COVID-19 has attracted more human attention to food safety, which also has a positive impact on smart agriculture market share. However, the security and privacy concern for smart agriculture has become more prominent. Since smart agriculture implies working with large sets of data, which usually sensitive, some are even confidential, and once leakage it can expose user privacy. Meanwhile, considering the data publishing of smart agriculture helps the public or investors to real-timely anticipate risks and benefits, these data are also a public resource. To balance the data publishing and data privacy, in this article, a privacy-preserving data aggregation scheme with a flexibility property uses ElGamal Cryptosystem is proposed. It is proved to be secure, private, and flexible with the analysis and performance simulation.
15 Aug.15, 2021
17430-17438
journalArticle
22
IEEE Sensors Journal
DOI 10.1109/JSEN.2022.3203853
20
IEEE Sensors Journal
ISSN 1558-1748
J. Byabazaire
G. M. P. O’Hare
D. T. Delaney
Data models
machine learning
Internet of Things
Big Data
Internet of Things (IoT)
Quality assessment
Measurement
Big data model
Data integrity
data quality
Sensor phenomena and characterization
trust
End-to-End Data Quality Assessment Using Trust for Data Shared IoT Deployments
Continued development of communication technologies has led to widespread Internet-of-Things (IoT) integration into various domains, including health, manufacturing, automotive, and precision agriculture. This has further led to the increased sharing of data among such domains to foster innovation. Most of these IoT deployments, however, are based on heterogeneous, pervasive sensors, which can lead to quality issues in the recorded data. This can lead to sharing of inaccurate or inconsistent data. There is a significant need to assess the quality of the collected data, should it be shared with multiple application domains, as inconsistencies in the data could have financial or health ramifications. This article builds on the recent research on trust metrics and presents a framework to integrate such metrics into the IoT data cycle for real-time data quality assessment. Critically, this article adopts a mechanism to facilitate end-user parameterization of a trust metric tailoring its use in the framework. Trust is a well-established metric that has been used to determine the validity of a piece or source of data in crowd-sourced or other unreliable data collection techniques such as that in IoT. The article further discusses how the trust-based framework eliminates the requirement for a gold standard and provides visibility into data quality assessment throughout the big data model. To qualify the use of trust as a measure of quality, an experiment is conducted using data collected from an IoT deployment of sensors to measure air quality in which low-cost sensors were colocated with a gold standard reference sensor. The calculated trust metric is compared with two well-understood metrics for data quality, root mean square error (RMSE), and mean absolute error (MAE). A strong correlation between the trust metric and the comparison metrics shows that trust may be used as an indicative quality metric for data quality. The metric incorporates the additional benefit of its ability for use in low context scenarios, as opposed to RMSE and MAE, which require a reference for comparison.
15 Oct.15, 2022
19995-20009
journalArticle
9
IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
DOI 10.1109/JSTARS.2016.2574810
12
IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
ISSN 2151-1535
L. Zhou
N. Chen
Z. Chen
C. Xing
Soil moisture
Agriculture
Earth
Remote sensing
Cloud computing
Distributed databases
Servers
earth observation data (EOD) sharing enhancement
precision agriculture (PA)
sensor observation service (SOS)
ROSCC: An Efficient Remote Sensing Observation-Sharing Method Based on Cloud Computing for Soil Moisture Mapping in Precision Agriculture
The inversion of remote sensing images is crucial for soil moisture mapping in precision agriculture. However, the large size of remote sensing images complicates their management. Therefore, this study proposes a remote sensing observation sharing method based on cloud computing (ROSCC) to enhance remote sensing observation storage, processing, and service capability. The ROSCC framework consists of a cloud computing-enabled sensor observation service, web processing service tier, and a distributed database tier. Using MongoDB as the distributed database and Apache Hadoop as the cloud computing service, this study achieves a high-throughput method for remote sensing observation storage and distribution. The map, reduced algorithms and the table structure design in distributed databases are then explained. Along the Yangtze River, the longest river in China, Hubei Province was selected as the study area to test the proposed framework. Using GF-1 as a data source, an experiment was performed to enhance earth observation data (EOD) storage and achieve large-scale soil moisture mapping. The proposed ROSCC can be applied to enhance EOD sharing in cloud computing context, so as to achieve soil moisture mapping via the modified perpendicular drought index in an efficient way to better serve precision agriculture.
Dec. 2016
5588-5598
journalArticle
7
IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
DOI 10.1109/JSTARS.2014.2315593
11
IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
ISSN 2151-1535
W. Han
Z. Yang
L. Di
B. Zhang
C. Peng
Agriculture
Geospatial analysis
Standards
Servers
Data visualization
Cropland Data Layer (CDL)
CropScape
CropScape, geospatial web service,
geospatial data sharing and interoperability
geospatial web service
service chain
Web services
Enhancing Agricultural Geospatial Data Dissemination and Applications Using Geospatial Web Services
There are many important publicly available agricultural geospatial data products for the agriculture-related research, applications, and educational outreach programs. The traditional data distribution method cannot fully meet users' on-demand geospatial data needs. This paper presents interoperable, standard-compliant Web services developed for geospatial data access, query, retrieval, statistics, mapping, and comparison. Those standard geospatial Web services can be integrated in scientific workflows to accomplish specific tasks or consumed over the Web to create value-added new geospatial application by users. In addition, this paper demonstrates, via real world use cases, applications of those services and potential impacts on facilitating geospatial Cropland Data Layer (CDL) retrieval, analysis, visualization, dissemination and integration in agricultural industry, government, research, and educational communities. This paper also shows that the geospatial Web service approach helps improve the reusability, interoperability, dissemination, and utilization of agricultural geospatial data. It allows for integrating multiple online applications and different geospatial data sources, and enables automated retrieving and delivery of agricultural geospatial information for decision-making support.
Nov. 2014
4539-4547
journalArticle
21
IEEE Sensors Journal
DOI 10.1109/JSEN.2021.3050084
16
IEEE Sensors Journal
ISSN 1558-1748
S. Nesteruk
D. Shadrin
M. Pukalchik
A. Somov
C. Zeidler
P. Zabel
D. Schubert
Monitoring
computer vision
Agriculture
Cameras
Machine learning
Plants (biology)
machine learning
Classification
Image coding
Antarctica
controlled-environment agriculture
image compression
Image Compression and Plants Classification Using Machine Learning in Controlled-Environment Agriculture: Antarctic Station Use Case
In this article, we share our experience in the scope of controlled-environment agriculture automation in the Antarctic station greenhouse facility called EDEN ISS. For remote plant monitoring, control, and maintenance, we solve the problem of plant classification. Due to the inherent communication limitations between Antarctica and Europe, we first propose the image compression mechanism for the data collection. We show that we can compress the images, on average, 7.2 times for efficient transmission over the weak channel. Moreover, we prove that decompressed images can be further used for computer vision applications. Upon decompressing images, we apply machine learning for the classification task. We achieve 92.6% accuracy on an 18-classes unbalanced dataset. The proposed approach is promising for a number of agriculture related applications, including the plant classification, identification of plant diseases, and deviation of plant phenology.
15 Aug.15, 2021
17564-17572
bookSection
62
ANNUAL REVIEW OF ENTOMOLOGY, VOL 62
Rosenheim
Jay A.
Gratton
Claudio
Berenbaum
MR
Ecoinformatics (Big Data) for Agricultural Entomology: Pitfalls, Progress, and Promise
Ecoinformatics, as defined in this review, is the use of preexisting data sets to address questions in ecology. We provide the first review of ecoinformatics methods in agricultural entomology. Ecoinformatics methods have been used to address the full range of questions studied by agricultural entomologists, enabled by the special opportunities associated with data sets, nearly all of which have been observational, that are larger and more diverse and that embrace larger spatial and temporal scales than most experimental studies do. We argue that ecoinformatics research methods and traditional, experimental research methods have strengths and weaknesses that are largely complementary. We address the important interpretational challenges associated with observational data sets, highlight common pitfalls, and propose some best practices for researchers using these methods. Ecoinformatics methods hold great promise as a vehicle for capitalizing on the explosion of data emanating from farmers, researchers, and the public, as novel sampling and sensing techniques are developed and digital data sharing becomes more widespread.
2017
WOS:000393550200023
DOI: 10.1146/annurev-ento-031616-035444
399-417
bookSection
164
PLANT GENETICS AND MOLECULAR BIOLOGY
Rathore
Abhishek
Singh
Vikas K.
Pandey
Sarita K.
Rao
Chukka Srinivasa
Thakur
Vivek
Pandey
Manish K.
Kumar
V. Anil
Das
Roma Rani
Varshney
RK
Pandey
MK
Chitikineni
A
Current Status and Future Prospects of Next-Generation Data Management and Analytical Decision Support Tools for Enhancing Genetic Gains in Crops
Agricultural disciplines are becoming data intensive and the agricultural research data generation technologies are becoming sophisticated and high throughput. On the one hand, high-throughput genotyping is generating petabytes of data; on the other hand, high-throughput phenotyping platforms are also generating data of similar magnitude. Under modern integrated crop breeding, scientists are working together by integrating genomic and phenomic data sets of huge data volumes on a routine basis. To manage such huge research data sets and use them appropriately in decision making, Data Management Analysis & Decision Support Tools (DMASTs) are a prerequisite. DMASTs are required for a range of operations including generating the correct breeding experiments, maintaining pedigrees, managing phenotypic data, storing and retrieving high-throughput genotypic data, performing analytics, including trial analysis, spatial adjustments, identifications of MTAs, predicting Genomic Breeding Values (GEBVs), and various selection indices. DMASTs are also a prerequisite for understanding trait dynamics, gene action, interactions, biology, GxE, and various other factors contributing to crop improvement programs by integrating data generated from various science streams. These tools have simplified scientists' lives and empowered them in terms of data storage, data retrieval, data analytics, data visualization, and sharing with other researchers and collaborators. This chapter focuses on availability, uses, and gaps in present-day DMASTs.[GRAPHICS].
2018
WOS:000457965800013
DOI: 10.1007/10_2017_56
277-292
journalArticle
9
F1000Research
DOI 10.12688/f1000research.26903.1
Walters
Judi
Light
Kate
Robinson
Nathan
Using agricultural metadata: a novel investigation of trends in sowing date in on-farm research trials using the Online Farm Trials database.
Background: A growing ability and interest in the collection of data, together with the development and adoption of the FAIR guiding principles, has increased the amount of data available in many disciplines. This has given rise to an urgent need for robust metadata. Within the Australian grains industry, data from over thousands of on-farm research trials (Trial Projects) have been made available via the Online Farm Trials (OFT) website. OFT Trial Project metadata were developed as filters to refine front-end database searches, but could also be used as a dataset to investigate trends in metadata elements. Australian grains crops are being sown earlier, but whether on-farm research trials reflect this change is currently unknown. Methods: We investigated whether OFT Trial Project metadata could be used to detect trends in sowing dates of on-farm crop research trials across Australia, testing the hypothesis that research trials are being sown earlier in line with local farming practices. The investigation included 15 autumn-sown, winter crop species listed in the database, with trial records from 1993 to 2019. Results: Our analyses showed that (i) OFT Trial Project metadata can be used as a dataset to detect trends in sowing date; and (ii) cropping research trials are being sown earlier in Victoria and Western Australia, but no trend exists within the other states. Discussion/Conclusion: Our findings show that OFT Trial Project metadata can be used to detect trends in crop sowing date, suggesting that metadata could also be used to detect trends in othermetadata elements such as harvest date. Because OFT is a national database of research trials, further assessment of metadata may uncover important agronomic, cultural or economic trends within or across the Australian cropping regions. New information could then be used to lead practice change and increase productivity within the Australian grains industry.
2020
MEDLINE:34354820
1305-1305
conferencePaper
Qian
Peisheng
Zhao
Ziyuan
Liu
Haobing
Wang
Yingcai
Peng
Yu
Hu
Sheng
Zhang
Jing
Deng
Yue
Zeng
Zeng
IEEE
Multi-Target Deep Learning for Algal Detection and Classification
Water quality has a direct impact on industry, agriculture, and public health. Algae species are common indicators of water quality. It is because algal communities are sensitive to changes in their habitats, giving valuable knowledge on variations in water quality. However, water quality analysis requires professional inspection of algal detection and classification under microscopes, which is very time-consuming and tedious. In this paper, we propose a novel multi-target deep learning framework for algal detection and classification. Extensive experiments were carried out on a large-scale colored microscopic algal dataset. Experimental results demonstrate that the proposed method leads to the promising performance on algal detection, class identification and genus identification.
2020
WOS:000621592202072
1954-1957
42ND ANNUAL INTERNATIONAL CONFERENCES OF THE IEEE ENGINEERING IN MEDICINE AND BIOLOGY SOCIETY: ENABLING INNOVATIVE TECHNOLOGIES FOR GLOBAL HEALTHCARE EMBC'20
journalArticle
15
PLOS ONE
DOI 10.1371/journal.pone.0230735
4
Douglas
Marlis R.
Anthonysamy
Whitney J. B.
Mussmann
Steven M.
Davis
Mark A.
Louis
Wade
Douglas
Michael E.
Multi-targeted management of upland game birds at the agroecosystem interface in midwestern North America
Despite its imperative, biodiversity conservation is chronically underfunded, a deficiency that often forces management agencies to prioritize. Single-species recovery thus becomes a focus (often with socio-political implications), whereas a more economical approach would be the transition to multi-targeted management (= MTM). This challenge is best represented in Midwestern North America where biodiversity has been impacted by 300+ years of chronic anthropogenic disturbance such that native tall-grass prairie is now supplanted by an agroecosystem. Here, we develop an MTM with a population genetic metric to collaboratively manage three Illinois upland gamebirds: common pheasant (Phasianus colchicus; pheasant), northern bobwhite quail (Colinus virginianus; quail), and threatened-endangered (T&E) greater prairie chicken (Tympanuchus cupido pinnatus; prairie chicken). We first genotyped our study pheasant at 19 microsatellite DNA loci and identified three captive breeding stocks (N = 143; IL Department of Natural Resources) as being significantly bottlenecked, with relatedness > 1st-cousin (mu R = 0.158). 'Wild' (non-stocked) pheasant [N = 543; 14 Pheasant-Habitat-Areas (PHAs)] were also bottlenecked, significantly interrelated (mu R = 0.150) and differentiated (mu FST = 0.047), yet distinct from propagation stock. PHAs that encompassed significantly with larger areas also reflected greater effective population sizes (mu NE = 43; P< 0.007). We juxtaposed these data against previously published results for prairie chicken and quail, and found population genetic structure driven by drift, habitat/climate impacts, and gender-biased selection via hunter-harvest. Each species (hunter-harvested or T&E) is independently managed, yet their composite population genetic baseline provides the quantitative criteria needed for an upland game bird MTM. Its implementation would require agricultural plots to be rehabilitated/reclaimed using a land-sharing/sparing portfolio that differs markedly from the Conservation Reserve Program (CRP), where sequestered land decreases as agricultural prices escalate. Cost-savings for an MTM would accrue by synchronizing single-species management with a dwindling hunter-harvest program, and by eliminating propagation/stocking programs. This would sustain not only native grasslands and their resident species, but also accelerate conservation at the wildlife-agroecosystem interface.
2020 APR 27
WOS:000536657400005
journalArticle
263
ENVIRONMENTAL POLLUTION
DOI 10.1016/j.envpol.2020.114618
Li
Shiyang
Bhattarai
Rabin
Cooke
Richard A.
Verma
Siddhartha
Huang
Xiangfeng
Markus
Momcilo
Christianson
Laura
Relative performance of different data mining techniques for nitrate concentration and load estimation in different type of watersheds
The increasing availability of water quality datasets has led to a greater focus on hydrologic and water quality analysis, thus requiring more efficient and accurate modelling methods. Data mining techniques have been increasingly used for water quality analysis and prediction of the concentration and load of nitrogen pollutants instead of more traditional simulation methods. In this study, we tested the multilayer perceptron (MLP), k-nearest neighbor (k-NN), random forest, and reduced error pruning tree (REPTree) methods, along with the traditional linear regression, to predict nitrate levels based on longterm data from six watersheds with different land-use practices in the midwestern United States. Both the concentration and load results indicated that REPTree had the best performance, with an R-2 of 0.61 -0.85 and a relative absolute error of <75.8%. The different watershed types, however, influenced the performance of the data mining methods, where all four methods showed a higher accuracy for urban dominant watershed and lower accuracy for agricultural and forest watersheds. Out of these four methods, classification tree methods (REPTree and RF) performed better than cluster methods (MLP and k-NN) for agricultural and forested watersheds. Our results indicated that both the data structure based on the dominant land use and type of algorithmic method should be carefully considered for selecting a data mining method to predict nitrate concentration and load for a watershed. (c) 2020 Elsevier Ltd. All rights reserved.
2020 AUG
WOS:000539426400052
journalArticle
732
SCIENCE OF THE TOTAL ENVIRONMENT
DOI 10.1016/j.scitotenv.2020.139204
Libran-Embid
Felipe
Klaus
Felix
Tscharntke
Teja
Grass
Ingo
Unmanned aerial vehicles for biodiversity-friendly agricultural landscapes-A systematic review
The development of biodiversity-friendly agricultural landscapes is of major importance to meet the sustainable development challenges of our time. The emergence of unmanned aerial vehicles (UAVs), i.e. drones, has opened a new set of research and management opportunities to achieve this goal. On the one hand, this review summarizes UAV applications in agricultural landscapes, focusing on biodiversity conservation and agricultural land monitoring, based on a systematic review of the literature that resulted in 550 studies. Additionally, the review proposes how to integrate UAV research in these fields and point to new potential applications that may contribute to biodiversity-friendly agricultural landscapes. UAV-based imagery can be used to identify and monitor plants, floral resources and animals, facilitating the detection of quality habitats with high prediction power. Through vegetation indices derived from their sensors, UAVs can estimate biomass, monitor crop plant health and stress, detect pest or pathogen infestations, monitor soil fertility and target patches of high weed or invasive plant pressure, allowing precise management practices and reduced agrochemical input. Thereby, UAVs are helping to design biodiversity-friendly agricultural landscapes and to mitigate yield-biodiversity trade-offs. In conclusion, UAV applications have become a major means of biodiversity conservation and biodiversity-friendly management in agriculture, while latest developments, such as the miniaturization and decreasing costs of hyperspectral sensors, promise many new applications for the future.
2020 AUG 25
WOS:000540001600003
journalArticle
30
IEEE TRANSACTIONS ON IMAGE PROCESSING
DOI 10.1109/TIP.2021.3082297
Zhu
Pengfei
Peng
Tao
Du
Dawei
Yu
Hongtao
Zhang
Libo
Hu
Qinghua
Graph Regularized Flow Attention Network for Video Animal Counting From Drones
In this paper, we propose a large-scale video based animal counting dataset collected by drones (AnimalDrone) for agriculture and wildlife protection. The dataset consists of two subsets, i.e., PartA captured on site by drones and PartB collected from the Internet, with rich annotations of more than 4 million objects in 53, 644 frames and corresponding attributes in terms of density, altitude and view. Moreover, we develop a new graph regularized flow attention network (GFAN) to perform density map estimation in dense crowds of video clips with arbitrary crowd density, perspective, and flight altitude. Specifically, our GFAN method leverages optical flow to warp the multi-scale feature maps in sequential frames to exploit the temporal relations, and then combines the enhanced features to predict the density maps. Moreover, we introduce the multi-granularity loss function including pixel-wise density loss and region-wise count loss to enforce the network to concentrate on discriminative features for different scales of objects. Meanwhile, the graph regularizer is imposed on the density maps of multiple consecutive frames to maintain temporal coherency. Extensive experiments are conducted to demonstrate the effectiveness of the proposed method, compared with several state-of-the-art counting algorithms. The AnimalDrone dataset is available at https://github.com/VisDrone/AnimalDrone.
2021
WOS:000658333500001
5339-5351
journalArticle
16
PLOS ONE
DOI 10.1371/journal.pone.0256327
8
Natori
Yoji
Hino
Akihiko
Global identification and mapping of socio-ecological production landscapes with the Satoyama Index
Production landscapes play an important role in conserving biodiversity outside protected areas. Socio-ecological production landscapes (SEPL) are places where people use for primary production that conserve biodiversity. Such places can be found around the world, but a lack of geographic information on SEPL has resulted in their potential for conservation being neglected in policies and programs. We tested the global applicability of the Satoyama Index for identifying SEPL in multi-use cultural landscapes using global land use/cover data and two datasets of known SEPL. We found that the Satoyama Index, which was developed with a focus on biodiversity and tested in Japan, could be used globally to identify landscapes resulting from complex interactions between people and nature with statistical significance. This makes SEPL more relevant in the global conservation discourse. As the Satoyama Index mapping revealed that approximately 80% of SEPL occur outside recognized conservation priorities, such as protected areas and key biodiversity areas, identifying SEPL under the scheme of other area-based conservation measures (OECM) may bring more conservation attention to SEPL. Based on the issues identified in the SEPL mapping, we discuss ways that could improve the Satoyama Index mapping at global scale with the longitudinal temporal dimension and at more local scale with spatial and thematic resolution.
2021
WOS:000686033500049
journalArticle
16
PLOS ONE
DOI 10.1371/journal.pone.0256694
9
Emran
Shah-Al
Krupnik
Timothy J.
Aravindakshan
Sreejith
Kumar
Virender
Pittelkow
Cameron M.
Factors contributing to farm-level productivity and household income generation in coastal Bangladesh's rice-based farming systems
Large changes have taken place in smallholder farming systems in South Asia's coastal areas in recent decades, particularly related to cropping intensity, input availability, climate risks, and off-farm activities. However, few studies have investigated the extent to which these changes have impacted farm-level crop productivity, which is a key driver of food security and poverty in rainfed, low-input, rice-based systems. The objective of this study was to conduct an integrated assessment of variables related to socioeconomic status, farm characteristics, and crop management practices to understand the major factors influencing crop productivity and identify promising leverage points for sustainable development in coastal Bangladesh. Using a panel survey dataset of 32 variables from 502 farm households located within polder (coastal embankment) and outside polder systems during 2005-2015, we employed statistical factor analysis to characterize five independent latent factors named here as Farming Challenges, Economic Status, Crop Management Practices, Asset Endowment, and Farm Characteristics. The factor Farming Challenges explained the most variation among households (31%), with decreases observed over time, specifically households located outside polders. Individual variables contributing to this factor included perceived cyclone severity, household distance to main roads and input-output markets, cropping intensity, and access to extension services. The most important factors for increasing crop productivity on a household and per unit area basis were Asset Endowment and Crop Management Practices, respectively. The former highlights the need for increasing gross cropped area, which can be achieved through greater cropping intensity, while the latter was associated with increased fertilizer, labor, and pesticide input use. Despite the importance of these factors, household poverty trajectory maps showed that changes in off-farm income had played the strongest role in improving livelihoods in this coastal area. This study can help inform development efforts and policies for boosting farm-level crop productivity, specifically through agricultural intensification (higher cropping intensity combined with appropriate and efficient use of inputs) and expanding opportunities for off-farm income as key pathways to bring smallholder households out of poverty.
2021
WOS:000729120700025
journalArticle
82
Brazilian journal of biology = Revista brasleira de biologia
DOI 10.1590/1519-6984.242635
Ehtisham
Akhtar
A
Khan
K A
Iqbal
M
Bano
S A
Hussain
M
Munawar
N
Habiba
U
Identification and crop damage assessment of indian crested porcupine (Hystrix indica) in selected zones of Abbottabad, Pakistan.
Indian crested porcupine is the largest rodent pest that damages a wide variety of crops, vegetables, and tree species which ultimately causes huge economic loss in Pakistan, which is an agricultural country. It prefers to live in hilly terrain but common in temperate and tropical forests, shrublands, and grasslands. This study focused on the identification and assessment of crops damaged along with the main precautionary measures used by the local farmers. The data was collected from twenty-four villages of two union councils i.e. Chamhad and Slahad of district Abbottabad. Two types of data (primary and secondary) were collected from the study area. Primary data was collected for identification and estimation calculation of total crop damaged through direct field observation by taking random quadrates in each village of the study area. The damage in the crop was assessed by randomly selecting a quadrate of 1x1 m2 for the wheat, pearl millet, and Sorghum fields. While 4x4 m2 quadrates were taken for maize and vegetables. At least three quadrate samples were taken from each field including one quadrate taken from the center of the field area. In union council Chamhad, damage to maize (11.31%) and wheat (0.73%) by the Indian crested porcupine while in union council Salhad, damage of maize (6.95%) and wheat (1.6%) was observed. In the entire study area, overall damage to maize crop (8.01%) and wheat (0.88%) was calculated. Based on information obtained from the farmers, the Indian porcupine inflicted damage to potato, tomato, cauliflower, chili pepper, turnip, radish, pea, and onion, etc. Secondary data obtained through a questionnaire survey to explore the human porcupine conflict and precautionary measures used by the farmers and landowners. Open and close-ended questionnaires (159) highlighted the presence of Indian crested porcupine in the study area and 96% of the respondents have seen porcupine directly. Many types of precautionary measures were used by the farmers such as fencing, night stay, night firing, and dogs to decrease the crop damage, respondents (63.91%) use guns for hunting. however, due to the largely agricultural area and nocturnal behavior of Indian crested porcupine majority of the respondents (51.57%) did not use any precautionary measure. Biological control of Indian porcupine is recommended in the study area. Farmers should be encouraged and provide incentives and killing through current should be banned while proper hunting license should be issued to overcome overhunting. Scientific studies are required to control the reproduction of porcupine specifically in the more damaged areas.
2021
MEDLINE:34190803
e242635-e242635
journalArticle
16
PLOS ONE
DOI 10.1371/journal.pone.0253939
7
Bajracharya
Sugat B.
Mishra
Arabinda
Maharjan
Amina
Determinants of crop residue burning practice in the Terai region of Nepal
The open burning of agricultural crop residue is a key environmental issue facing the Hindu Kush Himalaya region, the Indo-Gangetic plain in particular. There is a varying intensity in the incidence of open agricultural burning in this region, and multiple drivers that determine why farmers in this region decide to burn their crop residues. While there have been research studies conducted for other countries in the region, research into the determinants of crop-burning in the Nepalese context is missing. Using primary data from a survey of 388 farming households across three districts of the Nepal Terai-Nawalparasi, Rupandehi and Kapilvastu-applying a recursive bivariate probit model, this study seeks to find out what drives the Nepalese farmers to burn their crop residue instead of using them in a sustainable manner and suggest policy recommendations for mitigation. Our findings show that the major determining factors that influence the farmers' behavior in Nepal are livestock ownership, combine harvester use and awareness level of the farmers. While the effects of crop residue burning is transboundary in nature, the mitigation measures require to be region specific. Based on the findings, the study proposes raising livestock, using technology like Happy Seeders or upgrade the combine harvesters, raising awareness and changing perception of farmers, and promoting alternative uses of crop residue as viable mitigation measures.
2021
WOS:000668791400064
journalArticle
281
JOURNAL OF ENVIRONMENTAL MANAGEMENT
DOI 10.1016/j.jenvman.2020.111836
Baudoin
Lucie
Gittins
Joshua R.
The ecological outcomes of collaborative governance in large river basins: Who is in the room and does it matter?
Although collaborative governance has been presented as central in environmental management, it does not guarantee sustainable natural resources management. Due to methodological challenges and a lack of robust interdisciplinary data, few studies have linked collaborative processes to ecological outcomes. This paper contributes to that research effort by investigating whether the relative involvement of different interest groups in deliberations matters from an ecological perspective. To that end, this interdisciplinary paper links social and ecological indicators across two large French river basins in a dataset spanning 25 years. We find that the presence of different interest groups - agricultural, industrial and NGOs - during deliberations, is linked to different ecological outcomes. Most notably, the composition of present members does not play the same role depending on the type of pollution source studied (e.g. point and/or diffuse sources).
2021 MAR 1
WOS:000618047900006
journalArticle
282
JOURNAL OF ENVIRONMENTAL MANAGEMENT
DOI 10.1016/j.jenvman.2021.111965
Cerda
Artemi
Daliakopoulos
Ioannis N.
Terol
Enric
Novara
Agata
Fatahi
Yalda
Moradi
Ehsan
Salvati
Luca
Pulido
Manuel
Long-term monitoring of soil bulk density and erosion rates in two Prunus Persica (L) plantations under flood irrigation and glyphosate herbicide treatment in La Ribera district, Spain
Early season fruit production for the northern European market is highly intensive in fertilization, machinery, irrigation and the use of herbicides. Those conditions increase the soil losses and soil compaction and threaten the Sustainable Goals for Development of the United Nations by 2030. Long-term soil erosion measurements are necessary to determine the sustainability of agriculture managements. Moreover, soil erosion on flood irrigation land is a topic that request more surveys and research as rainfed sloping terrains attracted all the attention of scientists and research investment. Improved Stock Unearthing Method (ISUM) was applied to two 15 years-old herbicide treated fields of Saturn peaches (Prunus persica var. platycarpa) to determine long-term soil erosion rates (2004-2019). Using ISUM, a 1 mm thick nylon rope (700 mm length) was used to connect trees perpendicular to the direction of rows at the height of the graft. To detection soil lowering, the vertical distance of the rope to the soil surface was measured at 10 cm intervals along the rope. The ring method (264 samples at 0-6 cm) was used to determine the soil bulk density, which was in average 1.15 gr cm(-3) for both plots. There was found a compaction in the centre of both plots due to the pass of machinery with mean bulk density values of 1.23 gr cm(-3), meanwhile underneath of the trees, the soil bulk density was 1.05 gr cm(-3). The topography survey carried out with ISUM (2508 sampling points) informed that flood irrigation redistributed the soil from the upper to the lower field position, where a sedimentation layer was measured. We found that the two studied fields showed a contrasted response, with low soil erosion values in Benimodo and high in L'Alcudia study sites. Soil erosion rates were in average 1.46 Mg ha(1) yr(1) and 8.02 Mg ha(1) yr(1) for Benimodo and L'Alcudia, respectively. However, the maps development using ISUM allow to inform that the pattern of soil redistribution is similar for both fields as the highest soil lowering was found in the upper field part, where the flood discharge detach soil particles. In the lower field position sedimentation takes place. The dataset allows us to conclude that soil erosion in Saturn peaches fields is non-sustainable and more soil conservation management should be applied to reduce the soil erosion rates due to the bare soils as a consequence of the use of herbicides. This research informs that soil erosion in flood irrigated fields is a relevant process that needs more investigations around the world, where 94% of the irrigated land is under flood or furrow irrigation, and where irrigation is growing year after year.
2021 MAR 15
WOS:000616181900002
journalArticle
21
BMC PLANT BIOLOGY
DOI 10.1186/s12870-020-02817-2
1
Wang
Yu
Zhang
Wenze
Liu
Weikang
Ahammed
Golam Jalal
Wen
Wenxu
Guo
Shirong
Shu
Sheng
Sun
Jin
Auxin is involved in arbuscular mycorrhizal fungi-promoted tomato growth and NADP-malic enzymes expression in continuous cropping substrates
BackgroundDespite significant limitations of growth medium reuse, a large amount of organic substrate is reused in soilless cultivation of horticultural crops in China. Arbuscular mycorrhizal fungi (AMF) can promote nutrient absorption and improve plant tolerance to biotic and abiotic stresses. However, the mechanisms governing the effects of AMF on crop growth in organic continuous cropping substrates have not been elucidated.ResultsIn this study, we showed that the inoculation of AMF in continuous cropping substrates promoted growth and root development, and increased the root and NADP-malic enzyme (NADP-ME) activity of tomato seedlings. Root transcriptome analysis demonstrated that the plant hormone signal transduction pathway was highly enriched, and 109 genes that positively correlated with the AMF-inoculated plant phenotype were obtained by gene set enrichment analysis (GSEA), which identified 9 genes related to indole acetic acid (IAA). Importantly, the levels of endogenous IAA in tomato seedlings significantly increased after AMF inoculation. Furthermore, the application of AMF significantly increased the expression levels of NADP-ME1 and NADP-ME2, as well as the activity of NADP-ME, and enhanced the root activity of tomato seedlings in comparison to that observed without inoculation of AMF. However, these effects were blocked in plants treated with 2,3,5-triiodobenzoic acid (TIBA), a polar transport inhibitor of IAA.ConclusionsThese results suggest that IAA mediates the AMF-promoted tomato growth and expression of NADP-MEs in continuous cropping substrates. The study provides convincing evidence for the reuse of continuous cropping substrates by adding AMF as an amendment.
2021 JAN 18
WOS:000611913400003
journalArticle
16
PLOS ONE
DOI 10.1371/journal.pone.0245426
1
Olagunju
Kehinde Oluseyi
Ogunniyi
Adebayo Isaiah
Oyetunde-Usman
Zainab
Omotayo
Abiodun Olusola
Awotide
Bola Amoke
Does agricultural cooperative membership impact technical efficiency of maize production in Nigeria: An analysis correcting for biases from observed and unobserved attributes
The formation of agricultural cooperatives has been widely promoted as an agricultural development policy initiative to help smallholder farmers cope with multiple production and marketing challenges. Using a nationally representative survey dataset of smallholder maize producers from rural Nigeria, this study assesses the impact of agricultural cooperative membership on technical efficiency (TE). We based our estimation approach on the combination of a newly developed sample selection stochastic production frontier model with propensity score matching to control for possible selectivity biases from both observables and unobservables. We estimate stochastic meta-frontiers to examine TE differences between cooperative members and non-members. Our results reveal that TE levels of members are consistently higher than that of non-members. This calls for continued policy incentives targeted at encouraging farmers to form as well as participate in agricultural cooperatives.
2021 JAN 22
WOS:000612929300106
journalArticle
8
SCIENTIFIC DATA
DOI 10.1038/s41597-021-00817-x
1
Su
Yang
Gabrielle
Benoit
Makowski
David
A global dataset for crop production under conventional tillage and no tillage systems
No tillage (NT) is often presented as a means to grow crops with positive environmental externalities, such as enhanced carbon sequestration, improved soil quality, reduced soil erosion, and increased biodiversity. However, whether NT systems are as productive as those relying on conventional tillage (CT) is a controversial issue, fraught by a high variability over time and space. Here, we expand existing datasets to include the results of the most recent field experiments, and we produce a global dataset comparing the crop yields obtained under CT and NT systems. In addition to crop yield, our dataset also reports information on crop growing season, management practices, soil characteristics and key climate parameters throughout the experimental year. The final dataset contains 4403 paired yield observations between 1980 and 2017 for eight major staple crops in 50 countries. This dataset can help to gain insight into the main drivers explaining the variability of the productivity of NT and the consequence of its adoption on crop yields.
2021 JAN 28
WOS:000616393100001
journalArticle
28
ENVIRONMENTAL SCIENCE AND POLLUTION RESEARCH
DOI 10.1007/s11356-021-12522-8
21
Azareh
Ali
Sardooi
Elham Rafiei
Gholami
Hamid
Mosavi
Amirhosein
Shahdadi
Ali
Barkhori
Saeed
Detection and prediction of lake degradation using landscape metrics and remote sensing dataset
Monitoring changes in natural ecosystems is considered essential to natural resource management. Despite the global importance of the lakes' quality monitoring, there is currently a research gap in the simultaneous predictive modeling of lakes' land-use changes and ecosystem measurements. In the present study for projecting the water bodies of lakes and their surrounding ecosystems, the land-use changes and the landscape analysis of different periods, i.e., 1987, 2002, 2018, and 2030, are studied using remote sensing data and various metrics. The trend of land-use and landscape changes is projected for 2030. The results indicate significant degradation of rangelands and forests due to the conversion to agriculture and construction and the declining trend of lakes' water body and their transformation to salt lake and salt lands. The increase of agricultural lands and the overuse of groundwater wells upstream of the lakes could be one of the reasons for this decline. Decreasing the lakes' water body and subsequently increasing salt lands are considered a severe threat to human health and the ecosystem services of the lakes. Besides, the dust generated by salt lands could also decrease crop yield in the study area.
2021 JUN
WOS:000612599600018
27283-27298
journalArticle
20
NUTRITION JOURNAL
DOI 10.1186/s12937-021-00664-x
1
Radcliffe
Josalyn
Skinner
Kelly
Spring
Andrew
Picard
Lise
Benoit
France
Dodd
Warren
Virtual barriers: unpacking the sustainability implications of online food spaces and the Yellowknife Farmers Market's response to COVID-19
BackgroundThrough their support of local agriculture, relationships, and healthy diets, farmers markets can contribute to a sustainable food system. Markets like the Yellowknife Farmers Market (YKFM) are social spaces that support local food, yet the COVID-19 pandemic has forced changes to their current model. We explore the potential of online marketplaces to contribute to a resilient, sustainable food system through a case study of the YKFM.MethodsIn 2019, a collaborative mixed-method evaluation was initiated by the YKFM and university partners in the Northwest Territories (NWT), Canada. The evaluation included an in-person Rapid Market Assessment dot survey and questionnaire of market patrons from two YKFM dates prior to the pandemic. Due to COVID-19, a vendor survey and interviews were deferred. Data collected from the two patron surveys, alongside researcher observations, available literature, public announcements, and informal email and phone discussions, inform the discussion.ResultsFor the patron surveys, 59 dot survey and 31 questionnaire participants were recruited. The top motivators for attendance were eating dinner, atmosphere, and supporting local businesses, and most patrons attended as couples and spent over half of their time talking to others. The YKFM did not move online; instead, they proposed and implemented a "Shop, don't stop" market. Informal conversations suggested the small scale of the market and technology challenges were perceived barriers to moving online. The physically-distanced market was well-attended and featured in local media.ConclusionsNWT food strategies rely on farmers markets to nurture a local food system. Data suggest a potential incongruence between an online model and important market characteristics such as the event-like atmosphere. Available literature suggests online markets can support local food by facilitating purchasing and knowledge-sharing, yet they do not replicate the open-air or social experience. The decision not to move online for the YKFM reflects market patron characteristics and current food context in Yellowknife and the NWT. While online adaptation does not fit into the YKFM plan today, online markets may prove useful as a complementary strategy for future emerging stressors to enhance the resiliency of local systems.
2021 JAN 29
WOS:000616479500002
journalArticle
195
ENVIRONMENTAL RESEARCH
DOI 10.1016/j.envres.2021.110786
Fenta
Ayele Almaw
Tsunekawa
Atsushi
Haregeweyn
Nigussie
Tsubo
Mitsuru
Yasuda
Hiroshi
Kawai
Takayuki
Ebabu
Kindiye
Berihun
Mulatu Liyew
Belay
Ashebir Sewale
Sultan
Dagnenet
Agroecology-based soil erosion assessment for better conservation planning in Ethiopian river basins
Soil erosion by water is one of the main environmental concerns in Ethiopia. Several studies have examined this at plot and watershed scales, but no systematic study of soil erosion severity and management solutions at national scale is available. This study investigated soil erosion and the potential of land-cover- and agroecology-specific land management practices in reducing soil loss through employing the Revised Universal Soil Loss Equation and the best available datasets. The mean rate of soil loss by water erosion in Ethiopia was estimated as 16.5 t ha(-1) yr(-1), with an annual gross soil loss of ca. 1.9 x 10(9) t, of which the net soil loss was estimated as ca. 410 x 10(6) t (22% of the gross soil loss). Soil loss varied across land cover types, 15 agroecological zones, and 10 river basins, with the main contributors in the respective analyses being cropland (ca. 23% of Ethiopia; 50% of the soil loss; mean soil loss rate of 36.5 t ha(-1) yr(-1)), Moist Weyna Dega (ca. 10%; 20%; 33.3 t ha(-1) yr(-1)), and the Abay basin (ca. 15%; 30%; 32.8 t ha(-1) yr(-1)). Our results show that ca. 25% of Ethiopia (28 x 10(6) ha) has soil loss rates above 10 t ha(-1) yr(-1), which is higher than the tolerable soil loss limits estimated for Ethiopia. Ex-ante analysis revealed that implementation of land-cover- and agroecology-specific land management practices (level bunds, graded bunds, trenches, and exclosures combined with trenches and/or bunds) in such areas could reduce the mean soil loss rate from 16.5 t ha(-1) yr(-1) to 5.3 t ha(-1) yr(-1) (mean, by ca. 68%; range, 65-70%). Suitable land management practices in the Abay and Tekeze basins and Dega and Weyna Dega agroecologies, which experience particularly severe erosion, would account for ca. 50 and 70% of the estimated soil loss reduction, respectively. This study can help raise awareness among policy makers and land managers of the extent and severity of soil loss by water erosion for better conservation planning in river basins to support sustainable use of land and water resources.
2021 APR
WOS:000639328800072
journalArticle
18
INTERNATIONAL JOURNAL OF ENVIRONMENTAL RESEARCH AND PUBLIC HEALTH
DOI 10.3390/ijerph18031326
3
Guo
Aijun
Zhang
Rong
Song
Xiaoyu
Zhong
Fanglei
Jiang
Daiwei
Song
Yuan
Predicting the Water Rebound Effect in China under the Shared Socioeconomic Pathways
The rebound effect exists widely in the fields of energy, irrigation, and other resource utilizations. Previous studies have predicted the evolution of different resource utilizations under the shared socioeconomic pathways (SSPs), but it is still unclear whether total water use has a rebound effect. This study uses the SSPs as the basic prediction framework and evaluates the water resources and economic status of the provinces in China using the hydro-economic (HE) classification method. Then, combined with the SSPs scenario setting parameters, the conditional convergence model and the method recommended by the Food and Agriculture Organization of the United Nations (FAO) are used to simulate the changes in water use efficiency of the different provinces in China under different scenarios. Based on the future GDP forecast data of China's provinces, combined with the forecast of water use efficiency changes, the total water use changes in China's 31 provinces under different pathways from 2016 to 2030 are calculated. Among them, the future GDP data is predicted based on the Cobb-Douglas production function and SSPs scenario settings. Using a comprehensive evaluation of the evolution of the efficiency and the total amount, this study reveals whether there is a rebound effect. The results showed that with the continuous growth in the water use efficiency, the total water use had a "U" type trend, which indicated that there was a rebound effect in the total water use of China under the different SSPs. Based on this information, this study proposes some suggestions for irrigation water-saving technologies and policies.
2021 FEB
WOS:000615180000001
journalArticle
18
INTERNATIONAL JOURNAL OF ENVIRONMENTAL RESEARCH AND PUBLIC HEALTH
DOI 10.3390/ijerph18041637
4
Fisher
Jared A.
Spaur
Maya
Buller
Ian D.
Flory
Abigail R.
Beane Freeman
Laura E.
Hofmann
Jonathan N.
Giangrande
Michael
Jones
Rena R.
Ward
Mary H.
Spatial Heterogeneity in Positional Errors: A Comparison of Two Residential Geocoding Efforts in the Agricultural Health Study
Geocoding is a powerful tool for environmental exposure assessments that rely on spatial databases. Geocoding processes, locators, and reference datasets have improved over time; however, improvements have not been well-characterized. Enrollment addresses for the Agricultural Health Study, a cohort of pesticide applicators and their spouses in Iowa (IA) and North Carolina (NC), were geocoded in 2012-2016 and then again in 2019. We calculated distances between geocodes in the two periods. For a subset, we computed positional errors using "gold standard" rooftop coordinates (IA; N = 3566) or Global Positioning Systems (GPS) (IA and NC; N = 1258) and compared errors between periods. We used linear regression to model the change in positional error between time periods (improvement) by rural status and population density, and we used spatial relative risk functions to identify areas with significant improvement. Median improvement between time periods in IA was 41 m (interquartile range, IQR: -2 to 168) and 9 m (IQR: -80 to 133) based on rooftop coordinates and GPS, respectively. Median improvement in NC was 42 m (IQR: -1 to 109 m) based on GPS. Positional error was greater in rural and low-density areas compared to in towns and more densely populated areas. Areas of significant improvement in accuracy were identified and mapped across both states. Our findings underscore the importance of evaluating determinants and spatial distributions of errors in geocodes used in environmental epidemiology studies.
2021 FEB
WOS:000623562800001
journalArticle
284
JOURNAL OF ENVIRONMENTAL MANAGEMENT
DOI 10.1016/j.jenvman.2021.112010
Pacheco
Rayane
Raja
Raoni
Van der Hoff
Richard
Soares-Filho
Britaldo
Will farmers seek environmental regularization in the Amazon and how? Insights from the Rural Environmental Registry (CAR) questionnaires
The future availability and quality of natural resources essential to life such as ecosystem services and biodiversity depend on the conservation and restoration of native vegetation. The Brazilian Native Vegetation Protection Law (NVPL) requires farmers to conserve a minimum percentage of native vegetation within their properties as Legal Reserves (LR) as well as riparian forests and hilltops as Permanent Preservation Areas (PPAs). To monitor the conservation and facilitate the compliance of these areas, the Rural Environmental Registry (CAR) and the Environmental Regularization Program (PRA) were created. However, so far, little is known about farmers' interest in joining the PRA and the actions they intend to take to correct their past illegal deforestation. This article explores a unique dataset comprising of the individual answers of 97 thousand farmers in the states of Par ' a and Mato Grosso given to the Brazilian Forest Service in the process of joining at the national rural environmental registry system. We found that the adherence to the PRA is positively correlated with recognition of the LR deficit and the size of the rural property. Also medium and large landowners and crop producers tend to seek compliance by taking actions outside the farm (compensation), while small farmers and squatters are more likely to act inside their own areas (restoration). Understanding farmers' interests and options for LR compliance can contribute for the formulation of more effective implementation strategies for PRA and NVPL.
2021 APR 15
WOS:000621649200001
journalArticle
284
JOURNAL OF ENVIRONMENTAL MANAGEMENT
DOI 10.1016/j.jenvman.2021.112018
Bhattarai
Babu Ram
Morgan
Damian
Wright
Wendy
Equitable sharing of benefits from tiger conservation: Beneficiaries' willingness to pay to offset the costs of tiger conservation
Costs of large predator conservation may not be equitably distributed among stakeholders; these include farming communities, tourism business owners and visitors. Financial redistribution mechanisms based on accrued benefits and costs of conservation require relevant data unavailable in many locations. To address this, a contingent valuation method identified willingness to pay (WTP) among national park visitors and connected tourism business owners. Both groups derive benefit from government-funded conservation policies. The study was conducted in Bardia and Chitwan National Parks, Nepal 2017-2018; two locations world-renowned for tiger conservation. Local and international park visitors (N = 387) provided WTP for ongoing conservation via additional park entry fees. Tourism business owners (TBOs; N = 74) proximate to the parks stated their WTP for compensation funding provided directly to farmers. The majority (65%) of park visitors were willing to pay extra to support conservation (sample mean US$ 20) while 85 percent of TBOs supported their payment of funds for compensating farming communities (sample mean annual contribution being US$ 156). Valid WTP regression modelling found that visitor WTP was predicted by international travel costsand environmental organization affiliation. For TBOs indicating WTP, the amount to pay was predicted by annual net income from the tourism business. Application of study data indicates US$ 25 average increase to visitor park fees would maximise revenue and contribute a further US$ 495,000 available for conservation activities. Similarly, a flat-rate tariff on TBOs at the mean WTP amount would contribute more than double the annual budget available for farmer compensation (providing approximately US$ 43,000). More generally, the study findings are informative for policy-makers seeking equitable conservation outcomes while maintaining viable populations of critically endangered wild tigers. They should however be interpreted with caution given limitations of the sampling frame and method of data elicitation. Regardless, any policy decision effects require careful scrutiny to ensure desired outcomes are realized.
2021 APR 15
WOS:000621652400002
journalArticle
272
CHEMOSPHERE
DOI 10.1016/j.chemosphere.2021.129803
Pan
Zheng
Yang
Side
Zhao
Lixia
Li
Xiaojing
Weng
Liping
Sun
Yang
Li
Yongtao
Temporal and spatial variability of antibiotics in agricultural soils from Huang-Huai-Hai Plain, northern China
The objective of this study was to investigate the temporal and spatial distribution of antibiotics in agricultural soils of Huang-Huai-Hai Plain, which is a major agricultural producing area and economically developed region in China. In this study, 105 soil samples including 13 groups of soil profile samples (0-20, 20-40 and 40-60 cm) and 23 paired surface soil samples of greenhouse and open-field were collected from four provinces/municipality in 2018. The occurrence of 20 antibiotics, including four tetracyclines (TCs), seven quinolones (QNs), six sulfonamides (SAs) and three macrolides (MLs) were measured. The concentrations of total antibiotics fell in the range of 1.62-575 mu g kg(-1), with the mean value of 68.8 mu g kg(-1). TCs and QNs were dominant antibiotics in soil, accounting for 99.6% of the total concentration. Regional differences of antibiotic residues in soil were found among the four regions as well as between different cropping systems. The levels of antibiotics in greenhouse soils (3.52-575 mu g kg(-1)) were higher than those in open-field soils (1.62-142 mu g kg(-1)). In soils of greenhouse of 1-6 years old, the levels of antibiotics were higher than those with longer history (7-30 years). Antibiotics were mainly distributed in the depth of 0-20 cm. The total concentrations of antibiotics/QNs followed the order of 0-20 cm > 40-60 cm > 20-40 cm, due to probably their interactions with total organic carbon and associated bacterial communities. The results in the study will provide data supports for the formulation of soil antibiotic contamination prevention and control measures. (C) 2021 Elsevier Ltd. All rights reserved.
2021 JUN
WOS:000635594700125
journalArticle
21
SENSORS
DOI 10.3390/s21051601
5
Wang
Rujing
Liu
Liu
Xie
Chengjun
Yang
Po
Li
Rui
Zhou
Man
AgriPest: A Large-Scale Domain-Specific Benchmark Dataset for Practical Agricultural Pest Detection in the Wild
The recent explosion of large volume of standard dataset of annotated images has offered promising opportunities for deep learning techniques in effective and efficient object detection applications. However, due to a huge difference of quality between these standardized dataset and practical raw data, it is still a critical problem on how to maximize utilization of deep learning techniques in practical agriculture applications. Here, we introduce a domain-specific benchmark dataset, called AgriPest, in tiny wild pest recognition and detection, providing the researchers and communities with a standard large-scale dataset of practically wild pest images and annotations, as well as evaluation procedures. During the past seven years, AgriPest captures 49.7K images of four crops containing 14 species of pests by our designed image collection equipment in the field environment. All of the images are manually annotated by agricultural experts with up to 264.7K bounding boxes of locating pests. This paper also offers a detailed analysis of AgriPest where the validation set is split into four types of scenes that are common in practical pest monitoring applications. We explore and evaluate the performance of state-of-the-art deep learning techniques over AgriPest. We believe that the scale, accuracy, and diversity of AgriPest can offer great opportunities to researchers in computer vision as well as pest monitoring applications.
2021 MAR
WOS:000628584700001
journalArticle
21
SENSORS
DOI 10.3390/s21051617
5
Safonova
Anastasiia
Guirado
Emilio
Maglinets
Yuriy
Alcaraz-Segura
Domingo
Tabik
Siham
Olive Tree Biovolume from UAV Multi-Resolution Image Segmentation with Mask R-CNN
Olive tree growing is an important economic activity in many countries, mostly in the Mediterranean Basin, Argentina, Chile, Australia, and California. Although recent intensification techniques organize olive groves in hedgerows, most olive groves are rainfed and the trees are scattered (as in Spain and Italy, which account for 50% of the world's olive oil production). Accurate measurement of trees biovolume is a first step to monitor their performance in olive production and health. In this work, we use one of the most accurate deep learning instance segmentation methods (Mask R-CNN) and unmanned aerial vehicles (UAV) images for olive tree crown and shadow segmentation (OTCS) to further estimate the biovolume of individual trees. We evaluated our approach on images with different spectral bands (red, green, blue, and near infrared) and vegetation indices (normalized difference vegetation index-NDVI-and green normalized difference vegetation index-GNDVI). The performance of red-green-blue (RGB) images were assessed at two spatial resolutions 3 cm/pixel and 13 cm/pixel, while NDVI and GNDV images were only at 13 cm/pixel. All trained Mask R-CNN-based models showed high performance in the tree crown segmentation, particularly when using the fusion of all dataset in GNDVI and NDVI (F1-measure from 95% to 98%). The comparison in a subset of trees of our estimated biovolume with ground truth measurements showed an average accuracy of 82%. Our results support the use of NDVI and GNDVI spectral indices for the accurate estimation of the biovolume of scattered trees, such as olive trees, in UAV images.
2021 MAR
WOS:000628536600001
journalArticle
286
JOURNAL OF ENVIRONMENTAL MANAGEMENT
DOI 10.1016/j.jenvman.2021.112191
Abera
Wuletawu
Tamene
Lulseged
Abegaz
Assefa
Hailu
Habtamu
Piikki
Kristin
Soderstrom
Mats
Girvetz
Evan
Sommer
Rolf
Estimating spatially distributed SOC sequestration potentials of sustainable land management practices in Ethiopia
The sustainable land management program (SLMP) of Ethiopia aims to improve livelihoods and create resilient communities and landscape to climate change. Soil organic carbon (SOC) sequestration is one of the key cobenefits of the SLMP. The objective of this study was to estimate the spatial dynamics of SOC in 2010 and 2018 (before and after SLMP) and identify the SOC sequestration hotspots at landscape scale in four selected SLMP watersheds in the Ethiopian highlands. The specific objectives were to: 1) comparatively evaluate SOC sequestration estimation model building strategies using either a single watershed, a combined dataset from all watersheds, and leave-one-watershed-out using Random Forest (RF) model; 2) map SOC stock of 2010 and 2018 to estimate amount of SOC sequestration and potential; 3) evaluate the impacts of SLM practices on SOC in four SLMP watersheds. A total of 397 auger composite samples from the topsoil (0?20 cm depth) were collected in 2010, and the same number of samples were collected from the same locations in 2018. We used simple statistics to assess the SOC change between the two periods, and machine learning models to predict SOC stock spatially. The study showed that statistically significant variation (P < 0.05) of SOC was observed between the two years in two watersheds (Gafera and Adi Tsegora) whereas the differences were not significant in the other two watersheds (Yesir and Azugashuba). Comparative analysis of model-setups shows that a combined dataset from all the four watersheds to train and test RF outperform the other two strategies (a single watershed alone and a leaveone-watershed-out to train and test RF) during the testing dataset. Thus, this approach was used to predict SOC stock before (2010) and after (2018) land management interventions and to derive the SOC sequestration maps. We estimated the sequestrated, achievable and target level of SOC stock spatially in the four watersheds. We assessed the impact of SLM practices, specifically bunds, terraces, biological and various forms of tillage practices on SOC using partial dependency algorithms of prediction models. No tillage (NT) increased SOC in all watersheds. The combination of physical and biological interventions (?bunds + vegetations? or ?terraces + vegetations?) resulted in the highest SOC stock, followed by the biological intervention. The achievable SOC stock analysis showed that further SOC stock sequestration of up to 13.7 Mg C ha?1 may be possible in the Adi Tsegora, 15.8 Mg C ha-1 in Gafera, 33.2 Mg C ha-1 in Azuga suba and 34.7 Mg C ha-1 in Yesir watersheds.
2021 MAY 15
WOS:000634991000005
journalArticle
48
FUNCTIONAL PLANT BIOLOGY
DOI 10.1071/FP20309
8
Hu
Pengcheng
Chapman
Scott C.
Zheng
Bangyou
Coupling of machine learning methods to improve estimation of ground coverage from unmanned aerial vehicle (UAV) imagery for high-throughput phenotyping of crops
Ground coverage (GC) allows monitoring of crop growth and development and is normally estimated as the ratio of vegetation to the total pixels from nadir images captured by visible-spectrum (RGB) cameras. The accuracy of estimated GC can be significantly impacted by the effect of 'mixed pixels', which is related to the spatial resolution of the imagery as determined by flight altitude, camera resolution and crop characteristics (fine vs coarse textures). In this study, a two-step machine learning method was developed to improve the accuracy of GC of wheat (Triticum aestivum L.) estimated from coarse-resolution RGB images captured by an unmanned aerial vehicle (UAV) at higher altitudes. The classification tree-based per-pixel segmentation (PPS) method was first used to segment fine-resolution reference images into vegetation and background pixels. The reference and their segmented images were degraded to the target coarse spatial resolution. These degraded images were then used to generate a training dataset for a regression tree-based model to establish the sub-pixel classification (SPC) method. The newly proposed method (i.e. PPS-SPC) was evaluated with six synthetic and four real UAV image sets (SISs and RISs, respectively) with different spatial resolutions. Overall, the results demonstrated that the PPS-SPC method obtained higher accuracy of GC in both SISs and RISs comparing to PPS method, with root mean squared errors (RMSE) of less than 6% and relative RMSE (RRMSE) of less than 11% for SISs, and RMSE of less than 5% and RRMSE of less than 35% for RISs. The proposed PPS-SPC method can be potentially applied in plant breeding and precision agriculture to balance accuracy requirement and UAV flight height in the limited battery life and operation time.
2021
WOS:000625358800001
766-779
journalArticle
67
ENVIRONMENTAL MANAGEMENT
DOI 10.1007/s00267-021-01450-5
6
Maloney
Kelly Oliver
Carlisle
Daren Milo
Buchanan
Claire
Rapp
Jennifer Lynn
Austin
Samuel Hess
Cashman
Matthew Joseph
Young
John Andre
Linking Altered Flow Regimes to Biological Condition: an Example Using Benthic Macroinvertebrates in Small Streams of the Chesapeake Bay Watershed
Regionally scaled assessments of hydrologic alteration for small streams and its effects on freshwater taxa are often inhibited by a low number of stream gages. To overcome this limitation, we paired modeled estimates of hydrologic alteration to a benthic macroinvertebrate index of biotic integrity data for 4522 stream reaches across the Chesapeake Bay watershed. Using separate random-forest models, we predicted flow status (inflated, diminished, or indeterminant) for 12 published hydrologic metrics (HMs) that characterize the main components of flow regimes. We used these models to predict each HM status for each stream reach in the watershed, and linked predictions to macroinvertebrate condition samples collected from streams with drainage areas less than 200 km(2). Flow alteration was calculated as the number of HMs with inflated or diminished status and ranged from 0 (no HM inflated or diminished) to 12 (all 12 HMs inflated or diminished). When focused solely on the stream condition and flow-alteration relationship, degraded macroinvertebrate condition was, depending on the number of HMs used, 3.8-4.7 times more likely in a flow-altered site; this likelihood was over twofold higher in the urban-focused dataset (8.7-10.8), and was never significant in the agriculture-focused dataset. Logistic regression analysis using the entire dataset showed for every unit increase in flow-alteration intensity, the odds of a degraded condition increased 3.7%. Our results provide an indication of whether altered streamflow is a possible driver of degraded biological conditions, information that could help managers prioritize management actions and lead to more effective restoration efforts.
2021 JUN
WOS:000628066000001
1171-1185
journalArticle
118
PROCEEDINGS OF THE NATIONAL ACADEMY OF SCIENCES OF THE UNITED STATES OF AMERICA
DOI 10.1073/pnas.2026132118
13
Larena
Maximilian
Sanchez-Quinto
Federico
Sjodin
Per
McKenna
James
Ebeo
Carlo
Reyes
Rebecca
Casel
Ophelia
Huang
Jin-Yuan
Hagada
Kim Pullupul
Guilay
Dennis
Reyes
Jennelyn
Allian
Fatima Pir
Mori
Virgilio
Azarcon
Lahaina Sue
Manera
Alma
Terando
Celito
Jamero
Lucio, Jr.
Sireg
Gauden
Manginsay-Tremedal
Renefe
Labos
Maria Shiela
Vilar
Richard Dian
Latiph
Acram
Saway
Rodelio Linsahay
Marte
Erwin
Magbanua
Pablito
Morales
Amor
Java
Ismael
Reveche
Rudy
Barrios
Becky
Burton
Erlinda
Salon
Jesus Christopher
Kels
Ma Junaliah Tuazon
Albano
Adrian
Cruz-Angeles
Rose Beatrix
Molanida
Edison
Granehall
Lena
Vicente
Mario
Edlund
Hanna
Loo
Jun-Hun
Trejaut
Jean
Ho
Simon Y. W.
Reid
Lawrence
Malmstrom
Helena
Schlebusch
Carina
Lambeck
Kurt
Endicott
Phillip
Jakobsson
Mattias
Multiple migrations to the Philippines during the last 50,000 years
Island Southeast Asia has recently produced several surprises regarding human history, but the region's complex demography remains poorly understood. Here, we report similar to 2.3 million genotypes from 1,028 individuals representing 115 indigenous Philippine populations and genome-sequence data from two similar to 8,000-y-old individuals from Liangdao in the Taiwan Strait. We show that the Philippine islands were populated by at least five waves of human migration: initially by Northern and Southern Negritos (distantly related to Australian and Papuan groups), followed by Manobo, Sama, Papuan, and Cordilleran-related populations. The ancestors of Cordillerans diverged from indigenous peoples of Taiwan at least similar to 8,000 y ago, prior to the arrival of paddy field rice agriculture in the Philippines similar to 2,500 y ago, where some of their descendants remain to be the least admixed East Asian groups carrying an ancestry shared by all Austronesian-speaking populations. These observations contradict an exclusive "out-of-Taiwan" model of farming-language-people dispersal within the last four millennia for the Philippines and Island Southeast Asia. Sama-related ethnic groups of southwestern Philippines additionally experienced some minimal South Asian gene flow starting similar to 1,000 y ago. Lastly, only a few lowlanders, accounting for <1% of all individuals, presented a low level of West Eurasian admixture, indicating a limited genetic legacy of Spanish colonization in the Philippines. Altogether, our findings reveal a multilayered history of the Philippines, which served as a crucial gateway for the movement of people that ultimately changed the genetic landscape of the Asia-Pacific region.
2021 MAR 30
WOS:000637394200079
journalArticle
37
MYCOTOXIN RESEARCH
DOI 10.1007/s12550-021-00429-9
2
Focker
M.
van der Fels-klerx
H. J.
Oude Lansink
A. G. J. M.
Financial losses for Dutch stakeholders during the 2013 aflatoxin incident in Maize in Europe
Early 2013, high concentrations of aflatoxin M-1 were found in the bulk milk of a few dairy farms in the Netherlands. These high concentrations were caused by aflatoxin B-1 contaminated maize from Eastern Europe that was processed into compound feed, which was fed to dairy cows. Since the contamination was discovered in the downstream stages of the supply chain, multiple countries and parties were involved and recalls of the feed were necessary, resulting into financial losses. The aim of this study was to estimate the direct short-term financial losses related to the 2013 aflatoxin incident for the maize traders, the feed industry, and the dairy sector in the Netherlands. First, the sequence of events of the incident was retrieved. Then, a Monte Carlo simulation model was built to combine the scarce and uncertain data to estimate the direct financial losses for each stakeholder. The estimated total direct financial losses of this incident were estimated to be between 12 and 25 million euros. The largest share, about 60%, of the total losses was endured by the maize traders. About 39% of the total losses were for the feed industry, and less than 1% of the total losses were for the dairy sector. The financial losses estimated in this study should be interpreted cautiously due to limitations associated with the quality of the data used. Furthermore, this incident led to indirect long-term financial effects, identified but not estimated in this study.
2021 MAY
WOS:000635068500002
193-204
journalArticle
782
SCIENCE OF THE TOTAL ENVIRONMENT
DOI 10.1016/j.scitotenv.2021.146696
Tesfaye
Kindie
Takele
Robel
Sapkota
Tek B.
Khatri-Chhetri
Arun
Solomon
Dawit
Stirling
Clare
Albanito
Fabrizio
Model comparison and quantification of nitrous oxide emission and mitigation potential from maize and wheat fields at a global scale
Maize and wheat are major cereals that contribute two-thirds of the food energy intake globally. The two crops consume about 35% of the nitrogen (N) fertilizer used in agriculture and thereby contribute to fertilizer-induced nitrous oxide (N2O) emissions. Thus, estimation of spatially disaggregated N2O emissions from maize and wheat fields on a global scale could be useful for identifying emission and mitigation hotspots. It could also be needed for prioritizing mitigation options consistent with location-specific production and environmental goals. N2O emission from four models (CCAFS-MOT, IPCC Tier-I, IPCC Tier-II and Tropical N2O) using a standard gridded dataset from global maize and wheat fields were compared and their performance evaluated using measured N2O emission data points (777 globally distributed datapoints). The models were used to quantify spatially disaggregated N2O emission and mitigation potential from maize and wheat fields globally and the values were compared. Although the models differed in their performance of capturing the level of measured N2O emissions, they produced similar spatial patterns of annual N2O emissions from maize and wheat fields. Irrespective of the models, predicted N2O emissions per hectare were higher in some countries in East and South Asia, North America, and Western Europe, driven mainly by higher N application rates. The study indicated a substantial N2O abatement potential if application of excess N in the maize and wheat systems is reduced without compromising the yield of the crops through technological and crop management innovations. N2O mitigation potential is higher in those countries and regions where N application rates and current N2O emissions are already high. The estimated mitigation potentials are useful for hotspot countries to target fertilizer and crop management as one of the mitigation options in their Nationally Determined Contributions (NDCs) to the United Nations Framework Convention on Climate Change (UNFCCC). (C) 2021 The Author(s). Published by Elsevier B.V.
2021 AUG 15
WOS:000655529300015
journalArticle
197
WATER RESEARCH
DOI 10.1016/j.watres.2021.117068
Butte
G.
Niwagaba
C.
Nordin
A.
Assessing the microbial risk of faecal sludge use in Ugandan agriculture by comparing field and theoretical model output
Reuse of faecal sludge in agriculture has many potential benefits, but also poses risks to human health. To better understand the potential risks, Quantitative Microbial Risk Assessment (QMRA) was performed for three population groups in Kampala, Uganda: wastewater and faecal sludge treatment plant workers; farmers using faecal sludge; and consumers of faecal sludge-fertilised vegetables. Two models were applied for farmers and consumers, one based on pathogen concentrations from field sampling of sludge, soils and vegetables, and one based on theoretical pathogen contribution from the last sludge application, including decay and soil to crop transfer of pathogens. The risk was evaluated for two pathogens (enterohaemorrhagic E. coli (EHEC) and Ascaris lumbricoides ). The field data on sludge, soil and vegetables indicated that the last application of faecal sludge was not the sole pathogen source . Correspondingly, the model using field data resulted in higher risks for farmers and consumers than the theoretical model assuming risk from sludge only, except when negligible for both. For farmers, the yearly risk of illness, based on measured concentrations, was 26% from EHEC and 70% from Ascaris, compared with 1.2% and 1.4%, respectively, considering the theoretically assumed contribution from the sludge. For consumers, the risk of illness based on field samples was higher from consumption of leafy vegetables (100% from EHEC, 99% from Ascaris) than from consumption of cabbages (negligible for EHEC, 26% from Ascaris). With the theoretical model, the risk of illness from EHEC was negligible for both crops, whereas the risk of illness from Ascaris was 64% and 16% for leafy vegetables and cabbage, respectively. For treatment plant workers, yearly risk of illness was 100% from EHEC and 99.4% from Ascaris . Mitigation practices evaluated could reduce the relative risk by 30-70%. These results can help guide treatment and use of faecal sludge in Kampala, to protect plant workers, farmers and consumers.(c)& nbsp;2021 The Authors. Published by Elsevier Ltd. This is an open access article under the CC BY license ( http://creativecommons.org/licenses/by/4.0/ )
2021 JUN 1
WOS:000644359600021
journalArticle
32
CANCER CAUSES & CONTROL
DOI 10.1007/s10552-021-01429-x
7
Baldi
Isabelle
De Graaf
Lucie
Bouvier
Ghislaine
Gruber
Anne
Loiseau
Hugues
Meryet-Figuiere
Matthieu
Rousseau
Sarah
Fabbro-Peray
Pascale
Lebailly
Pierre
Occupational exposure to pesticides and central nervous system tumors: results from the CERENAT case-control study
Background The etiology of the central nervous system (CNS) tumors remains largely unknown. The role of pesticide exposure has been suggested by several epidemiological studies, but with no definitive conclusion. Objective To analyze associations between occupational pesticide exposure and primary CNS tumors in adults in the CERENAT study. Methods CERENAT is a multicenter case-control study conducted in France in 2004-2006. Data about occupational pesticide uses-in and outside agriculture-were collected during detailed face-to-face interviews and reviewed by experts for consistency and exposure assignment. Odds ratios (ORs) and 95% confidence intervals (95% CI) were estimated with conditional logistic regression. Results A total of 596 cases (273 gliomas, 218 meningiomas, 105 others) and 1 192 age- and sex-matched controls selected in the general population were analyzed. Direct and indirect exposures to pesticides in agriculture were respectively assigned to 125 (7.0%) and 629 (35.2%) individuals and exposure outside agriculture to 146 (8.2%) individuals. For overall agricultural exposure, we observed no increase in risk for all brain tumors (OR 1.04, 0.69-1.57) and a slight increase for gliomas (OR 1.37, 0.79-2.39). Risks for gliomas were higher when considering agricultural exposure for more than 10 years (OR 2.22, 0.94-5.24) and significantly trebled in open field agriculture (OR 3.58, 1.20-10.70). Increases in risk were also observed in non-agricultural exposures, especially in green space workers who were directly exposed (OR 1.89, 0.82-4.39), and these were statistically significant for those exposed for over 10 years (OR 2.84, 1.15-6.99). Discussion These data support some previous findings regarding the potential role of occupational exposures to pesticides in CNS tumors, both inside and outside agriculture.
2021 JUL
WOS:000641196500001
773-782
journalArticle
291
JOURNAL OF ENVIRONMENTAL MANAGEMENT
DOI 10.1016/j.jenvman.2021.112632
Sreeja
K. G.
Madhusoodhanan
C. G.
Eldho
T., I
Conflicting trajectories of landscape transformation in the humid tropical agricultural plantations of the Western Ghats, India
The forest-agricultural landscapes of the humid tropics are transforming in their physical and socio-cultural spaces. Even though the processes of landscape transformation are highly contextual, their drivers, impacts and implications fan out across multiple scales from the local to the global. In the present study, the processes of landscape change, their multi-scalar actors and trajectories are examined in the agricultural plantations of tea, coffee and cardamom within a humid tropical forest of the Western Ghats, India. It employs an integrated multiple-source analysis of data collected through household surveys and interviews, secondary datasets, satellite imageries and litigation documents. The landscape change processes identified in the physical, social and cultural spaces include confiscation of plantations by the state, simplification of agricultural practices or abandonment of cultivation altogether, casualisation and feminisation of labour and non-agricultural diversions such as land speculation and tourism, driven by the global plantation crisis and changes in national and state forest policies. Post-globalisation, there was a high out-migration of labour and a significant decline (43%) of the population in the region. The prominent institutional actors of the state, the planters and the judiciary make these forest-enclosed plantations a highly contested space, with 75% of the area under various conflicts of tenure. These processes and actors had resulted in contrasting trajectories of incipient forest regeneration on the one hand and increased degradation on the other. A contextualized analysis of these trajectories of landscape change in these globally important humid tropical landscapes can valuably inform sustainable natural resource management frameworks.
2021 AUG 1
WOS:000684998200005
journalArticle
16
PLOS ONE
DOI 10.1371/journal.pone.0250979
4
Rolle
Matteo
Tamea
Stefania
Claps
Pierluigi
ERA5-based global assessment of irrigation requirement and validation
While only 20% of harvested lands are actually irrigated, 40% of global agricultural production originates from irrigated areas. Therefore, assessing irrigation requirements is essential for the development of effective water-related policies for an efficient management of water resources. Moreover, global-scale analyses are becoming increasingly relevant, motivated by globalized production and international trade of food as well as by the need of common strategies to address climate change. In this study, a comprehensive model to estimate crop growth and irrigation requirements of 26 main crops at global scale is presented. The model computes a soil water balance using daily precipitation and reference evapotranspiration based on a high-resolution ERA5 reanalysis dataset from the European Copernicus Program. The irrigation requirement, defined as the minimum water volume to avoid water stress, is computed for year 2000 at the resolution of 5 arc-min (or 0.0833 degrees) and aggregated at different spatial and temporal scales for relevant analyses. The estimated global irrigation requirements for 962 km(3) is described in detail, also in relation to the spatial variability and to the monthly variation of the requirements. A focus on different areas of the world (California, Northern Italy and India) highlights the wealth of information provided by the model in different climatic conditions. National data of irrigation withdrawals have been used for an extensive comparison with model results. A crop-specific validation has also been made for the State of California, comparing model results with local data of irrigation volume and independent estimates of crop water use. In both cases, we found a good agreement between model results and real data.
2021 APR 30
WOS:000664607000058
journalArticle
16
PLOS ONE
DOI 10.1371/journal.pone.0250995
4
Mrowczynska-Kaminska
Aldona
Bajan
Bartlomiej
Pawlowski
Krzysztof Piotr
Genstwa
Natalia
Zmyslona
Jagoda
Greenhouse gas emissions intensity of food production systems and its determinants
It is estimated that about 1/4th of all greenhouse gas (GHG) emissions may be caused by the global food system. Reducing the GHG emissions from food production is a major challenge in the context of the projected growth of the world's population, which is increasing demand for food. In this context, the goal should be to achieve the lowest possible emission intensity of the food production system, understood as the amount of GHG emissions per unit of output. The study aimed to calculate the emission intensity of food production systems and to specify its determinants based on a panel regression model for 14 countries, which accounted for more than 65% of food production in the world between 2000 and 2014. In this article, emission intensity is defined as the amount of GHG emissions per value of global output. Research on the determinants of GHG emissions related to food production is well documented in the literature; however, there is a lack of research on the determinants of the emission intensity ratio for food production. Hence, the original contribution of this paper is the analysis of the determinants of GHG emissions intensity of food production systems. The study found the decreased of emission intensity from an average of more than 0.68 kg of CO2 equivalent per USD 1 worth of food production global output in 2000 to less than 0.46 in 2014. The determinants of emission intensity decrease included the yield of cereals, the use of nitrogen fertilizers, the agriculture material intensity, the Human Development Index, and the share of fossil fuel energy consumption in total energy use. The determinants of growth of emission intensity of food production systems included GDP per capita, population density, nitrogen fertilizer production, utilized agriculture area, share of animal production, and energy use per capita.
2021 APR 30
WOS:000664607000060
journalArticle
88
JOURNAL OF DAIRY RESEARCH
DOI 10.1017/S002202992100008X
2
Kemboi
Evans
Feroze
S. M.
Singh
Ram
Ahmed
Jabir
Tyngkan
Hehlangki
Yield gap in milk production is considerable in Indian Himalayan state of Meghalaya
Yield gaps in milk production are here defined as the differentials between the actual yield obtained by the dairy farmer and the potential farm yield (production achieved by the top 10% of farmers: Gap 2) as well as the differential between this potential farm yield and the yield registered in the research stations (Gap 1). Assessment of yield gaps provides valuable information on potential production enhancement and drivers behind yield gaps. Milk production can be increased by narrowing the predominant large yield gaps in resource-poor smallholder farming system. Hence, this study assessed the milk yield gap and factors affecting the yield gap in Ri-Bhoi district of Meghalaya, a state located in the north-eastern Himalayan region of India. This research paper provides a scope for exploring the possibilities for improving dairy production in the state as well as contributing to literature through incorporating crucial determinants responsible for milk yield gap. A sample of 81 respondents was drawn purposely from two blocks of the district. The results indicated that the average number of cattle per household was 9.38 in standard animal units. The total yield gap was estimated at 6.20 l (91.06%) per day, composed of 0.80 l (11.76%) per day of yield gap I and 5.40 l (79.30%) per day of yield gap II. This demonstrates that the top performing farms were achieving a production level not dissimilar to that obtained on the research stations, but many were doing far less well. The size of cattle shed, dairy farming experience, concentrate price and human labour were the important determinants of the yield gap. Hence, encouraging the right stocking density of cattle, training on the preparations of home-made concentrates, access to cheap and quality concentrates, incorporating training and experience sharing on proper dairy management practices and use of technology could benefit the dairy farmers of the region.
2021 MAY
WOS:000659225700002
121-127
journalArticle
13
VIRUSES-BASEL
DOI 10.3390/v13050791
5
Francois
Sarah
Antoine-Lorquin
Aymeric
Kulikowski
Maximilien
Frayssinet
Marie
Filloux
Denis
Fernandez
Emmanuel
Roumagnac
Philippe
Froissart
Remy
Ogliastro
Mylene
Characterisation of the Viral Community Associated with the Alfalfa Weevil (Hypera postica) and Its Host Plant, Alfalfa (Medicago sativa)
Advances in viral metagenomics have paved the way of virus discovery by making the exploration of viruses in any ecosystem possible. Applied to agroecosystems, such an approach opens new possibilities to explore how viruses circulate between insects and plants, which may help to optimise their management. It could also lead to identifying novel entomopathogenic viral resources potentially suitable for biocontrol strategies. We sampled the larvae of a natural population of alfalfa weevils (Hypera postica), a major herbivorous pest feeding on legumes, and its host plant alfalfa (Medicago sativa). Insect and plant samples were collected from a crop field and an adjacent meadow. We characterised the diversity and abundance of viruses associated with weevils and alfalfa, and described nine putative new virus species, including four associated with alfalfa and five with weevils. In addition, we found that trophic accumulation may result in a higher diversity of plant viruses in phytophagous pests compared to host plants.
2021 MAY
WOS:000654578000001
journalArticle
291
JOURNAL OF ENVIRONMENTAL MANAGEMENT
DOI 10.1016/j.jenvman.2021.112689
Yao
Ying
Liu
Yanxu
Wang
Yijia
Fu
Bojie
Greater increases in China's dryland ecosystem vulnerability in drier conditions than in wetter conditions
Dryland ecosystems are experiencing dramatic climate change, either drier or wetter. However, the differences in response amplitudes of dryland ecosystems to drier and wetter climates have not been frequently discussed, especially when using composite indicators at large scales. This study explores the changing patterns of ecosystem vulnerability in China's drylands by comprehensively considering exposure, sensitivity and resilience indicators using leaf area index (LAI) datasets and meteorological data within two periods from 1982 to 1999 (P1) and from 2000 to 2016 (P2). The results show that nearly 57% of China's drylands have experienced drier conditions in 2000-2016 based on the average aridity index (AI) values compared with the conditions in 1982-1999. Compared with the conditions in 1982-1999, ecosystem vulnerability has increased in 78% of dryland, and ecosystem resilience has decreased in 46% of the area in 2000-2016. The amplitudes of vulnerability increase are higher in drier conditions than in wetter conditions. Ecosystem resilience has obviously increased in wetter conditions but has decreased in drier conditions, especially in farming-pastoral ecotones with an obvious land use change. Consequently, vegetation-climate composite indicators provide a holistic pattern of China's dryland ecosystem response to climate change, and the decreased ecosystem resilience in drier conditions in northeast China should be a warning signal under the national vegetation greening background. This research highlights that the impact of drying on ecosystem resilience leads the response of ecosystems to drier environment.
2021 AUG 1
WOS:000684997900007
journalArticle
193
ENVIRONMENTAL MONITORING AND ASSESSMENT
DOI 10.1007/s10661-021-09084-0
5
Burbery
Lee
Abraham
Phil
Wood
David
de Lima
Steve
Applications of a UV optical nitrate sensor in a surface water/groundwater quality field study
Examples of the utility of UV optical nitrate sensors are provided for two field applications, investigating nitrate pollution in a lowland, peri-urban catchment. In one application, rapid, in-stream longitudinal nitrate surveys were made in summer and winter, by fixing an optical nitrate sensor operating in continuous measurement mode to a kayak that was paddled along 10 km of the mainstem of the low-order stream in under 4 h. Nitrate concentrations ranged between 3.45 and 6.39 mg NO3-N/L. Nitrate hot-spots and cool-spots were mapped and found to relate to point discharges from spring-fed tributaries and land drains. Effective nitrate removal (dN/dx=-0.08 mg N/L/km), inferred to be from assimilation reactions, was evident in the summer dataset, but not the winter nitrate dataset. In a second application, the optical sensor was configured with appropriate technology to establish an autonomous and fully automated nitrate monitoring station. The station makes daily nitrate measurements of surface water, and groundwater, sampled from a cluster of four multi-level wells. Quarterly maintenance of the nitrate sensor has proven sufficient to keep measurement errors under 5%. Most nitrate variation has been recorded at or near the water table where concentrations have ranged between 3.47 and 5.88 mg NO3-N/L, and annual maxima have occurred in late winter/spring, which coincides with when most nitrate leaching occurs from agricultural land. Seasonal nitrate patterns are not evident in groundwater sampled from 8-m depth, or deeper. High-frequency monitoring has revealed that some infra-season, short-term variability also occurs in shallow groundwater nitrate, driven by storm events, and which on occasion results in a temporary inversion of the groundwater nitrate-depth profile.
2021 MAY
WOS:000681305700002
journalArticle
68
ENVIRONMENTAL MANAGEMENT
DOI 10.1007/s00267-021-01477-8
1
Pathak
Santosh
Paudel
Krishna P.
Adusumilli
Naveen C.
Impact of the Federal Conservation Program Participation on Conservation Practice Adoption Intensity in Louisiana, USA
Conservation practices focusing on improving the soil and water quality of working lands are implemented across the United States, supported partially through the United States Department of Agriculture Natural Resources Conservation Service cost-share or incentive payment programs. We assess whether participation in federal conservation support programs induces a change in the number of conservation practices adopted by farmers. We also identify the factors that affect the adoption intensity of different best management practices. We use survey data collected from Louisiana farmers and estimate models using the matching method and Poisson quasi-likelihood model. We find that participation in the cost-share or incentive program leads to an increase in the number of conservation practices on the farms. Similarly, the use of precision technology application and farm being integrated are likely to have a higher number of on-farm conservation practices. Results have implications for federal working lands conservation support programs in the United States.
2021 JUL
WOS:000647498200001
1-16
journalArticle
16
PLOS ONE
DOI 10.1371/journal.pone.0250575
5
Parent
Leon Etienne
Jamaly
Reza
Atucha
Amaya
Jeanne Parent
Elizabeth
Workmaster
Beth Ann
Ziadi
Noura
Parent
Serge-Etienne
Current and next-year cranberry yields predicted from local features and carryover effects
Wisconsin and Quebec are the world leading cranberry-producing regions. Cranberries are grown in acidic, naturally low-fertility sandy beds. Cranberry fertilization is guided by general soil and tissue nutrient tests in addition to yield target and vegetative biomass. However, other factors such as cultivar, location, and carbon and nutrient storage impact cranberry nutrition and yield. The objective of this study was to customize nutrient diagnosis and fertilizer recommendation at local scale and for next-year cranberry production after accounting for local factors and carbon and nutrient carryover effects. We collected 1768 observations from on-farm surveys and fertilizer trials in Quebec and Wisconsin to elaborate a machine learning model using minimum datasets. We tested carryover effects in a 5-year Quebec fertilizer experiment established on permanent plots. Micronutrients contributed more than macronutrients to variation in tissue compositions. Random Forest model related accurately current-year berry yield to location, cultivars, climatic indices, fertilization, and tissue and soil tests as features (classification accuracy of 0.83). Comparing compositions of defective and successful tissue compositions in the Euclidean space of tissue compositions, the general across-factor diagnosis differed from the local factor-specific diagnosis. Nutrient standards elaborated in one region could hardly be transposed to another and, within the same region, from one bed to another due to site-specific characteristics. Next-year yield and nutrient adjustment could be predicted accurately from current-year yield and tissue composition and other features, with R-2 value of 0.73 in regression mode and classification accuracy of 0.85. Compositional and machine learning methods proved to be effective to customize nutrient diagnosis and predict site-specific measures for nutrient management of cranberry stands. This study emphasized the need to acquire large experimental and observational datasets to capture the numerous factor combinations impacting current and next-year cranberry yields at local scale.
2021 MAY 10
WOS:000664624400015
journalArticle
27
JOURNAL OF AGROMEDICINE
DOI 10.1080/1059924X.2021.1900971
2
Parak
Farideh
Poursaeed
Alireza
Eshraghi-Samani
Roya
Chaharsoughi-Amin
Hamed
Designing a Model via Grounded Theory to Reduce Agricultural Work Injury among Orchardists in Ilam Province
The present study aimed to design a model to reduce agricultural work injury among orchardists in Ilam Province, Iran. This was a qualitative research study that used grounded theory to analyze data. The study included 25 specialists, managers, and experts of horticulture in Ilam Province who were selected through purposive sampling. Field observations and interviews in the form of focus groups were used for collecting data. The results were extracted from the research data through the coding process (open, axial, and selective) in the form of concepts, subcategories, and categories using MAXqda12. The paradigm model included causal, contextual and intervening conditions, strategy, and consequences. The results indicated that several causal conditions can affect work injury in agriculture. These were identified as vulnerability level, personal characteristics of orchardists, subsistence level, general health, climatic conditions, and academic qualifications. Contextual conditions also included categories like trends, occupational safety and health principles, infrastructure, government support, and government incentives. Meanwhile, intervening conditions were identified as structural, educational-research factors, economic criteria, regulation and development of marketing horticultural and greenhouse products, type of exploitation system, and orchardists' motivation. Finally, reducing agricultural work injuries among orchardists involved the multi-faceted identification of various aspects of production and education, along with technical, operational, executive, and supervisory management strategies. Reducing the number of agricultural work injuries among orchardists would lead to regional, economic, individual, and social benefits. The results helped researchers to identify what areas to address and mitigate safety issues of horticultural activities in Ilam.
2022 APR 3
WOS:000649629800001
207-216
journalArticle
28
ENVIRONMENTAL SCIENCE AND POLLUTION RESEARCH
DOI 10.1007/s11356-021-14438-9
38
Zhou
Xudong
Xue
Zhengkai
Seydehmet
Jumeniyaz
An empirical study on industrial eco-efficiency in arid resource exploitation region of northwest China
Located in the northwest of China, Xinjiang is a typical arid desert area and mineral resources development zone. The lack of water resources and a fragile ecological environment restricts the sustainable development of the region. Based on the industrial panel data of Xinjiang from 2001 to 2015, this paper uses the undesirable output SBM model, Malmquist index model, and Tobit regression model to comprehensively and systematically measure and evaluate the industrial eco-efficiency and its change characteristics from provincial, regional, and prefectural levels. The results show that (1) the industrial eco-efficiency level in Xinjiang is generally low, lower than the national average, but the development trend is good, and it has been steadily rising over time, from 2001 to 2015 and from the "Tenth Five-Year Plan" period to the "Twelfth Five-Year Plan" period. (2) The spatial distribution of industrial ecological efficiency of Xinjiang is not balanced. Northern Xinjiang is larger than that of eastern Xinjiang and the southern Xinjiang. The developments of 14 prefectures are uneven and asynchronous, which can be divided into two development modes: industrial and agriculture and animal husbandry region. (3) Through the decomposition analysis of the Malmquist index, it has been found that the technological progress index is the restriction factor of the changing trend of TFP, while the technical efficiency index and the pure technical efficiency index are the promoting factors. (4) The main factors causing the decline in ecological efficiency are industrial sulfur dioxide emissions, industrial nitrogen oxide emissions, total industrial water consumption, and general industrial solid waste. It can be seen that the emission of air pollutants and excessive industrial water are the main problems in the region. (5) Industrial ecological efficiency is positively correlated with industrial development level, scientific and technological innovations, industrial structure, and environmental planning, whereas negatively correlated with the degree of opening up and industrial agglomeration. (6) Xinjiang is an extremely arid and water-scarce region. These are the keys and prerequisites for saving water resources and strengthening the comprehensive utilization of water resources. Whether in the industrial areas or in the agricultural and animal husbandry areas, water conservation should be given top priority.
2021 OCT
WOS:000653624400013
53394-53411
journalArticle
5
NATURE HUMAN BEHAVIOUR
DOI 10.1038/s41562-021-01120-w
11
Sandeford
David S.
A quantitative analysis of intensification in the ethnographic record
The intensification of food production plays a central role in the evolution of complex human societies. However, it is unclear whether the standard model of intensification is theoretically or empirically justified. This leaves social scientists unable to make reasonable inferences about the relationship between intensification and the evolution of social complexity in past societies. To remedy this problem, I derive a model of intensification from human macroecology, settlement scaling theory, human behavioural ecology, cultural evolutionary theory and niche construction theory. The standard and cultural niche construction models are formalized and their predictions are tested using a comprehensive ethnographic dataset that describes food production in 40 human societies, ranging in complexity from foraging bands to agricultural states. Analysis of the ethnographic record suggests that we reject the standard model and tentatively accept the cultural niche construction model. I attempt to demonstrate the broader utility of the cultural niche construction model as a framework that may help explain the transition from small-scale to large-scale complex societies.Sandeford challenges the standard model of intensification using an ethnographic dataset that describes food production in 40 human societies ranging in complexity from small-scale foraging bands to large-scale agricultural states.
2021 NOV
WOS:000655595800002
1502-+
journalArticle
169
MARINE POLLUTION BULLETIN
DOI 10.1016/j.marpolbul.2021.112526
Seceh
C.
Pinazo
C.
Rodier
M.
Lajaunie-Salla
K.
Mazoyer
C.
Grenz
C.
Le Gendre
R.
Biogeochemical model of nitrogen cycling in Ahe (French Polynesia), a South Pacific coral atoll with pearl farming
A biogeochemical model (ECO3M-Atoll) was configured to simulate the lower food web in Ahe Atoll lagoon where phytoplankton is mostly nitrogen limited. Understanding the dynamics of phytoplankton - the main food source for oysters - is crucial for the management and the allocation of new pearl farming sites. After parametrizing the model with in situ observations, we tested different hypotheses about nitrogen cycling (benthic remineralization, atmospheric N fixation, etc.) and compared the results to a large observational dataset. Model results show that simulated (pico- and nano-) phytoplankton biomass and nitrogen concentrations are close to in situ data. The simulated biogeochemical processes (uptake and primary production) are also very similar to the observed values. In the model, primary production ranged from 1.00 to 2.00 mg C m- 3 h-1 for pico- and 0.40 to 1.00 mg C m- 3 h-1 for nanophytoplankton; mean N uptake was 2.02 limol N m- 3 h-1 for pico- and 1.25 limol N m- 3 h-1 for nanophytoplankton.
2021 AUG
WOS:000679311200009
journalArticle
21
SENSORS
DOI 10.3390/s21113867
11
Lopez-Morales
Juan A.
Martinez
Juan A.
Caro
Manuel
Erena
Manuel
Skarmeta
Antonio F.
Climate-Aware and IoT-Enabled Selection of the Most Suitable Stone Fruit Tree Variety
The application of new technologies such as the Internet of Things offers the opportunity to improve current agricultural development, facilitate daily tasks, and turn farms into efficient and sustainable production systems. The use of these new technologies enables the digital transformation process demanded by the sector and provides agricultural collectives with more optimized analysis and prediction tools. Due to climate change, one of the farm industry's problems is the advance or decay in the cycle of stone fruit trees. The objective is to recommend whether a specific area meets the minimum climatic requirements for planting certain stone fruit trees based on climatic data and bioclimatic indicators. The methodology used implements a large amount of meteorological data to generate information on specific climatic conditions and interactions on crops. In this work, a pilot study has been carried out in the Region of Murcia using an IoT platform. We simulate scenarios for the development of stone fruit varieties better adapted to the environment. Based on the standard, open interfaces, and protocols, the platform integrates heterogeneous information sources and interoperability with other third-party solutions to exchange and exploit such information.
2021 JUN
WOS:000660662000001
journalArticle
19
MARINE DRUGS
DOI 10.3390/md19060314
6
Lee
Won-Kyu
Ryu
Yong-Kyun
Choi
Woon-Yong
Kim
Taeho
Park
Areumi
Lee
Yeon-Ji
Jeong
Younsik
Lee
Choul-Gyun
Kang
Do-Hyung
Year-Round Cultivation of Tetraselmis sp. for Essential Lipid Production in a Semi-Open Raceway System
There is increasing demand for essential fatty acids (EFAs) from non-fish sources such as microalgae, which are considered a renewable and sustainable biomass. The open raceway system (ORS) is an affordable system for microalgae biomass cultivation for industrial applications. However, seasonal variations in weather can affect biomass productivity and the quality of microalgal biomass. The aim of this study was to determine the feasibility of year-round Tetraselmis sp. cultivation in a semi-ORS in Korea for biomass and bioactive lipid production. To maximize biomass productivity of Tetraselmis sp., f medium was selected because it resulted in a significantly higher biomass productivity (1.64 +/- 0.03 g/L) and lower omega-6/omega-3 ratio (0.52/1) under laboratory conditions than f/2 medium (0.70/1). Then, we used climatic data-based building information modeling technology to construct a pilot plant of six semi-ORSs for controlling culture conditions, each with a culture volume of 40,000 L. Over 1 year, there were no significant variations in monthly biomass productivity, fatty acid composition, or the omega-6/omega-3 ratio; however, the lipid content correlated significantly with photosynthetic photon flux density. During year-round cultivation from November 2014 to October 2017, areal productivity was gradually increased by increasing medium salinity and injecting CO2 gas into the culture medium. Productivity peaked at 44.01 g/m(2)/d in October 2017. Throughout the trials, there were no significant differences in average lipid content, which was 14.88 +/- 1.26%, 14.73 +/- 2.44%, 12.81 +/- 2.82%, and 13.63 +/- 3.42% in 2014, 2015, 2016, and 2017, respectively. Our results demonstrated that high biomass productivity and constant lipid content can be sustainably maintained under Korean climate conditions.
2021 JUN
WOS:000665893000001
journalArticle
23
NANOIMPACT
DOI 10.1016/j.impact.2021.100326
Cummings
Christopher L.
Kuzma
Jennifer
Kokotovich
Adam
Glas
David
Grieger
Khara
Barriers to responsible innovation of nanotechnology applications in food and agriculture: A study of US experts and developers
The use of nanotechnology and engineered nanomaterials in food and agriculture (nano-agrifood) sectors is intended to provide several potential benefits to consumers and society, such as the provision of more nutritious processed foods, edible food coatings to extend shelf lives of fresh cut produce, and more sustainable alternatives to traditional agrochemicals. The responsible innovation of nano-agrifoods may be particularly important to pursue given previous case studies involving other agrifood technologies that experienced significant public consternation. Here, we define responsible innovation following Stilgoej et al. (2013) that establishes processes to iteratively review and reflect upon one's innovation, engage stakeholders in dialogue, and to be open and transparent throughout innovation stages - processes that go beyond primary focuses of understanding environmental, health, and safety impacts of nano-enabled products and implementing safe-by-design principles. Despite calls for responsible nano-innovation across diverse sectors, it has not yet been clear what types of barriers are faced by nano-agrifood researchers and innovators in particular. This study therefore identifies and builds the first typology of barriers to responsible innovation as perceived by researchers and product developers working in nano-agrifood sectors in the United States. Our findings report 5 key barriers to responsible innovation of nano-agrifoods: Lack of Data (reported by 70% of all interview participants, and represented 34.6% of all barrier-related excerpts), Lack of Product Oversight (reported by 60% of participants, and represented 28.7% of excerpts), Need for Ensuring Marketability & Use (reported by 70% of participants, and represented 21.3% of all barrier-related excerpts), Need for Increased Collaboration (reported by 40% of participants, and represented 10.3% of excerpts), and finally Lack of Adequate Training & Workforce (reported by 30% of participants, and represented by 5.1% of excerpts). We also relate these key barriers across three main nano-innovation phases, including 1) Scientific and Technical R&D, 2) Product Oversight, and 3) Post-commercialization Marketability & Use, and discuss how these barriers may impact stakeholders as well as present opportunities to align with principles of responsible innovation. Overall, these findings may help illuminate challenges that researchers and innovators face in the pursuit of responsible innovation relevant for the field of nanotechnology with relevancy for other emerging food and agricultural technologies more broadly.
2021 JUL
WOS:000693220800013
journalArticle
18
INTERNATIONAL JOURNAL OF ENVIRONMENTAL RESEARCH AND PUBLIC HEALTH
DOI 10.3390/ijerph18126517
12
Capacci
Enrico
Franceschetti
Bruno
Guzzomi
Andrew
Rondelli
Valda
Energy Absorption in Actual Tractor Rollovers with Different Tire Configurations
In order to better understand the complexities of modern tractor rollover, this paper investigates the energy absorbed by a Roll-Over Protective Structure (ROPS) cab during controlled lateral rollover testing carried out on a modern narrow-track tractor with a silent-block suspended ROPS cab. To investigate how different tractor set-ups may influence ROPS and energy partitioning, tests were conducted with two different wheel configurations, wide (equivalent to normal 'open field' operation) and narrow (equivalent to 'orchard/vineyard' operation), and refer to both the width of the tires and the corresponding track. Dynamic load cells and displacement transducers located at the ROPS-ground impact points provided a direct measurement of the energy absorbed by the ROPS cab frame. A trilateration method was developed and mounted onboard to measure load cell trajectory with respect to the cab floor in real-time. The associated video record of each rollover event provided further information and opportunity to explain the acquired data. The narrow tire configuration consistently subjected the ROPS cab frame to more energy than the wide tire arrangement. To better evaluate the influence of the ROPS cab silent-blocks in lateral rollover, static and dynamic tests were performed. The results confirm that tires influence the energy partition significantly and that further understanding of silent-blocks' dynamic performance is warranted.
2021 JUN
WOS:000665883900001
journalArticle
77
JOURNAL OF SAFETY RESEARCH
DOI 10.1016/j.jsr.2021.03.001
Kjestveit
Kari
Aas
Oddfrid
Holte
Kari Anne
Occupational injury rates among Norwegian farmers: A sociotechnical perspective
Introduction: This study addressed relative injury risk among Norwegian farmers, who are mostly self-employed and run small farm enterprises. The aim was to explore the relative importance of individual, enterprise, and work environment risks for occupational injury and to discuss the latent conditions for injuries using sociotechnical system theory. Method: Injury report and risk factors were collected through a survey among Norwegian farm owners in November 2012. The response rate was 40% (n = 2,967). Annual work hours were used to calculate injury rates within groups. Poisson regression using the log of hours worked as the offset variable allowed for the modeling of adjusted rate ratios for variables pre-dictive of injury risk. Finally, safety climate measures were introduced to assess potential moderating effects on risk. Results: Results showed that the most important risk factors for injuries were the design of the workplace, type of production, and off-farm work hours. The main results remained unchanged when adding safety climate measures, but the measures moderated the injury risk for categories of pre -dominant production and increased the risk for farmers working with family members and/or employees. An overall finding is how the risk factors were interrelated. Conclusions: The study identified large struc-tural diversities within and between groups of farmers. The study drew attention to operating conditions rather than individual characteristics. The farmer's role (managerial responsibility) versus regulation and safety climate is important for discussions of injury risk. Practical Applications: We need to study sub-groups to understand how regulation and structural changes affect work conditions and management within different work systems, conditioned by production. It is important to encourage actors in the political-economic system to become involved in issues that were found to affect the safety of farmers.(c) 2021 The Author(s). Published by the National Safety Council and Elsevier Ltd. This is an open access article under the CC BY license (http://creativecommons.org/licenses/by/4.0/).
2021 JUN
WOS:000658972700019
182-195
journalArticle
15
ANIMAL
DOI 10.1016/j.animal.2021.100248
7
Harrison
B. P.
Dorigo
M.
Reynolds
C. K.
Sinclair
L. A.
Ray
P. P.
Phosphorus feeding practices, barriers to and motivators for minimising phosphorus feeding to dairy cows in diverse dairy farming systems
Minimising phosphorus (P) feeding to dairy cows can reduce feed costs and minimise water pollution without impairing animal performance. This study aimed to determine current P feeding practices and identify the barriers to and motivators for minimising P feeding on dairy farms, using Great Britain (GB) dairy farming as an example of diverse systems. Farmers (n = 139) and feed advisers (n = 31) were involved simultaneously in independent questionnaire surveys on P feeding in dairy farms. Data on the herd size, milk yield and concentrate fed were analysed using ANOVA to investigate the effect of farm classification, region, and feed professional advice. Chi-square tests were used to investigate associations between farm characteristics and implemented P feeding and management practices. Most farmers (72%) did not know the P concentration in their lactating cow's diet and did not commonly adopt precision P feeding practices, indicating that cows might have been offered dietary P in excess of recommended P requirement. Farmers' tendency to feed P in excess of recommendations increased with herd size, but so did their awareness of P pollution issues and likeliness of testing manure P. However, 68% of farmers did not analyse manure P, indicating that mineral P fertiliser application rates were not adjusted accordingly, highlighting the risk of P being applied beyond crops' requirement. Almost all farmers (96%) were willing to lower dietary P concentration but the uncertainty of P availability in feed ingredients (30%) and concerns over reduced cow fertility (22%) were primary barriers. The willingness to reduce dietary P concentrations was driven by the prospect of reducing environmental damage (28%) and feed costs (27%) and advice from their feed professionals (25%). Most farmers (70%) relied on a feed professional, and these farmers had a higher tendency to analyse their forage P. However, farmers of pasture-based systems relied less on feed professionals. Both farmers (73%) and feed advisers (68%) were unsatisfied with the amount of training on P management available. Therefore, the training on P management needs to be more available and the influence that feed professionals have over P feeding should be better utilised. Study findings demonstrate the importance of considering type of dairy farming systems when developing precision P feeding strategies and highlight the increasing importance of feed professionals in minimising P feeding. (c) 2021 The Author(s). Published by Elsevier B.V. on behalf of The Animal Consortium. This is an open access article under the CC BY license (http://creativecommons.org/licenses/by/4.0/).
2021 JUL
WOS:000681313700028
journalArticle
16
PLOS ONE
DOI 10.1371/journal.pone.0253069
6
Molina-Venegas
Rafael
Rodriguez
Miguel Angel
Pardo-de-Santayana
Manuel
Mabberley
David J.
A global database of plant services for humankind
Humanity faces the challenge of conserving the attributes of biodiversity that may be essential to secure human wellbeing. Among all the organisms that are beneficial to humans, plants stand out as the most important providers of natural resources. Therefore, identifying plant uses is critical to preserve the beneficial potential of biodiversity and to promote basic and applied research on the relationship between plants and humans. However, much of this information is often uncritical, contradictory, of dubious value or simply not readily accessible to the great majority of scientists and policy makers. Here, we compiled a genus-level dataset of plant-use records for all accepted vascular plant taxa (13489 genera) using the information gathered in the 4(th) Edition of Mabberley's plant-book, the most comprehensive global review of plant classification and their uses published to date. From 1974 to 2017 all the information was systematically gathered, evaluated, and synthesized by David Mabberley, who reviewed over 1000 botanical sources including modern Floras, monographs, periodicals, handbooks, and authoritative websites. Plant uses were arranged across 28 standard categories of use following the Economic Botany Data Collection Standard guidelines, which resulted in a binary classification of 9478 plant-use records pertaining human and animal nutrition, materials, fuels, medicine, poisons, social and environmental uses. Of all the taxa included in the dataset, 33% were assigned to at least one category of use, the most common being "ornamental" (26%), "medicine" (16%), "human food" (13%) and "timber" (8%). In addition to a readily available binary matrix for quantitative analyses, we provide a control text matrix that links the former to the description of the uses in Mabberley's plant-book. We hope this dataset will serve to establish synergies between scientists and policy makers interested in plant-human interactions and to move towards the complete compilation and classification of the nature's contributions to people upon which the wellbeing of future generations may depend.
2021 JUN 15
WOS:000665475100022
journalArticle
286
ENVIRONMENTAL POLLUTION
DOI 10.1016/j.envpol.2021.117559
Hayashi
Kentaro
Shibata
Hideaki
Oita
Azusa
Nishina
Kazuya
Ito
Akihiko
Katagiri
Kiwamu
Shindo
Junko
Winiwarter
Wilfried
Nitrogen budgets in Japan from 2000 to 2015: Decreasing trend of nitrogen loss to the environment and the challenge to further reduce nitrogen waste*
The benefits of the artificial fixation of reactive nitrogen (Nr, nitrogen [N] compounds other than dinitrogen), in the form of N fertilizers and materials are huge, while at the same time posing substantial threats to human and ecosystem health by the release of Nr to the environment. To achieve sustainable N use, Nr loss to the envi-ronment must be reduced. An N-budget approach at the national level would allow us to fully grasp the whole picture of Nr loss to the environment through the quantification of important N flows in the country. In this study, the N budgets in Japan were estimated from 2000 to 2015 using available statistics, datasets, and liter-ature. The net N inflow to Japanese human sectors in 2010 was 6180 Gg N yr -1 in total. With 420 Gg N yr-1 accumulating in human settlements, 5760 Gg N yr -1 was released from the human sector, of which 1960 Gg N yr -1 was lost to the environment as Nr (64% to air and 36% to waters), and the remainder assumed as dinitrogen. Nr loss decreased in both atmospheric emissions and loss to terrestrial water over time. The distinct reduction in the atmospheric emissions of nitrogen oxides from transportation, at-4.3% yr-1, was attributed to both emission controls and a decrease in energy consumption. Reductions in runoff and leaching from land as well as the discharge of treated water were found, at-1.0% yr -1 for both. The aging of Japan's population coincided with the reductions in the per capita supply and consumption of food and energy. Future challenges for Japan lie in further reducing N waste and adapting its N flows in international trade to adopt more sustainable options considering the reduced demand due to the aging population.<comment>Superscript/Subscript Available</comment
2021 OCT 1
WOS:000691736200001
journalArticle
791
SCIENCE OF THE TOTAL ENVIRONMENT
DOI 10.1016/j.scitotenv.2021.148099
Adhikari
Kamal P.
Chibuike
Grace
Saggar
Surinder
Simon
Priscila L.
Luo
Jiafa
de Klein
Cecile A. M.
Management and implications of using nitrification inhibitors to reduce nitrous oxide emissions from urine patches on grazed pasture soils - A review
Livestock urine patches are the main source of nitrous oxide (N2O) emissions in pastoral system, and nitrification inhibitors (NIs) have been widely investigated as a N2O mitigation strategy. This study reviews the current understanding of the effect of NIs use on N2O emissions from urine patches, including the factors that affect their efficacy, as well as the unintended consequences of NIs use. It brings together the fundamental aspects of targeted management of urine patches for reducing N2O emissions involving inhibitors. The available literature of 196 datasets indicates that dicyandiamide (DCD), 3,4-dimethylpyrazole phosphate (DMPP), and 2-chloro-6-(trichloromethyl) pyridine (nitrapyrin) reduced N2O emissions from urine patches by 44 +/- 2%, 28 +/- 38% and 28 +/- 5%, (average +/- s.e.), respectively. DCD also increased pasture dry matter and nitrogen (N) uptake by 13 +/- 2% and 15 +/- 3%, (average +/- s.e.), respectively. The effect of DMPP and nitrapyrin on pasture dry matter and N uptake, assessed in only one study, was not significant. It also suggests that harmonizing the timing of inhibitor use with urine-N transformation increase the efficacy of NIs. No negative impacts on non-targeted soil and aquatic organisms have been reported with the recommended rate of DCD applied to urine and recommended applications of DMPP and nitrapyrin for treated mineral fertilisers and manures. However, there was evidence of the presence of small amounts of DCD residues in milk products as a result of its use on livestock grazed pasture. DMPP and nitrapyrin can also enter the food chain via grazing livestock. The study concludes that for the use of NIs in livestock grazed systems, research is needed to establish acceptable maximum residue level (MRL) of NIs in soil, plant, and animal products, and develop technologies that optimise physical mixing between NIs and urine patches. (C) 2021 Elsevier B.V. All rights reserved.
2021 OCT 15
WOS:000686011600012
journalArticle
184
CELL
DOI 10.1016/j.cell.2021.04.046
13
Qin
Peng
Lu
Hongwei
Du
Huilong
Wang
Hao
Chen
Weilan
Chen
Zhuo
He
Qiang
Ou
Shujun
Zhang
Hongyu
Li
Xuanzhao
Li
Xiuxiu
Li
Yan
Liao
Yi
Gao
Qiang
Tu
Bin
Yuan
Hua
Ma
Bingtian
Wang
Yuping
Qian
Yangwen
Fan
Shijun
Li
Weitao
Wang
Jing
He
Min
Yin
Junjie
Li
Ting
Jiang
Ning
Chen
Xuewei
Liang
Chengzhi
Li
Shigui
Pan-genome analysis of 33 genetically diverse rice accessions reveals hidden genomic variations
Structural variations (SVs) and gene copy number variations (gCNVs) have contributed to crop evolution, domestication, and improvement. Here, we assembled 31 high-quality genomes of genetically diverse rice accessions. Coupling with two existing assemblies, we developed pan-genome-scale genomic resources including a graph-based genome, providing access to rice genomic variations. Specifically, we discovered 171,072 SVs and 25,549 gCNVs and used an Oryza glaberrima assembly to infer the derived states of SVs in the Oryza sativa population. Our analyses of SV formation mechanisms, impacts on gene expression, and distributions among subpopulations illustrate the utility of these resources for understanding how SVs and gCNVs shaped rice environmental adaptation and domestication. Our graph-based genome enabled genome-wide association study (GWAS)-based identification of phenotype-associated genetic variations undetectable when using only SNPs and a single reference assembly. Our work provides rich population-scale resources paired with easy-to-access tools to facilitate rice breeding as well as plant functional genomics and evolutionary biology research.
2021 JUN 24
WOS:000665547300018
3542-+
journalArticle
295
JOURNAL OF ENVIRONMENTAL MANAGEMENT
DOI 10.1016/j.jenvman.2021.113141
Upadhyay
Shweta
Singh
Rishikesh
Verma
Pramit
Raghubanshi
Akhilesh Singh
Spatio-temporal variability in soil CO2 efflux and regulatory physicochemical parameters from the tropical urban natural and anthropogenic land use classes
Urban ecosystems, the heterogeneous and rapidly changing landscape, showed a considerable impact on the global C cycle. However, studies encompassing the spatial differences in urban land uses on soil C dynamics are limited in tropical ecosystems. In this study, seasonal and temporal variability in soil CO2 efflux (SCE) and its regulatory physicochemical variables under five urban land use classes viz., Bare (BAR), Agriculture (AGR), Plantation (PLT), Grassland (GRA) and Lawns (LAW) were assessed from 2014 to 2016. Bare land use was considered as the reference for observing the variation for different land uses. Seasonal measurements of SCE, soil temperature, moisture content, pH, ammonium-N, nitrate-N and microbial biomass C (MBC) were performed whereas soil organic C (SOC), soil N, and soil physical properties were measured annually. Our results showed a significant (P < 0.01) increase in SCE by 89%, 117%, 132% and 166% for land use types from BAR to AGR, PLT, GRA and LAW, respectively. The results revealed a two-fold increase in SCE from anthropogenically managed urban lawns as compared to bare soil. PLT and LAW land use classes showed higher SOC and N contents. SCE was found positively correlated with temperature, moisture, SOC, soil N and MBC whereas negatively correlated with ammonium-N and nitrate-N (at P < 0.05) for the overall dataset. Soil moisture, temperature, SOC, porosity and pH were identified as the major determinant of urban SCE by explaining 63% of the variability in overall SCE. Further, temperature for BAR and LAW; moisture for PLT; ammonium-N for GRA; and nitrate-N for AGR were identified as the major regulators of SCE for different land use classes. The findings revealed that the interaction of soil temperature and moisture with nutrient availability regulates overall and seasonal variability in SCE in an urban ecosystem. Since these variables are highly affected by climate change, thus, the soil C source-sink relationships in tropical urban ecosystems may further change and induce a positive global warming potential from urban ecosystems.
2021 OCT 1
WOS:000681299300006
journalArticle
51
AMBIO
DOI 10.1007/s13280-021-01590-2
3
Tombre
Ingunn M.
Fredriksen
Fredrik
Jerpstad
Odd
Ostnes
Jan Eivind
Eythorsson
Einar
Population control by means of organised hunting effort: Experiences from a voluntary goose hunting arrangement
Implementing management objectives may be challenging when decisions are made at different scales than where they are supposed to be carried out. In this study we present a situation where local goose hunting arrangements respond to objectives in an international management plan for pink-footed geese (Anser brachyrhynchus) and a local wish to reduce goose numbers as means to reduce grazing damage on farmland. A unique ten-year dataset provides an evaluation of the efficiency of voluntary actions at a local scale for implementing a policy of population control of geese, and general lessons are drawn for collaboration and co-production of knowledge for adaptive management. The study demonstrates how both the hunters and geese adapt in a situation where increasing the harvest of geese is the main objective. Introducing hunting-free days and safe foraging areas significantly increased goose numbers in the study area, with a corresponding increase in hunting success in terms of number of harvested geese. The geese's behavioural response to hunting also triggered the hunters to adapt accordingly by optimal timing and placement in the landscape. Based on the results of the present study we suggest a framework for local implementation of management actions. Bringing end-users on board, facilitates processes and strengthens the achievements, as they represent the actors where implementation occurs. Specifically, our findings demonstrate how optimal goose hunting can be practiced by the use of an adaptive framework with active stakeholder participation.
2022 MAR
WOS:000668093200001
728-742
journalArticle
66
ANNALS OF WORK EXPOSURES AND HEALTH
DOI 10.1093/annweh/wxab047
1
Austigard
Ase Dalseth
Smedbold
Hans Thore
Hydrogen Sulphide (H2S) Exposure Hazard Assessment: An Algorithm for Generating Exposure Index Based on Direct Instrument Readings
Objectives: Increased use of small affordable alarm sensors with logging or network capabilities has improved the ability to monitor exposure.The large datasets generated from these monitors calls for development of a computer algorithm to assess these data.Methods: We examined 88 time series of hydrogen sulphide (H2S) from wastewater works previously used for developing the exposure index.The time series covered 331 h, where 16 h had readings different from zero.Results: The developed algorithm reproduced the manual assessed index almost perfectly (linear regression beta = 1.02, R-2 = 0.97, P < 0.001). Time-weighted average (TWA) values of the 88 time series showed a mean value of 0.04 ppm (range 0.0-0.9). The mean index value was 18 (range 0-337), with a good linear fit (beta = 0.002, R-2 = 0.93, and P < 0.001). The index gave us a better resolution and basis for risk assessment than the TWA, and managed to combine evaluation of TWA and exceedance of ceiling value in one number.Conclusions: As long as peaks above ceiling value occur, we find alarm tools with an H2S sensor to be an essential personal protective equipment against H2S. The proposed method has been verified, and it removes some common human errors in graph evaluation. Use of the index is a possible way of quantifying risk level in exposure to H2S in one single number and provides better understanding of the risk of exposure, as it eases the analysis and evaluation of large numbers of time series.
2022 JAN
WOS:000743314400014
124-129
journalArticle
21
SENSORS
DOI 10.3390/s21144801
14
Kim
Wan-Soo
Lee
Dae-Hyun
Kim
Taehyeong
Kim
Hyunggun
Sim
Taeyong
Kim
Yong-Joo
Weakly Supervised Crop Area Segmentation for an Autonomous Combine Harvester
Machine vision with deep learning is a promising type of automatic visual perception for detecting and segmenting an object effectively; however, the scarcity of labelled datasets in agricultural fields prevents the application of deep learning to agriculture. For this reason, this study proposes weakly supervised crop area segmentation (WSCAS) to identify the uncut crop area efficiently for path guidance. Weakly supervised learning has advantage for training models because it entails less laborious annotation. The proposed method trains the classification model using area-specific images so that the target area can be segmented from the input image based on implicitly learned localization. This way makes the model implementation easy even with a small data scale. The performance of the proposed method was evaluated using recorded video frames that were then compared with previous deep-learning-based segmentation methods. The results showed that the proposed method can be conducted with the lowest inference time and that the crop area can be localized with an intersection over union of approximately 0.94. Additionally, the uncut crop edge could be detected for practical use based on the segmentation results with post-image processing such as with a Canny edge detector and Hough transformation. The proposed method showed the significant ability of using automatic perception in agricultural navigation to infer the crop area with real-time level speed and have localization comparable to existing semantic segmentation methods. It is expected that our method will be used as essential tool for the automatic path guidance system of a combine harvester.
2021 JUL
WOS:000677082300001
journalArticle
21
SENSORS
DOI 10.3390/s21134537
13
Gong
Liyun
Yu
Miao
Jiang
Shouyong
Cutsuridis
Vassilis
Pearson
Simon
Deep Learning Based Prediction on Greenhouse Crop Yield Combined TCN and RNN
Currently, greenhouses are widely applied for plant growth, and environmental parameters can also be controlled in the modern greenhouse to guarantee the maximum crop yield. In order to optimally control greenhouses' environmental parameters, one indispensable requirement is to accurately predict crop yields based on given environmental parameter settings. In addition, crop yield forecasting in greenhouses plays an important role in greenhouse farming planning and management, which allows cultivators and farmers to utilize the yield prediction results to make knowledgeable management and financial decisions. It is thus important to accurately predict the crop yield in a greenhouse considering the benefits that can be brought by accurate greenhouse crop yield prediction. In this work, we have developed a new greenhouse crop yield prediction technique, by combining two state-of-the-arts networks for temporal sequence processing-temporal convolutional network (TCN) and recurrent neural network (RNN). Comprehensive evaluations of the proposed algorithm have been made on multiple datasets obtained from multiple real greenhouse sites for tomato growing. Based on a statistical analysis of the root mean square errors (RMSEs) between the predicted and actual crop yields, it is shown that the proposed approach achieves more accurate yield prediction performance than both traditional machine learning methods and other classical deep neural networks. Moreover, the experimental study also shows that the historical yield information is the most important factor for accurately predicting future crop yields.
2021 JUL
WOS:000671314400001
journalArticle
21
SENSORS
DOI 10.3390/s21134386
13
Azizi
Afshin
Abbaspour-Gilandeh
Yousef
Mesri-Gundoshmian
Tarahom
Farooque
Aitazaz A.
Afzaal
Hassan
Estimation of Soil Surface Roughness Using Stereo Vision Approach
Soil roughness is one of the most challenging issues in the agricultural domain and plays a crucial role in soil quality. The objective of this research was to develop a computerized method based on stereo vision technique to estimate the roughness formed on the agricultural soils. Additionally, soil till quality was investigated by analyzing the height of plow layers. An image dataset was provided in the real conditions of the field. For determining the soil surface roughness, the elevation of clods obtained from tillage operations was computed using a depth map. This map was obtained by extracting and matching corresponding keypoints as super pixels of images. Regression equations and coefficients of determination between the measured and estimated values indicate that the proposed method has a strong potential for the estimation of soil shallow roughness as an important physical parameter in tillage operations. In addition, peak fitting of tilled layers was applied to the height profile to evaluate the till quality. The results of this suggest that the peak fitting is an effective method of judging tillage quality in the fields.
2021 JUL
WOS:000671285300001
journalArticle
59
GROUNDWATER
DOI 10.1111/gwat.13119
6
Butler
J. J., Jr.
Knobbe
S.
Reboulet
E. C.
Whittemore
D. O.
Wilson
B. B.
Bohling
G. C.
Water Well Hydrographs: An Underutilized Resource for Characterizing Subsurface Conditions
Many of the world's major aquifers are under severe stress as a result of intensive pumping to support irrigated agriculture and provide drinking water supplies for millions. The question of what the future holds for these aquifers is one of global importance. Without better information about subsurface conditions, it will be difficult to reliably assess an aquifer's response to management actions and climatic stresses. One important but underutilized source of information is the data from monitoring well networks that provide near-continuous records of water levels through time. Most organizations running these networks are, by necessity, primarily focused on network maintenance. The result is that relatively little attention is given to interpretation of the acquired hydrographs. However, embedded in those hydrographs is valuable information about subsurface conditions and aquifer responses to natural and anthropogenic stresses. We demonstrate the range of insights that can be gleaned from such hydrographs using data from the High Plains aquifer index well network of the Kansas Geological Survey. We show how information about an aquifer's hydraulic state and lateral extent, the nature of recharge, the hydraulic connection to the aquifer and nearby pumping wells, and the expected response to conservation-based pumping reductions can be extracted from these hydrographs. The value of this information is dependent on accurate water-level measurements; errors in those measurements can make it difficult to fully exploit the insights that water-well hydrographs can provide. We therefore conclude by presenting measures that can help reduce the potential for such errors.
2021 NOV
WOS:000669479400001
808-818
journalArticle
28
ENVIRONMENTAL SCIENCE AND POLLUTION RESEARCH
DOI 10.1007/s11356-021-15658-9
46
Liu
Yize
Zhang
Jian
Zhuang
Minghao
Bottom-up re-estimations of greenhouse gas and atmospheric pollutants derived from straw burning of three cereal crops production in China based on a national questionnaire
Crop straw open burning is considered as an important source of greenhouse gas and atmospheric pollutants emissions, which affects global climate change and regional air quality. However, due to the limitation of data availability, the current emission estimation of greenhouse gas and atmospheric pollutants from crop straw open burning remains uncertain based on the bottom-up method. Therefore, we re-estimate the greenhouse gas and atmospheric pollutants from crop straw open burning at the county level based on a national questionnaire and the up-to-data emission factors. Results showed that emissions of CO2, CH4, N2O, PM10, PM2.5, NMVOC, NH3, NOx, SO2, CO, BC, and OC from open straw burning are 69250.8 Gg, 242.9 Gg, 4.2 Gg, 771.0 Gg, 539.7 Gg, 498.2 Gg, 34.7 Gg, 200.4 Gg, 24.8 Gg, 3426.5 Gg, 63.0 Gg, and 278.5 Gg, respectively, which were lower than those of previous studies. Maize was the largest contribution, followed by wheat, rice. Hotspots for greenhouse gas and atmospheric pollutants from straw burning are mainly distributed in the 54 counties of northeast China, accounting for 20% of total emissions on average. However, the high emission of maize, wheat, and rice are mainly located at the counties of north China, northeast China, and middle-lower Yangtze River region, respectively. This study not only provides the targeted counties that need decrease further the straw open burning, but also improves the precision of emission estimation that benefits air quality modeling.
2021 DEC
WOS:000678513500034
65410-65415
journalArticle
798
SCIENCE OF THE TOTAL ENVIRONMENT
DOI 10.1016/j.scitotenv.2021.149326
Ragoobur
Doorgha
Huerta-Lwanga
Esperanza
Somaroo
Geeta Devi
Microplastics in agricultural soils, wastewater effluents and sewage sludge in Mauritius
The rapid and silent emergence of microplastics (MPs) in the environment has recently become a global problem with more and more studies are showing the harmful effects of MPs on different ecosystems. The aim of this study was to investigate the presence of MPs in agricultural soils, wastewater effluents and sewage sludge in Mauritius. The soil samples were collected randomly from three different agricultural lands which have been used for conventional agriculture for more than 25 years. Wastewater effluents and sewage sludge were collected once, using the grab sampling method, from three main operating wastewater treatment plants (WWTP) across the island and were analysed in triplicate. MPs were extracted using the flotation technique, followed by hydrogen peroxide digestion. The abundance of MPs was found to be 320.0 +/- 112.2 and 420.0 +/- 244.0 particles.kg(-1) in shallow and deep soils, respectively, out of which 42.4% and 95.8% were less than 1 mm in size, respectively. Site 3 had the highest abundance of MPs due to cumulated plastic debris dumped on the field. In addition, the average MPs concentration in sewage sludge and in wastewater effluents were 14,750 +/- 8612.9 particles.kg(-1) and 276.3 +/- 137.3 particles.L-1, respectively, whereby 90% of the MPs were less than 0.5 mm in size. WWTP 1 had the largest share of MPs in both sewage sludge and wastewater effluents. The attenuated total reflection Fourier transform infrared spectroscopy revealed that polypropylene (fibres, fragments, and flakes) was in abundance in agricultural soil samples by 56.26%, while in WWTP polyamide (fibres) was predominant by 88.85%. The findings of this preliminary study confirmed the presence of MPs in Mauritian lands, wastewater effluents and sewage sludge and therefore provide salient data to advocate for subsequent research on MPs. (C) 2021 Elsevier B.V. All rights reserved.
2021 DEC 1
WOS:000701768400011
journalArticle
50
JOURNAL OF ENVIRONMENTAL QUALITY
DOI 10.1002/jeq2.20262
5
Lewis
Kathleen
Rainford
James
Tzilivakis
John
Garthwaite
David
Application of the Danish pesticide load indicator to arable agriculture in the United Kingdom
Pesticides are an important component of worldwide agriculture systems and have contributed to significant increases in crop quality and yields and therefore to food security. However, despite their societal benefits, pesticides can be hazardous to humans and the environment. Therefore, effective pesticide polices are needed that balance the societal and economic benefits with the unintentional and undesirable environmental and health impacts. As a result, there has been consistent policy interest in pragmatic and practical techniques that are suitable for assessing the environmental and human health implications of agricultural pesticide use from a national perspective for assisting in the development of policy initiatives and for communicating policy outcomes to the public. The work described herein explored the appropriateness of the Danish Pesticide Load Indictor for assessing agricultural pesticides applied in the United Kingdom from 2016 and 2018. The findings for the two datasets appear broadly comparable, suggesting that the overall environmental load from pesticides on the U.K. environment remained relatively constant during this period. Regional differences in environmental load and the major contributing substances were identified. Where large differences between the two years were seen, regulatory interventions appear to have been the cause. Overall, the indicator behaves as expected and appears to be sufficiently responsive to changes in pesticide use. However, various concerns were identified that may lead to modifications in how the indicator is calculated and what parameters are included to make it better able to deliver U.K. policy objectives.
2021 SEP
WOS:000680272300001
1110-1122
journalArticle
21
SENSORS
DOI 10.3390/s21155110
15
Placidi
Pisana
Morbidelli
Renato
Fortunati
Diego
Papini
Nicola
Gobbi
Francesco
Scorzoni
Andrea
Monitoring Soil and Ambient Parameters in the IoT Precision Agriculture Scenario: An Original Modeling Approach Dedicated to Low-Cost Soil Water Content Sensors
A low power wireless sensor network based on LoRaWAN protocol was designed with a focus on the IoT low-cost Precision Agriculture applications, such as greenhouse sensing and actuation. All subsystems used in this research are designed by using commercial components and free or open-source software libraries. The whole system was implemented to demonstrate the feasibility of a modular system built with cheap off-the-shelf components, including sensors. The experimental outputs were collected and stored in a database managed by a virtual machine running in a cloud service. The collected data can be visualized in real time by the user with a graphical interface. The reliability of the whole system was proven during a continued experiment with two natural soils, Loamy Sand and Silty Loam. Regarding soil parameters, the system performance has been compared with that of a reference sensor from Sentek. Measurements highlighted a good agreement for the temperature within the supposed accuracy of the adopted sensors and a non-constant sensitivity for the low-cost volumetric water contents (VWC) sensor. Finally, for the low-cost VWC sensor we implemented a novel procedure to optimize the parameters of the non-linear fitting equation correlating its analog voltage output with the reference VWC.
2021 AUG
WOS:000682259100001
journalArticle
801
SCIENCE OF THE TOTAL ENVIRONMENT
DOI 10.1016/j.scitotenv.2021.149342
Gurung
Ram B.
Ogle
Stephen M.
Breidt
F. Jay
Parton
William J.
Del Grosso
Stephen J.
Zhang
Yao
Hartman
Melannie D.
Williams
Stephen A.
Venterea
Rodney T.
Modeling nitrous oxide mitigation potential of enhanced efficiency nitrogen fertilizers from agricultural systems
Agriculture soils are responsible for a large proportion of global nitrous oxide (N2O) emissions-a potent greenhouse gas and ozone depleting substance. Enhanced-efficiency nitrogen (N) fertilizers (EENFs) can reduce N2O emission from N-fertilized soils, but their effect varies considerably due to a combination of factors, including climatic conditions, edaphic characteristics and management practices. In this study, we further developed the DayCent ecosystem model to simulate two EENFs: controlled-release N fertilizers (CRNFs) and nitrification inhibitors (NIs) and evaluated their N2O mitigation potentials. We implemented a Bayesian calibration method using the sampling importance resampling (SIR) algorithm to derive a joint posterior distribution of model parameters that was informed by N2O flux measurements from corn production systems a network of experimental sites within the GRACEnet program. The joint posterior distribution can be applied to estimate predictions of N2O reduction factors when EENFs are adopted in place of conventional urea-based N fertilizer. The resulting median reduction factors were - 11.9% for CRNFs (ranging from -51.7% and 0.58%) and -26.7% for NIs (ranging from -61.8% to 3.1%), which is comparable to the measured reduction factors in the dataset. By incorporating EENFs, the DayCent ecosystem model is able to simulate a broader suite of options to identify best management practices for reducing N2O emissions. (C) 2021 Published by Elsevier B.V.
2021 DEC 20
WOS:000704389000020
journalArticle
287
CHEMOSPHERE
DOI 10.1016/j.chemosphere.2021.131889
Singh
Simranjit
Kasana
Singara Singh
Quantitative estimation of soil properties using hybrid features and RNN variants
Estimating soil properties is important for maximizing the production of crops in sustainable agriculture. The hyperspectral data next input depends upon the previous one, and the current techniques do not take advantage of this sequential nature of hyperspectral signatures. The variants of RNN can learn the short-term and long-term dependencies between data. This paper proposes a deep learning hybrid framework for quantifying the soil minerals like Clay, CEC, pH of H2O, Nitrogen, Organic Carbon, Sand of European Union from the LUCAS library. The hyperspectral signatures contain the data in the range of 400-2500 nm captured from the FOSS spectroscope in the laboratory. As hyperspectral data is high dimensional, Principal Component Analysis and Locality Preserving Projections are utilized to form the hybrid features, which have low dimensions containing the local and global information of the original dataset. These hybrid features are passed on to Long Short Term Memory Networks, a deep learning framework for building an effective prediction model. The effectiveness of the prepared models is demonstrated by comparing it to existing state-of-the-art techniques.
2022 JAN
WOS:000704764600002
journalArticle
16
PLOS ONE
DOI 10.1371/journal.pone.0256803
8
Forsman
Anders
De Moor
Tine
van Weeren
Rene
Farjam
Mike
Dehkordi
Molood Ale Ebrahim
Ghorbani
Amineh
Bravo
Giangiacomo
Comparisons of historical Dutch commons inform about the long-term dynamics of social-ecological systems
Human societies and natural ecosystems are under threat by growing populations, overexploitation of natural resources and climate change. This calls for more sustainable utilization of resources based on past experiences and insights from many different disciplines. Interdisciplinary approaches to studies of historical commons have potential to identify drivers of change and keys to success in the past, and offer advice about the management and use of shared resources in contemporary and future systems. We address these issues by applying an ecological perspective to historical data on social-ecological systems. We perform comparisons and time series analyses for nine successful Dutch commons for which high-resolution data on the regulatory activities and use of shared resources is available for on average 380 years (range 236 to 568) during the period 1300 to 1972. Within commons, institutional developments were oscillating, with periods of intense regulatory activity being separated by periods of low activity, and with the dynamics of regulations being largely independent across commons. Ecological theory posits that species that occupy similar niches should show correlated responses to environmental challenges; however, commons using more similar resources did not have more parallel or similar institutional developments. One notable exception was that sanctioning was more frequent in commons that directed more regulatory activities towards non-renewable subsoil resources, whereas there was no association between sanctioning and the use of renewable resources. This might indicate that commoners were aware of potential resource depletion and attempted to influence freeriding by actively trying to solve the underlying social dilemmas. Sanctioning regulations were more frequent during the first than during the second part of a common's life, indicating that while sanctioning might have been important for the establishment of commons it was not key to the long-term persistence of historical commons.
2021 AUG 27
WOS:000752313300045
journalArticle
18
INTERNATIONAL JOURNAL OF BEHAVIORAL NUTRITION AND PHYSICAL ACTIVITY
DOI 10.1186/s12966-021-01168-x
1
Seguin-Fowler
Rebecca A.
Hanson
Karla L.
Pitts
Stephanie B. Jilcott
Kolodinsky
Jane
Sitaker
Marilyn
Ammerman
Alice S.
Marshall
Grace A.
Belarmino
Emily H.
Garner
Jennifer A.
Wang
Weiwei
Community supported agriculture plus nutrition education improves skills, self-efficacy, and eating behaviors among low-income caregivers but not their children: a randomized controlled trial
Background: Adults and children in the U.S. consume inadequate quantities of fruit and vegetables (FV), in part, due to poor access among households with lower socioeconomic status. One approach to improving access to FV is community supported agriculture (CSA) in which households purchase a `share' of local farm produce throughout the growing season. This study examined the effects of cost-offset (half-price) CSA plus tailored nutrition education for low-income households with children.Methods: The Farm Fresh Foods for Healthy Kids (F3HK) randomized controlled trial in New York, North Carolina, Vermont, and Washington (2016-2018) assigned caregiver-child dyads (n = 305) into cost-offset CSA plus education intervention or control (delayed intervention) groups. Following one growing season of CSA participation, changes in children's diet quality, body mass index (BMI), and physical activity; caregivers' nutrition knowledge, attitudes, behaviors, and diet quality; and household food access and security were examined using multiple linear or logistic regression, with adjustment for baseline value within an intent-to-treat (ITT) framework in which missing data were multiply imputed.Results: No significant net effects on children's dietary intake, BMI, or physical activity were observed. Statistically significant net improvements were observed after one growing season for caregivers' cooking attitudes, skills, and self-efficacy; FV intake and skin carotenoid levels; and household food security. Changes in attitudes and selfefficacy remained one-year after baseline, but improvements in caregiver diet and household food security did not. The number of weeks that participants picked up a CSA share (but not number of education sessions attended) was associated with improvements in caregiver FV intake and household food security.Conclusions: Cost-offset CSA plus tailored nutrition education for low-income households improved important caregiver and household outcomes within just one season of participation; most notably, both self-reported and objectively measured caregiver FV intake and household food security improved. Households that picked up more shares also reported larger improvements. However, these changes were not maintained after the CSA season ended. These results suggest that cost-offset CSA is a viable approach to improving adult, but not child, FV intake and household food security for low-income families, but the seasonality of most CSAs may limit their potential to improve year-round dietary behavior and food security.
2021 AUG 31
WOS:000692410200001
journalArticle
802
SCIENCE OF THE TOTAL ENVIRONMENT
DOI 10.1016/j.scitotenv.2021.149960
Avadi
Angel
Galland
Victor
Versini
Antoine
Bockstaller
Christian
Suitability of operational N direct field emissions models to represent contrasting agricultural situations in agricultural LCA: Review and prospectus
N biogeochemical flows and associated N losses exceed currently planetary boundaries and represent a major threat for sustainability. Measuring N losses is a resource-intensive endeavour, and not suitable for ex-ante assessments, thus modelling is a common approach for estimating N losses associated with agricultural scenarios (systems, practices, situations). The aim of this study is to review some of the N models commonly used for estimating direct field emissions of agricultural systems, and to assess their suitability to systems featuring contrasted agricultural and pedoclimatic conditions.Simple N models were chosen based on their frequent use in LCA, including ecoinvent v3, Indigo-N v1/v2, AGRIBALYSE v1.2/v1.3, and the Mineral fertiliser equivalents (MFE) calculator. Model sets were contrasted, among them and with the dynamic crop model STICS, regarding their consideration of the biophysical processes determining N losses to the environment from agriculture, namely plant uptake, nitrification, denitrification, NH3 volatilisation, NO3 leaching, erosion and run-off, and N2O emission to air; using four reference agricultural datasets. Models' consideration of management drivers such as crop rotations and the allocation of fertilisers and emissions among crops in a crop rotation, over-fertilisation and fertilisation technique, were also contrasted, as well as their management of the mineralisation of soil organic matter and organic fertilisers, and of drainage regimes.For the four agricultural datasets, the ecoinvent model predicted significantly lower values for NH3 than AGRIBALYSE and STICS. For N2O, no significant differences were found among models. For NO3, ecoinvent and AGRIBALYSE predicted significantly higher emissions than STICS. regardless of the fertilisation regime. For both emissions, values of Indigo-N were close to those of STICS. By analysing the reasons for such differences, and the underlying factors considered by models, a list of recommendations was produced regarding more accurate ways to model N losses (e.g. by including the main drivers regulating emissions). (C) 2021 Elsevier B.V. All rights reserved.
2022 JAN 1
WOS:000701774600003
journalArticle
135
WASTE MANAGEMENT
DOI 10.1016/j.wasman.2021.08.035
Aleisa
Esra
Alsulaili
Abdalrahman
Almuzaini
Yasmeen
Recirculating treated sewage sludge for agricultural use: Life cycle assessment for a circular economy
The objective of this study is to assess the environmental value of recirculating nutrients from treated sewage sludge by application to agricultural soils to grow forage as opposed to landfilling and incineration. The methodological choices are aligned to the circular economy framework using life cycle assessment. Consequential modeling and open loop modeling were adopted and adhere to ISO 14044 and International Reference Life Cycle Data System (ILCD) standards. The functional unit is defined in terms of the amounts of nitrogen (N), phosphorus (P) and potassium (K) recirculated from the treated sewage sludge produced annually in Kuwait. The results indicate a reduction in environmental burden with respect to fossil fuel depletion, metal depletion and climate change. A total of 95% of the reduction is realized by avoiding virgin nitrogen production and instead using its recirculated counterpart. Considerable amounts of natural gas, coal, dinitrogen monoxide (nitrous oxide, N2O) and copper are consumed during virgin N fertilizer production.
2021 NOV
WOS:000700578500004
79-89
journalArticle
21
SENSORS
DOI 10.3390/s21175949
17
Mateo-Fornes
Jordi
Pages-Bernaus
Adela
Pla-Aragones
Lluis Miquel
Castells-Gasia
Joan Pau
Babot-Gaspa
Daniel
An Internet of Things Platform Based on Microservices and Cloud Paradigms for Livestock
With the growing adoption of the Internet of Things (IoT) technology in the agricultural sector, smart devices are becoming more prevalent. The availability of new, timely, and precise data offers a great opportunity to develop advanced analytical models. Therefore, the platform used to deliver new developments to the final user is a key enabler for adopting IoT technology. This work presents a generic design of a software platform based on the cloud and implemented using microservices to facilitate the use of predictive or prescriptive analytics under different IoT scenarios. Several technologies are combined to comply with the essential features-scalability, portability, interoperability, and usability-that the platform must consider to assist decision-making in agricultural 4.0 contexts. The platform is prepared to integrate new sensor devices, perform data operations, integrate several data sources, transfer complex statistical model developments seamlessly, and provide a user-friendly graphical interface. The proposed software architecture is implemented with open-source technologies and validated in a smart farming scenario. The growth of a batch of pigs at the fattening stage is estimated from the data provided by a level sensor installed in the silo that stores the feed from which the animals are fed. With this application, we demonstrate how farmers can monitor the weight distribution and receive alarms when high deviations happen.
2021 SEP
WOS:000694539800001
journalArticle
21
SENSORS
DOI 10.3390/s21175836
17
Khorramifar
Ali
Rasekh
Mansour
Karami
Hamed
Malaga-Tobola
Urszula
Gancarz
Marek
A Machine Learning Method for Classification and Identification of Potato Cultivars Based on the Reaction of MOS Type Sensor-Array
In response to one of the most important challenges of the century, i.e., the estimation of the food demands of a growing population, advanced technologies have been employed in agriculture. The potato has the main contribution to people's diet worldwide. Therefore, its different aspects are worth studying. The large number of potato varieties, lack of awareness about its new cultivars among farmers to cultivate, time-consuming and inaccurate process of identifying different potato cultivars, and the significance of identifying potato cultivars and other agricultural products (in every food industry process) all necessitate new, fast, and accurate methods. The aim of this study was to use an electronic nose, along with chemometrics methods, including PCA, LDA, and ANN as fast, inexpensive, and non-destructive methods for detecting different potato cultivars. In the present study, nine sensors with the best response to VOCs were adopted. VOCs sensors were used at various VOCs concentrations (1 to 10,000 ppm) to detect different gases. The results showed that a PCA with two main components, PC1 and PC2, described 92% of the total samples' dataset variance. In addition, the accuracy of the LDA and ANN methods were 100 and 96%, respectively.
2021 SEP
WOS:000694466700001
journalArticle
16
PLOS ONE
DOI 10.1371/journal.pone.0256913
9
Grebitus
Carola
Small-scale urban agriculture: Drivers of growing produce at home and in community gardens in Detroit
The desire for fresh, local food has increased interest in alternative food production approaches, such as private small-scale agriculture, wherein households grow their own food. Accordingly, it is worth investigating private agricultural production, especially in urban areas, given that an increasing share of the world's population is living in cities. This study analyzed the growth of produce at people's homes and in community gardens, focusing on behavioral and socio-demographic factors. Data were collected through an online survey in Detroit, Michigan; 420 citizens were interviewed. The results revealed that trust, attitude, and knowledge affect the growing of produce at home. Involvement and personality are also drivers of community gardening. Regarding socio-demographics, household size affects the growing of produce at home, while gender, age, and income affect community gardening. The findings have valuable implications for stakeholders who wish to foster private small-scale urban agriculture, for example, through city planning and nutrition education.
2021 SEP 7
WOS:000707070200045
journalArticle
51
JOURNAL OF ENVIRONMENTAL QUALITY
DOI 10.1002/jeq2.20271
4
Booth
Eric G.
Kucharik
Christopher J.
Data inaccessibility at sub-county scale limits implementation of manuresheds
The manureshed concept aims to rebalance surplus manure nutrients produced at animal feeding operations (sources) and the demands from nutrient-deficient croplands (sinks) to reduce negative environmental impacts and utilize nutrients more efficiently. Due to water quality implications, studies focused on this rebalancing have typically created domain boundaries that match a particular watershed. However, a majority of agricultural datasets that are used to inform these analyses-specifically, livestock populations-are only available at the county scale, which generally does not match watershed boundaries. The common method used to address this mismatch is to weight the county statistics based on the proportion of watershed area within the county. However, these straightforward assumptions imply that animal density is uniform across a county, which can be highly problematic, especially in an era of increasing concentration of livestock production on a smaller land area. We present a case study of the Lake Mendota watershed in south-central Wisconsin using both a typical county-based downscaled dataset as well as a more spatially explicit dataset of livestock counts from the Census of Agriculture that aggregates a set of zip codes that best matches the watershed boundary. This comparison reveals a substantial difference in estimated livestock numbers and their associated manure production that is due to a concentration of dairy operations within the watershed compared with the rest of the county. We argue that sub-county scale data need to become more available and integrated into nutrient and water quality management efforts so that manuresheds can be more effectively delineated and implemented.
2022 JUL
WOS:000693687500001
614-621
journalArticle
300
JOURNAL OF ENVIRONMENTAL MANAGEMENT
DOI 10.1016/j.jenvman.2021.113698
Zhang
Lu
Ruiz-Menjivar
Jorge
Tong
Qingmeng
Zhang
Junbiao
Yue
Meng
Examining the carbon footprint of rice production and consumption in Hubei, China: A life cycle assessment and uncertainty analysis approach
This study aimed to quantify greenhouse gas emissions derived from the production-consumption of rice in Hubei-a major rice-producing province in central China. This research employed primary and secondary data collection methods. Primary data sources included interviews and experimental observations from seven counties in Hubei collected from June 2016 to December 2016. Secondary data sources-including national datasets, inter-governmental reports, and peer-reviewed articles-were used to extract relevant data, such as emission factors, and national and provincial rice output. Life Cycle Assessment was employed to build a comprehensive inventory and map of the rice carbon footprint, including the following five stages: production inputs, farm management, growth period, processing and sale, and consumption. Uncertainty analysis was performed to validate the reliability of carbon footprint estimations. Results showed that the carbon footprint for every 1 ton of polished rice in Hubei ranged between 4.19-6.81 t CO2e/t and was 5.39 t CO2e/t on average. Greenhouse gas emissions were primarily produced from rice fields during the growth stage (over 60% of greenhouse gas emissions of the whole life cycle of rice), followed by the consumption stage, and the production and transportation of agricultural inputs. Uncertainty analysis estimations indicated acceptable levels of reliability. This study's results indicate that the production and consumption of rice is a significant contributor to agricultural carbon emissions in Hubei-consistent with national estimates that place China as the largest carbon dioxide emitter globally. This research provides further insight into future policies and targeted initiatives for the efficient use of low-carbon agricultural inputs for rice production and consumption stages in China.
2021 DEC 15
WOS:000704765000007
journalArticle
66
ANNALS OF WORK EXPOSURES AND HEALTH
DOI 10.1093/annweh/wxab083
3
Petit
Pascal
Bosson-Rieutort
Delphine
Maugard
Charlotte
Gondard
Elise
Ozenfant
Damien
Joubert
Nadia
Francois
Olivier
Bonneterre
Vincent
The TRACTOR Project: TRACking and MoniToring Occupational Risks in Agriculture Using French Insurance Health Data (MSA)
Objectives A vast data mining project called 'TRACking and moniToring Occupational Risks in agriculture' (TRACTOR) was initiated in 2017 to investigate work-related health events among the entire French agricultural workforce. The goal of this work is to present the TRACTOR project, the challenges faced during its implementation, to discuss its strengths and limitations and to address its potential impact for health surveillance. Methods Three routinely collected administrative health databases from the National Health Insurance Fund for Agricultural Workers and Farmers (MSA) were made available for the TRACTOR project. Data management was required to properly clean and prepare the data before linking together all available databases. Results After removing few missing and aberrant data (4.6% values), all available databases were fully linked together. The TRACTOR project is an exhaustive database of agricultural workforce (active and retired) from 2002 to 2016, with around 10.5 million individuals including seasonal workers and farm managers. From 2012 to 2016, a total of 6 906 290 individuals were recorded. Half of these individuals were active and 46% had at least one health event (e.g. declared chronic disease, reimbursed drug prescription) during this 5-year period. Conclusions The assembled MSA databases available in the TRACTOR project are regularly updated and represent a promising and unprecedent dataset for data mining analysis dedicated to the early identification of current and emerging work-related illnesses and hypothesis generation. As a result, this project could help building a prospective integrated health surveillance system for the benefit of agricultural workers.
2022 MAR 15
WOS:000756682000001
402-411
journalArticle
805
SCIENCE OF THE TOTAL ENVIRONMENT
DOI 10.1016/j.scitotenv.2021.150441
Fan
Bingqian
Wang
Hongyuan
Zhai
Limei
Li
Jungai
Fenton
Owen
Daly
Karen
Lei
Qiuliang
Wu
Shuxia
Liu
Hongbin
Leached phosphorus apportionment and future management strategies across the main soil areas and cropping system types in northern China
Excess phosphorus (P) leached from high fertiliser input cropping systems in northern China is having detrimental effects on water quality. Before improved management can be directed at specific soils and cropping system types estimates of P leached loss apportionment and mitigation potentials across the main soil (fluvo-aquic soil, FAS; cinnamon soil, CS; black soil, BS) areas and cropping systems (protected vegetable fields, PVFs; open vegetable fields, OVFs; cereal fields, CFs) are needed. The present study designed and implemented conventional fertilisation and low input system trials at 75 sites inclusive of these main soils and cropping system types in northern China. At all sites, a uniform lysimeter design (to 0.9 m depth) enabled the collection and analysis of leachate samples from 7578 individual events between 2008 and 2018. In addition, site-specific static and dynamic activity data were recorded. Results showed that annual total phosphorus (TP) leached losses across the main soil areas and cropping systems were 4.99 x 10(6) kg in northern China. A major finding was PVFs contributed to 48.5% of the TP leached losses but only accounted for 5.7% of the total cropping areas. The CFs and OVFs accounted for 40.3% and 11.2% of the TP leached losses, respectively. Across northern China, the TP leached losses in PVFs and OVFs were greatest in FAS areas followed by CS and BS areas. The higher TP leached losses in FAS areas were closely correlated with greater P fertiliser inputs and irrigation practices. From a management perspective in PVFs and OVFs systems, a decrease of P inputs by 10-30% would not negatively affect yields while protecting water quality. The present study highlights the importance of decreasing P inputs in PVFs and OVFs and supporting soil P nutrient advocacy for farmers in China. (C) 2021 Elsevier B.V. All rights reserved.
2022 JAN 20
WOS:000701753200002
journalArticle
27
GLOBAL CHANGE BIOLOGY
DOI 10.1111/gcb.15884
24
Hergoualc'h
Kristell
Mueller
Nathan
Bernoux
Martial
Kasimir
Asa
Weerden
Tony J.
Ogle
Stephen M.
Improved accuracy and reduced uncertainty in greenhouse gas inventories by refining the IPCC emission factor for direct N2O emissions from nitrogen inputs to managed soils
Most national GHG inventories estimating direct N2O emissions from managed soils rely on a default Tier 1 emission factor (EF1) amounting to 1% of nitrogen inputs. Recent research has, however, demonstrated the potential for refining the EF1 considering variables that are readily available at national scales. Building on existing reviews, we produced a large dataset (n = 848) enriched in dry and low latitude tropical climate observations as compared to former global efforts and disaggregated the EF1 according to most meaningful controlling factors. Using spatially explicit N fertilizer and manure inputs, we also investigated the implications of using the EF1 developed as part of this research and adopted by the 2019 IPCC refinement report. Our results demonstrated that climate is a major driver of emission, with an EF1 three times higher in wet climates (0.014, 95% CI 0.011-0.017) than in dry climates (0.005, 95% CI 0.000-0.011). Likewise, the form of the fertilizer markedly modulated the EF1 in wet climates, where the EF1 for synthetic and mixed forms (0.016, 95% CI 0.013-0.019) was also almost three times larger than the EF1 for organic forms (0.006; 95% CI 0.001-0.011). Other factors such as land cover and soil texture, C content, and pH were also important regulators of the EF1. The uncertainty associated with the disaggregated EF1 was considerably reduced as compared to the range in the 2006 IPCC guidelines. Compared to estimates from the 2006 IPCC EF1, emissions based on the 2019 IPCC EF1 range from 15% to 46% lower in countries dominated by dry climates to 7%-37% higher in countries with wet climates and high synthetic N fertilizer consumption. The adoption of the 2019 IPCC EF1 will allow parties to improve the accuracy of emissions' inventories and to better target areas for implementing mitigation strategies.
2021 DEC
WOS:000698988600001
6536-6550
journalArticle
31
ECOLOGICAL APPLICATIONS
DOI 10.1002/eap.2447
8
D'Amario
Sarah C.
Wilson
Henry F.
Xenopoulos
Marguerite A.
Concentration-discharge relationships derived from a larger regional dataset as a tool for watershed management
Concentration-discharge (C-Q) relationships have been widely used to assess the hydrochemical processes that control solute fluxes from streams. Here, using a large regional dataset we assessed long-term C-Q relationships for total phosphorus (TP), soluble reactive phosphorus (SRP), total Kjeldahl nitrogen (TKN), and nitrate (NO3) for 63 streams in Ontario, Canada, to better understand seasonal regional behavior of nutrients. We used C-Q plots, Kruskal-Wallis tests, and breakpoint analysis to characterize overall regional nutrient C-Q relationships and assess seasonal effects, anthropogenic impacts, and differences between "rising" and "falling" hydrograph limbs to gain an understanding of the dominant processes controlling overall C-Q relationships. We found that all nutrient concentrations were higher on average in catchments with greater levels of anthropogenic disturbance (agricultural and urban land use). TP, SRP, and TKN showed similar C-Q dynamics, with nearly flat or gently sloping C-Q relationships up to a discharge threshold after which C-Q slopes substantially increased during the rising limb. These thresholds were seasonally variable, with summer and winter thresholds occurring at lower flows compared with autumn and greater variability during snowmelt. These patterns suggest that seasonal strategies to reduce high flows, such as creating riparian wetlands or reservoirs, in conjunction with reducing related nutrient transport during high flows would be the most effective way to mitigate elevated in-stream concentrations and event export. Elevated rising limb concentrations suggest that nutrients accumulate in upland parts of the catchment during drier periods and that these are released during rain events. NO3 C-Q patterns tended to be different from the other nutrients and were further complicated by anthropogenic land use, with greater reductions on the falling limb in more disturbed catchments during certain seasons. There were few significant NO3 hydrograph limb differences, indicating that there was likely to be no dominant hysteretic pattern across our study region due to variability in hysteresis from catchment to catchment. This suggests that this nutrient may be difficult to successfully manage at the regional scale.
2021 DEC
WOS:000701231700001
journalArticle
806
SCIENCE OF THE TOTAL ENVIRONMENT
DOI 10.1016/j.scitotenv.2021.150308
Zaldo-Aubanell
Quim
Serra
Isabel
Bach
Albert
Knobel
Pablo
i Lopez
Ferran Campillo
Belmonte
Jordina
Daunis-I-Estadella
Pepus
Maneja
Roser
Environmental heterogeneity in human health studies. A compositional methodology for Land Use and Land cover data
The use of Land use and Land cover (LULC) data is gradually becoming more widely spread in studies relating the environment to human health. However, little research has acknowledged the compositional nature of these data. The goal of the present study is to explore, for the first time, the independent effect of eight LULC categories (agricultural land, bare land, coniferous forest, broad-leaved forest, sclerophyll forest, grassland and shrubs, urban areas, and waterbodies) on three selected common health conditions: type 2 diabetes mellitus (T2DM), asthma and anxiety, using a compositional methodological approach and leveraging observational health data of Catalonia (Spain) at area level. We fixed the risk exposure scenario using three covariates (socioeconomic status, age group, and sex). Then, we assessed the independent effect of the eight LULC categories on each health condition. Our results show that each LULC category has a distinctive effect on the three health conditions and that the three covariates clearly modify this effect. This compositional approach has yielded plausible results supported by the existing literature, highlighting the relevance of environmental heterogeneity in health studies. In this sense, we argue that different types of envi-ronment possess exclusive biotic and abiotic elements affecting distinctively on human health. We believe our contribution might help researchers approach the environment in a more multidimensional man-ner integrating environmental heterogeneity in the analysis. (c) 2021 The Authors. Published by Elsevier B.V. This is an open access article under the CC BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/).
2022 FEB 1
WOS:000709731100015
journalArticle
21
SENSORS
DOI 10.3390/s21206705
20
Farkhani
Sadaf
Skovsen
Soren Kelstrup
Dyrmann
Mads
Jorgensen
Rasmus Nyholm
Karstoft
Henrik
Weed Classification Using Explainable Multi-Resolution Slot Attention
In agriculture, explainable deep neural networks (DNNs) can be used to pinpoint the discriminative part of weeds for an imagery classification task, albeit at a low resolution, to control the weed population. This paper proposes the use of a multi-layer attention procedure based on a transformer combined with a fusion rule to present an interpretation of the DNN decision through a high-resolution attention map. The fusion rule is a weighted average method that is used to combine attention maps from different layers based on saliency. Attention maps with an explanation for why a weed is or is not classified as a certain class help agronomists to shape the high-resolution weed identification keys (WIK) that the model perceives. The model is trained and evaluated on two agricultural datasets that contain plants grown under different conditions: the Plant Seedlings Dataset (PSD) and the Open Plant Phenotyping Dataset (OPPD). The model represents attention maps with highlighted requirements and information about misclassification to enable cross-dataset evaluations. State-of-the-art comparisons represent classification developments after applying attention maps. Average accuracies of 95.42% and 96% are gained for the negative and positive explanations of the PSD test sets, respectively. In OPPD evaluations, accuracies of 97.78% and 97.83% are obtained for negative and positive explanations, respectively. The visual comparison between attention maps also shows high-resolution information.
2021 OCT
WOS:000778244000001
journalArticle
21
SENSORS
DOI 10.3390/s21206910
20
Angarita-Zapata
Juan S.
Alonso-Vicario
Ainhoa
Masegosa
Antonio D.
Legarda
Jon
A Taxonomy of Food Supply Chain Problems from a Computational Intelligence Perspective
In the last few years, the Internet of Things, and other enabling technologies, have been progressively used for digitizing Food Supply Chains (FSC). These and other digitalization-enabling technologies are generating a massive amount of data with enormous potential to manage supply chains more efficiently and sustainably. Nevertheless, the intricate patterns and complexity embedded in large volumes of data present a challenge for systematic human expert analysis. In such a data-driven context, Computational Intelligence (CI) has achieved significant momentum to analyze, mine, and extract the underlying data information, or solve complex optimization problems, striking a balance between productive efficiency and sustainability of food supply systems. Although some recent studies have sorted the CI literature in this field, they are mainly oriented towards a single family of CI methods (a group of methods that share common characteristics) and review their application in specific FSC stages. As such, there is a gap in identifying and classifying FSC problems from a broader perspective, encompassing the various families of CI methods that can be applied in different stages (from production to retailing) and identifying the problems that arise in these stages from a CI perspective. This paper presents a new and comprehensive taxonomy of FSC problems (associated with agriculture, fish farming, and livestock) from a CI approach; that is, it defines FSC problems (from production to retail) and categorizes them based on how they can be modeled from a CI point of view. Furthermore, we review the CI approaches that are more commonly used in each stage of the FSC and in their corresponding categories of problems. We also introduce a set of guidelines to help FSC researchers and practitioners to decide on suitable families of methods when addressing any particular problems they might encounter. Finally, based on the proposed taxonomy, we identify and discuss challenges and research opportunities that the community should explore to enhance the contributions that CI can bring to the digitization of the FSC.
2021 OCT
WOS:000714722900001
journalArticle
18
INTEGRATED ENVIRONMENTAL ASSESSMENT AND MANAGEMENT
DOI 10.1002/ieam.4518
3
Aydogan
Mehmet
Demiryurek
Kursat
Ozer
Osman Orkan
Uysal
Osman
Factors accelerating agricultural innovation and sustainability: The case of paddy farmers
The primary purpose of this study is to reveal the factors accelerating both the innovativeness and sustainability levels of paddy farmers. The data used in the study were obtained from the questionnaires conducted with 70 paddy farmers in the Bafra district of Samsun province, Turkey, determined by a simple random sampling method. Paddy farmers were divided into three groups as low, medium, and high innovativeness groups with hierarchical cluster analysis. An ANOVA was used to compare the socioeconomic and farming characteristics of the paddy farmers, and accelerated failure time models were used to analyze the factors affecting the innovativeness and sustainability variables. The research results indicated that the number of years of formal education, the agricultural experience, the amount of labor per unit area, the animal assets, the share of agricultural income in the total income, the number of memberships to farmer organizations, paddy production area, sustainable agriculture area, and cooperation scores differed from the innovativeness groups. The farmers' collaboration in agricultural activities increased the likelihood that they are an innovator. The results concluded that the number of years of formal education, global good agriculture practice, agricultural experience, household size, animal assets, and women's employment influenced both the innovativeness and sustainability variables. Encouraging the participation of women in agricultural production in rural areas, including sustainability-related issues in addition to technical issues in farmer training programs, and ensuring the participation of women in such training are issues that should be considered in future. Integr Environ Assess Manag 2021;00:1-12. (c) 2021 SETAC
2022 MAY
WOS:000703659700001
824-835
journalArticle
27
GLOBAL CHANGE BIOLOGY
DOI 10.1111/gcb.15897
24
Rodrigues
Leonor
Hardy
Brieuc
Huyghebeart
Bruno
Fohrafellner
Julia
Fornara
Dario
Barancikova
Gabriela
Barcena
Teresa G.
De Boever
Maarten
Di Bene
Claudia
Feiziene
Dalia
Kaetterer
Thomas
Laszlo
Peter
O'Sullivan
Lilian
Seitz
Daria
Leifeld
Jens
Achievable agricultural soil carbon sequestration across Europe from country-specific estimates
The role of soils in the global carbon cycle and in reducing GHG emissions from agriculture has been increasingly acknowledged. The '4 per 1000' (4p1000) initiative has become a prominent action plan for climate change mitigation and achieve food security through an annual increase in soil organic carbon (SOC) stocks by 0.4%, (i.e. 4 parts per thousand per year). However, the feasibility of the 4p1000 scenario and, more generally, the capacity of individual countries to implement soil carbon sequestration (SCS) measures remain highly uncertain. Here, we evaluated country-specific SCS potentials of agricultural land for 24 countries in Europe. Based on a detailed survey of available literature, we estimate that between 0.1% and 27% of the agricultural greenhouse gas (GHG) emissions can potentially be compensated by SCS annually within the next decades. Measures varied widely across countries, indicating differences in country-specific environmental conditions and agricultural practices. None of the countries' SCS potential reached the aspirational goal of the 4p1000 initiative, suggesting that in order to achieve this goal, a wider range of measures and implementation pathways need to be explored. Yet, SCS potentials exceeded those from previous pan-European modelling scenarios, underpinning the general need to include national/regional knowledge and expertise to improve estimates of SCS potentials. The complexity of the chosen SCS measurement approaches between countries ranked from tier 1 to tier 3 and included the effect of different controlling factors, suggesting that methodological improvements and standardization of SCS accounting are urgently required. Standardization should include the assessment of key controlling factors such as realistic areas, technical and practical feasibility, trade-offs with other GHG and climate change. Our analysis suggests that country-specific knowledge and SCS estimates together with improved data sharing and harmonization are crucial to better quantify the role of soils in offsetting anthropogenic GHG emissions at global level.
2021 DEC
WOS:000704117400001
6363-6380
journalArticle
806
SCIENCE OF THE TOTAL ENVIRONMENT
DOI 10.1016/j.scitotenv.2021.150718
Viana
Claudia M.
Freire
Dulce
Abrantes
Patricia
Rocha
Jorge
Pereira
Paulo
Agricultural land systems importance for supporting food security and sustainable development goals: A systematic review
Agriculture provides the largest share of food supplies and ensures a critical number of ecosystem services (e.g., food provisioning). Therefore, agriculture is vital for food security and supports the Sustainable Development Goal (SDGs) 2 (SDG 2 -zero hunger) as others SDG's. Several studies have been published in different world areas with different research directions focused on increasing food and nutritional security from an agricultural land system perspective. The heterogeneity of the agricultural research studies calls for an interdisciplinary and comprehensive systematization of the different research directions and the plethora of approaches, scales of analysis, and reference data used. Thus, this work aims to systematically review the contributions of the different agricultural research studies by systematizing the main research fields and present a synthesis of the diversity and scope of research and knowledge. From an initial search of 1151 articles, 260 meet the criteria to be used in the review. Our analysis revealed that most articles were published between 2015 and 2019 (59%), and most of the case studies were carried out in Asia (36%) and Africa (20%). The number of studies carried out in the other continents was lower. In the last 30 years, most of the research was centred in six main research fields: land-use changes (28%), agricultural efficiency (27%), climate change (16%), farmer's motivation (12%), urban and peri-urban agriculture (11%), and land suitability (7%). Overall, the research fields identified are directly or indirectly linked to 11 of the 17 SDGs. There are essential differences in the number of articles among research fields, and future efforts are needed in the ones that are less represented to support food security and the SDGs. (c) 2021 The Authors. Published by Elsevier B.V. This is an open access article under the CC BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/).
2022 FEB 1
WOS:000707655700011
journalArticle
206
WATER RESEARCH
DOI 10.1016/j.watres.2021.117693
Roberts
William M.
Couldrick
Laurence B.
Williams
Gareth
Robins
Dawn
Cooper
Dave
Mapping the potential for Payments for Ecosystem Services schemes to improve water quality in agricultural catchments: A multi-criteria approach based on the supply and demand concept
Payments for Ecosystem Services (PES) schemes are an increasingly popular form of catchment management for improving surface water and groundwater quality. In these schemes, downstream water users who are impacted by agricultural diffuse pollution incentivise upstream farmers to adopt better practices. However, this type of scheme will not be successful in all situations, in part, due to a lack of potential for agriculture to improve the suuply of good water quality and/or a lack in demand from downstream users for good water quality. As such, this study aims to present a flexible approach to mapping the potential for PES schemes to improve water quality in agricultural catchments. The approach is based on multi-criteria analysis, with supply and demand as key criteria. It uses expert judgement or current guidance on PES to select supply and demand sub-criteria, expert judgement to weight all criteria through pairwise comparisons and readily available, national datasets to indicate criteria. Once indicator data are normalized, it combines them in a weighted sums analysis and presents results spatially at the national scale, all within a geographical information system. The approach can easily be applied to the country or region of interest by using locally relevant criteria, expert judgement and data. For example, when applied to the situation for river waterbodies in England, supply sub-criteria were the contribution of agriculture to loads of the major pollutants (nitrogen, phosphorus and sediments) and demand sub-criteria were the different downstream water users present (water companies and, tourist and local recreational users). Experts assigned equal weight to supply and demand criteria and the highest weights to sediments and water companies for sub-criteria, respectively. When national scale datasets to indicate these criteria were combined in a weighted sums analysis, it was possible to identify areas of high potential for PES. This would hopefully motivate more detailed research at the individual catchment level into the constraints in linking supply and demand. Three case -study schemes were also examined to show how some of these constraints are being identified and overcome. As such, the approach forms the first tier in a two-tier framework for establishing PES schemes to improve water quality in agricultural catchments.
2021 NOV 1
WOS:000713194100003
journalArticle
114
JOURNAL OF ECONOMIC ENTOMOLOGY
DOI 10.1093/jee/toab192
6
Maino
James L.
Cushen
Alexander
Valavi
Roozbeh
Umina
Paul A.
Spatial Variation in Australian Neonicotinoid Usage and Priorities for Resistance Monitoring
Australia is the third largest exporting country of cereals and a leader in other major commodity crops, yet little data exist on pesticide usage patterns in agriculture. This knowledge gap limits the management of off-target chemical impacts, such as the evolution of pesticide resistance. Here, for the first time, we quantify spatial patterns in neonicotinoid applications in Australia by coalescing land use data with sales and market research data contributed by agrichemical and agribusiness companies. An example application to resistance management is explored through the development of recommendations for the cosmopolitan crop pest, Myzus persicae (Sulzer) (Hemiptera: Aphididae), utilizing spatial statistical models. This novel dataset identified Australian neonicotinoid usage patterns, with most neonicotinoid products in Australia applied as cereal, canola, cotton and legume seed treatments and soil applications in sugarcane. Importantly, there were strong regional differences in pesticide applications, which will require regionally specific strategies to manage off-target impacts. Indeed, the estimated spatial grid of neonicotinoid usage demonstrated a statistically significant influence on the distribution of M. persicae neonicotinoid resistance, indicating off-target impacts are unevenly distributed in space. Future research on neonicotinoid usage will be supported by the spatial grids generated and made available through this study. Overall, neonicotinoid pesticides are widely relied upon throughout Australia's plant production systems but will face increasing pressure from resistance evolution, emerging research on off-target impacts, and stricter regulatory pressures.
2021 DEC
WOS:000733374100032
2524-2533
journalArticle
50
JOURNAL OF ENVIRONMENTAL QUALITY
DOI 10.1002/jeq2.20288
6
Gray
Colin William
Cavanagh
Jo-Anne Elizabeth
Prediction of soil solution concentrations and leaching losses of cadmium in agricultural soils
Cadmium (Cd) leaching is often estimated in Cd balance models using the product of drainage water (precipitation excess) and soil solution Cd concentration. However, Cd concentrations are seldom available but rather predicted using empirical models. Despite the availability of empirical models that estimate soil solution Cd concentrations, they have limitations for use in New Zealand where total Cd in agricultural soils is low and organic matter (OM) high. This study derived a Freundlich-type model from desorption data and a soil-liquid partitioning coefficient (K-D) model based on sorption data to predict soil solution Cd concentrations from commonly measured soil parameters that could be used to calculate Cd leaching fluxes. Independent soil solution Cd concentrations and Cd fluxes measured in drainage water from field trials were used to validate the predictive capacity of the models. It was found that soil pH and OM content were the most important factors controlling soil solution Cd, along with total Cd. Both models explained 83% of the variation in measured soil solution Cd concentrations in an independent dataset. Comparisons between Cd fluxes predicted using the Freundlich-type model and measured fluxes were within 25% of each other at 6 of 19 field sites studied. However, physical and chemical nonequilibrium conditions in soils and uncertainty in measured values likely contributed to differences between predicted and measured Cd fluxes at other sites. To unravel the impact of nonequilibrium and soil physical conditions on Cd concentrations in drainage water, more data are required on Cd concentrations collected under field conditions. This will allow better validation of the approach used in Cd balance models to calculate Cd leaching from soils.
2021 NOV
WOS:000705546000001
1464-1475
journalArticle
11
SCIENTIFIC REPORTS
DOI 10.1038/s41598-021-99343-4
1
Naqvi
Asjad
Monasterolo
Irene
Assessing the cascading impacts of natural disasters in a multi-layer behavioral network framework
Natural disasters negatively impact regions and exacerbate socioeconomic vulnerabilities. While the direct impacts of natural disasters are well understood, the channels through which these shocks spread to non-affected regions, still represents an open research question. In this paper we propose modelling socioeconomic systems as spatially-explicit, multi-layer behavioral networks, where the interplay of supply-side production, and demand-side consumption decisions, can help us understand how climate shocks cascade. We apply this modelling framework to analyze the spatial-temporal evolution of vulnerability following a negative food-production shock in one part of an agriculture-dependent economy. Simulation results show that vulnerability is cyclical, and its distribution critically depends on the network density and distance from the epicenter of the shock. We also introduce a new multi-layer measure, the Vulnerability Rank (VRank), which synthesizes various location-level risks into a single index. This framework can help design policies, aimed to better understand, effectively respond, and build resilience to natural disasters. This is particularly important for poorer regions, where response time is critical and financial resources are limited.
2021 OCT 11
WOS:000706395800092
journalArticle
16
PLOS ONE
DOI 10.1371/journal.pone.0258991
10
DuPont
Sara Tianna
Kalcsits
Lee
Kogan
Clark
Soil health indicators for Central Washington orchards
Soil health assessment can be a critical soil testing tool that includes biological and physical indicators of soil function related to crop and environmental health. Soil health indicator minimum data sets should be regional and management goal specific. The objective of this study was to initiate the steps to develop a soil assessment tool for irrigated orchard soils in Central Washington, United States including defining objectives, gathering baseline data and selecting target indicators. This study measured twenty-one biological, physical and chemical properties of soils in irrigated Central Washington apple orchards including indicators of water availability, root health, fertility, and biological activity. Soil factors were related to fruit yield and quality. Principal components and nonlinear Bayesian modeling were used to explore the relationship between soil health indicators and yield. Soil indicators measurements in Washington state orchards varied widely but generally had lower organic matter, available water capacity, wet aggregate stability and higher percent sand than in other regions. Linear mixed effects models for available water capacity and percent sand showed significant effects on yield, and models for root health ratings and Pratylenchus nematodes had moderate effects. The minimum dataset of soil health indicators for Central Washington orchards should include measurements of water availability (available water capacity, percent sand) and of root health (bean root health rating, Pratylenchus nematodes) in addition to standard fertility indicators to meet stakeholder management goals.
2021 OCT 28
WOS:000755563200054
journalArticle
374
SCIENCE
DOI 10.1126/science.abe4943
6567
Farrell
Justin
Burow
Paul Berne
McConnell
Kathryn
Bayham
Jude
Whyte
Kyle
Koss
Gal
Effects of land dispossession and forced migration on Indigenous peoples in North America
What are the full extent and long-term effects of land dispossession and forced migration for Indigenous peoples in North America? We leveraged a new dataset of Indigenous land dispossession and forced migration to statistically compare features of historical tribal lands to present-day tribal lands at the aggregate and individual tribe level. Results show a near-total aggregate reduction of Indigenous land density and spread. Indigenous peoples were forced to lands that are more exposed to climate change risks and hazards and are less likely to lie over valuable subsurface oil and gas resources. Agricultural suitability and federal land proximity results-which affect Indigenous movements, management, and traditional uses-are mixed. These findings have substantial policy implications related to heightened climate vulnerability, extensive land reduction, and diminished land value.
2021 OCT 29
WOS:000714943400032
journalArticle
21
SENSORS
DOI 10.3390/s21227502
22
Zhang
Rihong
Li
Xiaomin
Edge Computing Driven Data Sensing Strategy in the Entire Crop Lifecycle for Smart Agriculture
In the context of smart agriculture, high-value data sensing in the entire crop lifecycle is fundamental for realizing crop cultivation control. However, the existing data sensing methods are deficient regarding the sensing data value, poor data correlation, and high data collection cost. The main problem for data sensing over the entire crop lifecycle is how to sense high-value data according to crop growth stage at a low cost. To solve this problem, a data sensing framework was developed by combining edge computing with the Internet of Things, and a novel data sensing strategy for the entire crop lifecycle is proposed in this paper. The proposed strategy includes four phases. In the first phase, the crop growth stage is divided by Gath-Geva (GG) fuzzy clustering, and the key growth parameters corresponding to the growth stage are extracted. In the second phase, based on the current crop growth information, a prediction method of the current crop growth stage is constructed by using a Tkagi-Sugneo (T-S) fuzzy neural network. In the third phase, based on Deng's grey relational analysis method, the environmental sensing parameters of the corresponding crop growth stage are optimized. In the fourth phase, an adaptive sensing method of sensing nodes with effective sensing area constraints is established. Finally, based on the actual crop growth history data, the whole crop life cycle dataset is established to test the performance and prediction accuracy of the proposed method for crop growth stage division. Based on the historical data, the simulation data sensing environment is established. Then, the proposed algorithm is tested and compared with the traditional algorithms. The comparison results show that the proposed strategy can divide and predict a crop growth cycle with high accuracy. The proposed strategy can significantly reduce the sensing and data collection times and energy consumption and significantly improve the value of sensing data.
2021 NOV
WOS:000724414000001
journalArticle
21
SENSORS
DOI 10.3390/s21227475
22
Peppes
Nikolaos
Daskalakis
Emmanouil
Alexakis
Theodoros
Adamopoulou
Evgenia
Demestichas
Konstantinos
Performance of Machine Learning-Based Multi-Model Voting Ensemble Methods for Network Threat Detection in Agriculture 4.0
The upcoming agricultural revolution, known as Agriculture 4.0, integrates cutting-edge Information and Communication Technologies in existing operations. Various cyber threats related to the aforementioned integration have attracted increasing interest from security researchers. Network traffic analysis and classification based on Machine Learning (ML) methodologies can play a vital role in tackling such threats. Towards this direction, this research work presents and evaluates different ML classifiers for network traffic classification, i.e., K-Nearest Neighbors (KNN), Support Vector Classification (SVC), Decision Tree (DT), Random Forest (RF) and Stochastic Gradient Descent (SGD), as well as a hard voting and a soft voting ensemble model of these classifiers. In the context of this research work, three variations of the NSL-KDD dataset were utilized, i.e., initial dataset, undersampled dataset and oversampled dataset. The performance of the individual ML algorithms was evaluated in all three dataset variations and was compared to the performance of the voting ensemble methods. In most cases, both the hard and the soft voting models were found to perform better in terms of accuracy compared to the individual models.
2021 NOV
WOS:000725936200001
journalArticle
32
Yingyong Shengtai Xuebao
DOI 10.13287/j.1001-9332.202111.012
11
Gao Wen-bo
Lin Zheng-yu
Wang Ming-tian
He Peng
Chen Chun-yan
Liu Yuan-li
Cao Jie
Spatiotemporal evolution characteristics of the late frost damage risk to shrubby tea trees in tea region, southwest China from 1971 to 2020
Understanding the spatiotemporal evolution characteristics of the risk of late frost damage has scientific guiding significance for optimizing the regional agricultural production layout and variety tuning. Based on the daily meteorological data of 65 weather stations in the southwest China tea region from 1971 to 2020, we analyzed variation characteristics of the last frost date (LFD), tea bud open date (BOD), and their relationships, constructed frost damage probability index and frost damage severity index of spring shoots of shrubby tea trees, and analyzed the spatiotemporal evolution characteristics of the late frost damage risk of shrub tea trees in the southwest tea region. The results showed that both the BOD and LFD had a significant ahead of trend from 1971 to 2020 and the early rate of the LFD was relatively faster than that of the BOD in the southwest tea region. The number of days that the tea buds were exposed to late frost damage after germination showed an non. significant declining trend. The risk of late frost damage of shrubby tea trees in most parts of the southwest tea region showed a declining trend, but Guizhou tea planting region showed an insignificant increasing trend. The risk of late frost damage to shrubby tea trees was high in the western marginal mountai-nous areas of Sichuan tea region, and the junction of Guizhou and Yunnan tea region. The risk of late frost damage was at low level in Sichuan Basin, southern Yunnan tea region, and southern Guizhou tea region. The risk of late frost damage to shrubby tea trees in the northern and central-eastern parts of Yunnan tea region showed an obvious decreasing trend, but increased significantly in the central and eastern parts of Guizhou tea region.
2021
BCI:BCI202200077123
4029-4038
journalArticle
125
FUNGAL BIOLOGY
DOI 10.1016/j.funbio.2021.08.004
12
Souza
Daniela Aguiar
de Oliveira
Charles Martins
Tamai
Marco Antonio
Faria
Marcos
Lopes
Rogerio Biaggioni
First report on the natural occurrence of entomopathogenic fungi in populations of the leafhopper Dalbulus maidis (Hemiptera: Cicadellidae): Pathogen identifications and their incidence in maize crops
The corn leafhopper Dalbulus maidis is one of the most important pests of maize in Latin America. Here we report, for the first time, the natural occurrence of two fungal species infecting the adult stage of this pest. In 2020, insects killed by a pale bluish green fungus in irrigated maize fields located in Northeast Brazil were found attached to the abaxial surface of leaves. Using morphological characters and multi-genic phylogeny, it was identified as Metarhizium brasiliense. In the beginning of 2021, the same pathogen was seen on adults in a maize field in the Central-Western region, alongside an entomophthoralean fungus during an epizootic. The latter pathogen was molecularly identified as a species in the genus Batkoa. The number of Batkoa-infected leafhoppers, displaying the typical swollen abdomen and extended wings, reached an average of 1.88 per maize leaf (86.42% of the sampled adults). The incidence of M. brasiliense was higher in plots in the Northeastern region (0.22 and 0.53 adult per leaf) when compared to the Central-Western region (0.04 adult per leaf). The report of D. maidis adults infected by M. brasiliense in agricultural settings located in different geographic regions and over 550 km apart in-dicates probable widespread occurrence of this pathogen in Brazil. Moreover, this opens the possibility of more applied biological control studies and, perhaps, the development of new tools to manage D. maidis populations. (c) 2021 British Mycological Society. Published by Elsevier Ltd. All rights reserved.
2021 DEC
WOS:000719241900004
980-988
journalArticle
29
ENVIRONMENTAL SCIENCE AND POLLUTION RESEARCH
DOI 10.1007/s11356-021-17358-w
15
Liu
Fan
Wang
Cui
Zhang
Yingyan
Zhou
Shuling
Yang
Yaliu
Wu
Xue
Hu
Fagang
Liu
Conghu
Data-driven analysis and evaluation of regional agriculture for high-quality development of Anhui Province in the Yangtze River Delta
This study aims to promote the high-quality development of regional agriculture. This study proposes a data-driven method for regional agricultural analysis and evaluation. Based on the data collection and processing related to regional agricultural development, the location entropy index was used to analyze the industrial agglomeration level, and the shift-share model was constructed to evaluate the industrial structure and competitiveness. Based on the above analysis and evaluation, high-quality development policy suggestions for regional agriculture were provided. Taking the agricultural development of the Yangtze River Delta from 2010 to 2019 as an example, this study shows the implementation process of the method. From the perspective of high-quality agricultural development in the Anhui Province, this paper proposes policy suggestions on industrial structure adjustment and promoting competitiveness. This study provides theoretical and methodological support for the development of high-quality regional agriculture.
2022 MAR
WOS:000719727400006
22490-22503
journalArticle
16
PLOS ONE
DOI 10.1371/journal.pone.0259264
11
Gatto
Marcel
Islam
Abu Hayat Md Saiful
Impacts of COVID-19 on rural livelihoods in Bangladesh: Evidence using panel data
Rapid assessments have been emerging on the effects of COVID-19, yet rigorous analyses remain scant. Here, rigorous evidence of the impacts of COVID-19 on several livelihood outcomes are presented, with a particular focus on heterogenous effects of COVID-19. We use a household-level panel dataset consisting of 880 data points collected in rural Bangladesh in 2018 and 2020, and employ difference-in-differences with fixed effects regression techniques. Results suggest that COVID-19 had significant and heterogenous effects on livelihood outcomes. Agricultural production and share of production sold were reduced, especially for rice crops. Further, diet diversity and education expenditure were reduced for the total sample. Households primarily affected by (fear of) sickness had a significantly lower agricultural production, share of crop market sales, and lower health and education expenditure, compared to households affected by other COVID-19 effects, such as travel restrictions. In turn, (fear of) sickness and the correlated reduced incidence of leaving the house, resulted in higher off-farm incomes suggesting that households engage in less physically demanding and localized work. Policy-makers need to be cognizant of these heterogenous COVID-19 effects and formulate policies that are targeted at those households that are most vulnerable (e.g., unable/willing to leave the house due to (fear of) sickness).
2021 NOV 29
WOS:000752076100014
journalArticle
808
SCIENCE OF THE TOTAL ENVIRONMENT
DOI 10.1016/j.scitotenv.2021.152073
Bai
Shahla Hosseini
Omidvar
Negar
Gallart
Marta
Kamper
Wiebke
Tahmasbian
Iman
Farrar
Michael B.
Singh
Kanika
Zhou
Guiyao
Muqadass
Bushra
Xu
Cheng-Yuan
Koech
Richard
Li
Yujuan
Nguyen
Thi Thu Nhan
van Zwieten
Lukas
Combined effects of biochar and fertilizer applications on yield: A review and meta-analysis
The use of biochar is changing, and the combined application of biochar with fertilizer is increasingly gaining acceptance. However, the yield gains results reported in the existing literature through the co-application of fertilizer with biochar are conflicting. To resolve this, we utilized a meta-analysis of 627 paired data points extracted from 57 published articles to assess the performance of the co-application of biochar and fertilizers on crop yield compared with the corresponding con-trols. We also studied the impact of biochar characteristics, experimental conditions, and soil properties on crop yield. Our analysis showed that individually, biochar and inorganic fertilizer increased crop yield by 25.3% +/- 3.2 (Bootstrap CI 95%) and 21.9% +/- 4.4, respectively. The co-application of biochar with both inorganic and organic fertilizers increased crop yield by 179.6% +/- 18.7, however, this data needs to be treated with caution dueto the limited dataset. The highest yield increase was observed with amendments to very acidic soils (pH <= 5), but the benefits of biochar were not affected by the rate and the time after the application. In addition, the effects of biochar are enhanced when it is produced at 401-500 degrees C with a C:N ratio of 31-100. Our results suggest that the co-application of biochar with either inorganic and/or organic fertilizers in acidic soils increase crop productivity compared to amendment with either fertilizer or bio-char. Our meta-analysis supports the utilization of biochar to enhance the efficiency and profitability of fertilizers.
2022 FEB 20
WOS:000740209300004
journalArticle
10
INFECTIOUS DISEASES OF POVERTY
DOI 10.1186/s40249-021-00919-z
1
Rinaldo
Daniele
Perez-Saez
Javier
Vounatsou
Penelope
Utzinger
Jurg
Arcand
Jean-Louis
The economic impact of schistosomiasis
Background: The economic impact of schistosomiasis and the underlying tradeoffs between water resources development and public health concerns have yet to be quantified. Schistosomiasis exerts large health, social and financial burdens on infected individuals and households. While irrigation schemes are one of the most important policy responses designed to reduce poverty, particularly in sub-Saharan Africa, they facilitate the propagation of schistosomiasis and other diseases.Methods: We estimate the economic impact of schistosomiasis in Burkina Faso via its effect on agricultural production. We create an original dataset that combines detailed household and agricultural surveys with high-resolution geo-statistical disease maps. We develop new methods that use the densities of the intermediate host snails of schistosomiasis as instrumental variables together with panel, spatial and machine learning techniques.Results: We estimate that the elimination of schistosomiasis in Burkina Faso would increase average crop yields by around 7%, rising to 32% for high infection clusters. Keeping schistosomiasis unchecked, in turn, would correspond to a loss of gross domestic product of approximately 0.8%. We identify the disease burden as a shock to the agricultural productivity of farmers. The poorest households engaged in subsistence agriculture bear a far heavier disease burden than their wealthier counterparts, experiencing an average yield loss due to schistosomiasis of between 32 and 45%. We show that the returns to water resources development are substantially reduced once its health effects are taken into account: villages in proximity of large-scale dams suffer an average yield loss of around 20%, and this burden decreases as distance between dams and villages increases.Conclusions: This study provides a rigorous estimation of how schistosomiasis affects agricultural production and how it is both a driver and a consequence of poverty. It further quantifies the tradeoff between the economics of water infrastructures and their impact on public health. Although we focus on Burkina Faso, our approach can be applied to any country in which schistosomiasis is endemic.
2021 DEC 13
WOS:000729361600001
journalArticle
810
SCIENCE OF THE TOTAL ENVIRONMENT
DOI 10.1016/j.scitotenv.2021.152142
Vogeler
Iris
Boldt
Matthias
Taube
Friedhelm
Mineralisation of catch crop residues and N transfer to the subsequent crop
Catch crops (CC) are widely used to reduce nitrogen leaching from arable cropping systems. However, the mineralisation rate of different catch crop species, and the fate of the mineralised N remain unclear. In this study, we performed an analysis, based on N mineralisation incubation experiments, to test and parameterise a simple mineralisation model (SMM), based on a first order decay, for different catch crops. For brassicas and legumes, the C:N was confirmed to be a good predictor of both, the amount and rate of mineral N release of CC residues. For grasses, the mineralisation rate could not be well predicted by the C:N, which might partly be due to a very limited dataset. The SMM was then linked with the Agricultural Production Simulator (APSIM) and used to predict the N release from CC residues of either brassicas or legumes, and its fate, including N leaching and N uptake by a subsequent spring barley (SB) crop. APSIM simulations were set up for a period of 20 years and for two sites with different temperature and soil conditions in North-West Europe, Foulum in Denmark and Kiel, Germany. Simulated N uptake by the CC was higher in Kiel compared with Foulum, with an average of 14.8 kg/ha for the crucifers and 16.8 kg/ha for the legume in Foulum, and of 33.2 kg/ha for the crucifers and 51.4 kg/ha for the legume in Kiel. CC increased yield of SB on average by 5 to 7%, due to transfer of N. This N transfer resulted in an average reduction in N leaching by 59% (brassica) and by 43% (legume) in Foulum, and by 83% (brassica) and by 43% (legume) in Kiel. N fertilisation of CC is not of any benefit in most of the 20 years of simulation.
2022 MAR 1
WOS:000744495400006
journalArticle
810
SCIENCE OF THE TOTAL ENVIRONMENT
DOI 10.1016/j.scitotenv.2021.152248
Scarlato
M.
Dogliotti
S.
Bianchi
F. J. J. A.
Rossing
W. A. H.
Ample room for reducing agrochemical inputs without productivity loss: The case of vegetable production in Uruguay
Vegetables are commonly produced with high inputs of pesticides and fertilisers to boost production and meet cosmetic market standards. Yet, reports on the relationships between agrochemical inputs and crop productivity are scattered and an overview is missing. We assessed the relationship between pesticide and nutrient inputs and crop productivity for five vegetable crops in the south of Uruguay at field and farm level and explored the relation with farm resource endowment. We analysed crop yield and input use for tomato, onion, sweet potato, and strawberry with a dataset of 82 farms and 428 fields constructed between 2012 and 2017. Clear crop-specific patterns in pesticide and nutrient input levels were found, despite considerable variation across fields within the same crop. Strawberry and long cycle tomato had the greatest pesticide input regarding of the number of applications (20 and 18, respectively) and pesticide load (21 kg Al ha(-1)). Cumulative nutrient inputs were greatest for long cycle tomato (1127 kg ha(-1)). The relationships between inputs and yield were weak or non-significant, indicating inefficiencies and overuse of inputs, and there was no agronomical rationale for input use. We found substantial variation in management practices between fields and farms. In several cases, 21% of the fields and 17% of the farms producing onion, strawberry and tomato, attained relatively high yield levels with limited input levels. Yield and input use levels were not related to farm resource endowment Our findings question the efficiency of the current high levels of pesticide and nutrient inputs in Uruguayan vegetable systems. The inputs may pose environmental and human health risks and in most cases did not increase yields. Learning from positive deviant farmers in combination with guided farm redesign, high-quality extension services, and use of context-specific knowledge and technologies may equip farmers to use more sustainable management practices.
2022 MAR 1
WOS:000740224700011
journalArticle
16
PLOS ONE
DOI 10.1371/journal.pone.0261612
12
Alvarez
Faver
Casanoves
Fernando
Carlos Suarez
Juan
Influence of scattered trees in grazing areas on soil properties in the Piedmont region of the Colombian Amazon
Trees dispersed in grazing areas are contribute to the sustainability of livestock systems. The interactions between trees and soil are ecological processes that allow the modification of the biology, fertility, and physics of the soil. This study was aimed to assess the influence of dispersed trees in pastures on soil properties in grazing areas for dual-purpose cattle systems in the Piedmont region of the Colombian Amazon. The work was done in grazing areas with scattered trees at the Centro de Investigaciones Amazonicas CIMAZ-Macagual in Florencia-Caqueta-Colombia. We evaluated the effect of five tree species, Andira inermis, Bellucia pentamera, Guarea Guidonia, Psidium guajava and Zygia longifolia, on soil properties (up to 30 cm soil depth) under and outside the influence of the crown. Under the tree crown, three points were systematically taken in different cardinal positions. This was done at a distance corresponding to half the radius of the tree crown. The sampling points in the open pasture area (out of crown) were made in the same way, but at 15 m from the crown border. The ANOVA showed significant interaction (P < 0.0001) between tree species and location for macrofauna abundance up to 30 cm soil depth. For this reason, we performed the comparison between locations for each tree species. Chemical soil variables up to 10 cm soil depth only showed interaction of tree species-location for exchangeable potassium (P = 0.0004). Soil physical soil characteristics up to 30 cm soil depth only showed interaction of tree species-location at 20 cm soil depth (P = 0.0003). The principal component analysis for soil properties explained 61.1% of the total variability of the data with the two first axes. Using Monte Carlo test, we found crown effect for all species. Trees help to control exchangeable mineral elements that can affect the soil, potentiate basic cations such as magnesium and potassium, increase the abundance of soil macrofauna; but some trees with high ground level of shade in grazing areas could increase soil compaction due to the greater concentration of cattle in these areas.
2021 DEC 29
WOS:000760118200016
journalArticle
17
PloS one
DOI 10.1371/journal.pone.0274361
9
Steiner
Bigna L
Martinez-Grau
Hector
Bernasconi
Stefano M
Gross
Eda
Hajdas
Irka
Jacomet
Stefanie
Jaggi
Madalina
Schaeren
Gishan F
Antolin
Ferran
Archaeobotanical and isotopic analyses of waterlogged remains from the Neolithic pile-dwelling site of Zug-Riedmatt (Switzerland): Resilience strategies of a plant economy in a changing local environment.
The excellent preservation of the waterlogged botanical remains of the multiphase Neolithic pile-dwelling site of Zug-Riedmatt (Central Switzerland) yielded an ideal dataset to delve into the issue of plant economy of a community spanning several decades. The study identified a major change in crops where oil plants played a key role in the site's initial phase before being supplanted over the course of a few decades by naked wheat, barley and pea. Wild plants continued to be gathered albeit in different proportions. In the latest settlement phase, the changes in the local vegetation and in the values of the analyses of carbon stable isotopes suggest a less humid environment. The hypothesis is that the changes perceived in the plant economy represent a resilience strategy adopted by the inhabitants in reaction to short term local climatic alterations. The two types of soil sampling techniques (monolith and bulk) allowed comparing these results. While the density of plant remains appears to be underestimated among the samples collected by the monolith technique, the proportions of economic taxa remain unaffected. The findings thus reveal that when the bulk samplings are distributed carefully throughout multiphase sites and avoid mixing stratigraphical units, and if the samplings are representative of all archaeological features from a whole area, then each of the two techniques offer analogous results.
2022
MEDLINE:36170265
e0274361-e0274361
journalArticle
22
SENSORS
DOI 10.3390/s22010146
1
Shafi
Uferah
Mumtaz
Rafia
Ul Haq
Ihsan
Hafeez
Maryam
Iqbal
Naveed
Shaukat
Arslan
Zaidi
Syed Mohammad Hassan
Mahmood
Zahid
Wheat Yellow Rust Disease Infection Type Classification Using Texture Features
Wheat is a staple crop of Pakistan that covers almost 40% of the cultivated land and contributes almost 3% in the overall Gross Domestic Product (GDP) of Pakistan. However, due to increasing seasonal variation, it was observed that wheat is majorly affected by rust disease, particularly in rain-fed areas. Rust is considered the most harmful fungal disease for wheat, which can cause reductions of 20-30% in wheat yield. Its capability to spread rapidly over time has made its management most challenging, becoming a major threat to food security. In order to counter this threat, precise detection of wheat rust and its infection types is important for minimizing yield losses. For this purpose, we have proposed a framework for classifying wheat yellow rust infection types using machine learning techniques. First, an image dataset of different yellow rust infections was collected using mobile cameras. Six Gray Level Co-occurrence Matrix (GLCM) texture features and four Local Binary Patterns (LBP) texture features were extracted from grayscale images of the collected dataset. In order to classify wheat yellow rust disease into its three classes (healthy, resistant, and susceptible), Decision Tree, Random Forest, Light Gradient Boosting Machine (LightGBM), Extreme Gradient Boosting (XGBoost), and CatBoost were used with (i) GLCM, (ii) LBP, and (iii) combined GLCM-LBP texture features. The results indicate that CatBoost outperformed on GLCM texture features with an accuracy of 92.30%. This accuracy can be further improved by scaling up the dataset and applying deep learning models. The development of the proposed study could be useful for the agricultural community for the early detection of wheat yellow rust infection and assist in taking remedial measures to contain crop yield.
2022 JAN
WOS:000744279400001
journalArticle
19
MATHEMATICAL BIOSCIENCES AND ENGINEERING
DOI 10.3934/mbe.2022370
8
Pandey
Vishal
Anand
Khushboo
Kalra
Anmol
Gupta
Anmol
Roy
Partha Pratim
Kim
Byung-Gyu
Enhancing object detection in aerial images
Unmanned Aerial Vehicles have proven to be helpful in domains like defence and agriculture and will play a vital role in implementing smart cities in the upcoming years. Object detection is an essential feature in any such application. This work addresses the challenges of object detection in aerial images like improving the accuracy of small and dense object detection, handling the class-imbalance problem, and using contextual information to boost the performance. We have used a density map-based approach on the drone dataset VisDrone-2019 accompanied with increased receptive field architecture such that it can detect small objects properly. Further, to address the class imbalance problem, we have picked out the images with classes occurring fewer times and augmented them back into the dataset with rotations. Subsequently, we have used RetinaNet with adjusted anchor parameters instead of other conventional detectors to detect aerial imagery objects accurately and effi- ciently. The performance of the proposed three step pipeline of implementing object detection in aerial images is a significant improvement over the existing methods. Future work may include improvement in the computations of the proposed method, and minimising the effect of perspective distortions and occlusions.
2022
WOS:000806871700003
7920-7932
journalArticle
119
Proceedings of the National Academy of Sciences of the United States of America
DOI 10.1073/pnas.2113936119
21
Padilla-Iglesias
Cecilia
Atmore
Lane M
Olivero
Jesus
Lupo
Karen
Manica
Andrea
Arango Isaza
Epifania
Vinicius
Lucio
Migliano
Andrea Bamberg
Population interconnectivity over the past 120,000 years explains distribution and diversity of Central African hunter-gatherers.
The evolutionary history of African hunter-gatherers holds key insights into modern human diversity. Here, we combine ethnographic and genetic data on Central African hunter-gatherers (CAHG) to show that their current distribution and density are explained by ecology rather than by a displacement to marginal habitats due to recent farming expansions, as commonly assumed. We also estimate the range of hunter-gatherer presence across Central Africa over the past 120,000 years using paleoclimatic reconstructions, which were statistically validated by our newly compiled dataset of dated archaeological sites. Finally, we show that genomic estimates of divergence times between CAHG groups match our ecological estimates of periods favoring population splits, and that recoveries of connectivity would have facilitated subsequent gene flow. Our results reveal that CAHG stem from a deep history of partially connected populations. This form of sociality allowed the coexistence of relatively large effective population sizes and local differentiation, with important implications for the evolution of genetic and cultural diversity in Homo sapiens.
2022 05 24 (Epub 2022 May 17)
MEDLINE:35580185
e2113936119-e2113936119
journalArticle
194
ENVIRONMENTAL MONITORING AND ASSESSMENT
DOI 10.1007/s10661-021-09663-1
1
Ozsahin
Emre
Ozdes
Mehmet
Agricultural land suitability assessment for agricultural productivity based on GIS modeling and multi-criteria decision analysis: the case of Tekirdag province
Grains play a significant role in meeting the nutritional needs of the increasing world population. Consequently, the need for new studies on agricultural production and land suitability assessments has increased. The present paper aims to perform agricultural land suitability assessment to evaluate agricultural productivity in Tekirdag province to determine precise productive agricultural areas. This study combines a variety of datasets to develop a dynamic model using GIS-based multi-criteria decision analysis for land suitability assessment and agricultural productivity. The datasets used in this study are supported by terrestrial samples and processed with spatial technologies. The results of the study indicate that the agricultural potential of the provincial lands is quite high. It reveals that 65.7% of province lands are suitable for agricultural production. Of the remaining lands, 20.3% is marginally suitable while only 8% of the land is unsuitable for agricultural production. In the northwestern part, suitable land for agricultural productivity is higher compared to other parts of the study area. This part also corresponds to the areas where industrial activities are marginal. The results also imply that agricultural activities in grain production areas must be reconsidered and replanned according to the new classification of land suitability assessment. In this respect, our study suggests that the policymakers and the government should take necessary steps to ensure the protection and sustainability of agricultural lands while planning for the industrial and settlement development in grain production areas.
2022 JAN
WOS:000733284100001
journalArticle
17
PLOS ONE
DOI 10.1371/journal.pone.0267627
7
Lin
Haofeng
Zrelli
Houyem
Mohamed
Noha Hassan abd Algalil
Li
Yonghui
Alam
Mohammad Mahtab
Guo
Wei
Khan
Yousaf Ali
The impact of agricultural water salvation investment on economics development: Evidence from Eastern China
Agricultural water salvation is the lifeblood of the national economy and is of great significance to the high-quality development of the region. In order to maximize the economic assistances of agricultural water salvation investment, this article focuses on panel data from 2005 to 2019 in 14 provinces in Eastern China, this research constructs an economic development evaluation index system from five dimensions: innovative development, coordinated development, green development, open development and shared development, and uses dynamic panel model to explore the influence relationship and path of Eastern Agricultural water salvation investment on economic development. The results represent that: there is a significant non-linear effect between agricultural water salvation investment and economic growth, showing an inverted U-shaped relationship. Which means that with the expansion of agricultural water salvation investment; economic growth has risen first and then declined. At present, the impact of agricultural water salvation investment in the Eastern region on economic development is in the promotion stage of positive and sustained growth. The recommendation of this research will help the state control in the amount of agricultural water salvation investment in the Eastern region, improve the efficiency of agricultural water salvation investment, and provide support in decision making.
2022
WOS:000835338100020
journalArticle
119
Proceedings of the National Academy of Sciences of the United States of America
DOI 10.1073/pnas.2109321119
43
Frahm
Ellery
Carolus
Christina M
Identifying the origins of obsidian artifacts in the Deh Luran Plain (Southwestern Iran) highlights community connections in the Neolithic Zagros.
Exchange networks created by Neolithic pastoral transhumance have been central to explaining the distant transport of obsidian since chemical analysis was first used to attribute Near Eastern artifacts to their volcanic origins in the 1960s. Since then, critical reassessments of floral, faunal, and chronological data have upended long-held interpretations regarding the emergence of food production and have demonstrated that far-traveled, nomadic pastoralists were more myth than reality, at least during the Neolithic. Despite debates regarding their proposed conveyance mechanisms, obsidian artifacts' transport has received relatively little attention compared with zooarchaeological and archaeobotanical lines of investigation. The rise of nondestructive and portable instruments permits entire obsidian assemblages to be traced to their sources, renewing their significance in elucidating connections among early pastoral and agricultural communities. Here we share our findings about the obsidian artifacts excavated from the sites of Ali Kosh and Chagha Sefid in the southern Zagros. In the 1960s and 1970s, 28 obsidian artifacts from the sites were destructively tested, and the remainder were sorted by color. Our results emphasize a dynamic, accelerating connectivity among the Early and Late Neolithic communities. Here we propose and support an alternative model for obsidian distribution among more settled communities. In brief, diversity in the obsidian assemblage accelerated diachronically, an invisible trend in the earlier studies. Our model of increasing population densities is supported by archaeological data and computational simulations, offering insights regarding the Neolithic Demographic Transition in the Zagros, an equivalent of which is commonly thought to have occurred around the world.
2022 10 25 (Epub 2022 Oct 17)
MEDLINE:36252033
e2109321119-e2109321119
journalArticle
17
PloS one
DOI 10.1371/journal.pone.0272508
8
Butruille
Gregoire
Thomas
Marielle
Pasquet
Alain
Amoussou
Nellya
Toomey
Lola
Rosenstein
Axel
Chauchard
Sandrine
Lecocq
Thomas
AquaDesign: A tool to assist aquaculture production design based on abiotic requirements of animal species.
Farming new species and promoting polyculture can enhance aquaculture sustainability. This implies to define the rearing conditions that meet the ecological requirements of a target species and/or to assess if different species can live in the same farming environment. However, there is a large number of rearing conditions and/or taxon combinations that can be considered. In order to minimise cumbersome and expensive empirical trials to explore all possibilities, we introduce a tool, AquaDesign. It is based on a R-script and package which help to determine farming conditions that are most likely suitable for species through in silico assessment. We estimate farming conditions potentially suitable for an aquatic organism by considering the species niche. We define the species n-dimensional niche hypervolume using a correlative approach in which the species niche is estimated by relating distribution data to environmental conditions. Required input datasets are mined from several public databases. The assistant tool allows users to highlight (i) abiotic conditions that are most likely suitable for species and (ii) combinations of species potentially able to live in the same abiotic environment. Moreover, it offers the possibility to assess if a particular set of abiotic conditions or a given farming location is potentially suitable for the monoculture or the polyculture of species of interest. Our tool provides useful pieces of information to develop freshwater aquacultures. Using the large amount of biogeographic and abiotic information available in public databases allows us to propose a pragmatic and operational tool even for species for which abiotic requirements are poorly or not available in literature such as currently non-produced species. Overall, we argue that the assistant tool can act as a stepping stone to promote new aquatic productions which are required to enhance aquaculture sustainability.
2022
MEDLINE:35913974
e0272508-e0272508
journalArticle
17
PLOS ONE
DOI 10.1371/journal.pone.0269729
6
Benzeev
Rayna
Wilson
Bradley
Butler
Megan
Massoca
Paulo
Paudel
Karuna P.
Redmore
Lauren P.
Zarba
Lucia P.
What's governance got to do with it? Examining the relationship between governance and deforestation in the Brazilian Amazon
Deforestation continues at rapid rates despite global conservation efforts. Evidence suggests that governance may play a critical role in influencing deforestation, and while a number of studies have demonstrated a clear relationship between national-level governance and deforestation, much remains to be known about the relative importance of subnational governance to deforestation outcomes. With a focus on the Brazilian Amazon, this study aims to understand the relationship between governance and deforestation at the municipal level. Drawing on the World Bank Worldwide Governance Indicators (WGI) as a guiding conceptual framework, and incorporating the additional dimension of environmental governance, we identified a wide array of publicly available data sources related to governance indicators that we used to select relevant governance variables. We compiled a dataset of 22 municipal-level governance variables covering the 2005-2018 period for 457 municipalities in the Brazilian Amazon. Using an econometric approach, we tested the relationship between governance variables and deforestation rates in a fixed-effects panel regression analysis. We found that municipalities with increasing numbers of agricultural companies tended to have higher rates of deforestation, municipalities with an environmental fund tended to have lower rates of deforestation, and municipalities that had previously elected a female mayor tended to have lower rates of deforestation. These results add to the wider conversation on the role of local-level governance, revealing that certain governance variables may contribute to halting deforestation in the Brazilian Amazon.
2022
WOS:000830362700063
journalArticle
23
HEALTH PROMOTION PRACTICE
DOI 10.1177/15248399211070546
3
Martinez
Celina L.
Rosero
Daisy
Thomas
Tammy
Soto Mas
Francisco
Community Supported Agriculture, Human Capital, and Community Health
Community supported agriculture (CSA) strengthens the local food system (LFS) and plays a critical role in promoting human capital (HC) and addressing social determinants of health (SDH). Most CSAs develop relationships that build a sense of community, and engage in activities that facilitate access to food and economic opportunities. CSAs may also contribute to personal development, education and income, working experience, and knowledge. CSA principles align with the principles of HC, specifically the pursuit of economic development. While research on the connection between CSA and HC has broadly focused on the economic aspect, the human development dimension has remained at the conceptual level. The purpose of this study was to assess the potential HC contributions by CSA and the implications for health outcomes in central/northern New Mexico. Primary and secondary data were collected through a semi-structured, open-ended questionnaire and an internet search. Purposive sampling was used to select 13 CSAs. Eight (61.5%) responded and reported activities that address HC and SDH such as training, job creation, education, access to healthy food, food security, health education and disease management, social connections, and food justice. Given the potential impact, public health must contribute to CSA by generating evidence on its health and social benefits, training practitioners on supporting local food program, and promoting policy that stimulates the local economy, fosters social relations and food justice, and empowers community members. This study calls for research and practice to take a multilevel perspective on the contribution of LFSs to equity and wellbeing.
2022 MAY
WOS:000747731500001
407-415
journalArticle
815
SCIENCE OF THE TOTAL ENVIRONMENT
DOI 10.1016/j.scitotenv.2021.152880
Li
Zhenwang
Ding
Lei
Xu
Dawei
Exploring the potential role of environmental and multi-source satellite data in crop yield prediction across Northeast China
Developing an accurate crop yield predicting system at a large scale is of paramount importance for agricultural resource management and global food security. Earth observation provides a unique source of information to monitor crops from a diversity of spectral ranges. However, the integrated use of these data and their values in crop yield prediction is still understudied. Here we proposed the combination of environmental data (climate, soil, geography, and topography) with multiple satellite data (optical-based vegetation indices, solar-induced fluorescence (SIF), land surface temperature (LST), and microwave vegetation optical depth (VOD)) into the framework to estimate crop yield for maize, rice, and soybean in northeast China, and their unique value and relative influence on yield prediction was assessed. Two linear regression methods, three machine learning (ML) methods, and one ML ensemble model were adopted to build yield prediction models. Results showed that the individual ML methods outperformed the linear regression methods, the ML ensemble model further improved the single ML models. Moreover, models with more inputs achieved better performance, the combination of satellite data with environmental data, which explained 72%, 69%, and 57% of maize, rice, and soybean yield variability, respectively, demonstrated higher yield prediction performance than individual inputs. While satellite data contributed to crop yield prediction mainly at the early-peak of the growing season, climate data offered extra information mainly at the peak-late season. We also found that the combined use of EVI, LST and SIF has improved the model accuracy compared to the benchmark EVI model. However, the optical-based vegetation indices shared similar information and did not provide much extra information beyond EVI. The within-season yield forecasting showed that crop yields can be satisfactorily forecasted at two to three months prior to harvest. Geography, topography, VOD, EVI, soil hydraulic and nutrient parameters are more important for crop yield prediction.
2022 APR 1
WOS:000800372200012
journalArticle
2022
COMPUTATIONAL AND MATHEMATICAL METHODS IN MEDICINE
DOI 10.1155/2022/3522510
Aljaloud
Saud
Alshudukhi
Jalawi
Alhamazani
Khalid Twarish
Belay
Assaye
Comparative Study of Artificial Intelligence Techniques for the Diagnosis of Chronic Nerve Diseases
Farming is essential to the long-term viability of any economy. It differs in each country, but it is essential for long-term economic success. Only a few of the agricultural industry's issues include a lack of suitable irrigation systems, weeds, and plant monitoring concerns as a consequence of efficient management in distinct open and closed zones for crop and plant treatment. The objective of this work is to carry out a study on the use of artificial intelligence and computer vision methods for diagnosis of diseases in agro sectors in the context of agribusiness, demonstrating the feasibility of using these techniques as tools to support automation and obtain productivity gains in this sector. During the literary analysis, it was determined that technology could improve efficiency, hence decreasing these types of concerns. Given the consequences of a wrong diagnosis, diagnosis is work that requires a high level of precision. Fuzzy cognitive maps were shown to be the most efficient method of utilizing bibliographically reviewed preferences, which led to the consideration of neural networks as a second option because this technique is the most robust in terms of the qualifying criteria of the data stored in databases.
2022 JAN 13
WOS:000772898400010
journalArticle
9
SCIENTIFIC DATA
DOI 10.1038/s41597-021-01100-9
1
Tyrrell
Peter
Amoke
Irene
Betjes
Koen
Broekhuis
Femke
Buitenwerf
Robert
Carroll
Sarah
Hahn
Nathan
Haywood
Daniel
Klaassen
Britt
Lovschal
Mette
Macdonald
David
Maiyo
Karen
Mbithi
Hellen
Mwangi
Nelson
Ochola
Churchil
Odire
Erick
Ondrusek
Victoria
Ratemo
Junior
Pope
Frank
Russell
Samantha
Sairowua
Wilson
Sigilai
Kiptoo
Stabach
Jared A.
Svenning
Jens-Christian
Stone
Elizabeth
du Toit
Johan T.
Western
Guy
Wittemyer
George
Wall
Jake
Landscape Dynamics (landDX) an open-access spatial-temporal database for the Kenya-Tanzania borderlands
The savannas of the Kenya-Tanzania borderland cover >100,000 km(2) and is one of the most important regions globally for biodiversity conservation, particularly large mammals. The region also supports >1 million pastoralists and their livestock. In these systems, resources for both large mammals and pastoralists are highly variable in space and time and thus require connected landscapes. However, ongoing fragmentation of (semi-)natural vegetation by smallholder fencing and expansion of agriculture threatens this social-ecological system. Spatial data on fences and agricultural expansion are localized and dispersed among data owners and databases. Here, we synthesized data from several research groups and conservation NGOs and present the first release of the Landscape Dynamics (landDX) spatial-temporal database, covering similar to 30,000 km(2) of southern Kenya. The data includes 31,000 livestock enclosures, nearly 40,000 kilometres of fencing, and 1,500 km(2) of agricultural land. We provide caveats and interpretation of the different methodologies used. These data are useful to answer fundamental ecological questions, to quantify the rate of change of ecosystem function and wildlife populations, for conservation and livestock management, and for local and governmental spatial planning.
2022 JAN 18
WOS:000744920000001
journalArticle
820
SCIENCE OF THE TOTAL ENVIRONMENT
DOI 10.1016/j.scitotenv.2022.153118
Sun
Y.
Amelung
W.
Wu
B.
Haneklaus
S.
Schnug
E.
Bol
R.
Fertilizer P-derived uranium continues to accumulate at Rothamsted long-term experiments
The application of phosphorus (P) fertilizers inevitably contributes to the accumulation of trace elements, such as ura-nium (U), in agricultural soils. The fertilizer-derived U accumulation was first reported in Rothamsted Research in 1979. In the present study, we expand this early key research by evaluating the fertilizer-derived U accumulation in topsoil (0-23 cm) from 1876 to the 2010s. We found that total U accumulation rates ranged from 2.8 to 6.1 mu g U kg(-1) yr(-1) at the Broadbalk and Park Grass, respectively, being similar to those observed 40 years ago. This highlights that U accumulation is still an ongoing process in Rothamsted. Fortunately, the proportion of fertilizer-derived U did not significantly increase in the ammonium acetate extractable ('proxy' of plant-available) fraction over 130 years. In addition, we compiled an overview of the global rate of mineral P fertilizer-derived U accumulation in agricultural sys-tems using existing literature (36 experimental trials, from 11 countries). The resulting dataset predicts an estimated mean U accumulation of 0.85 mu g U kg(-1) soil for an annual application of 1 kg P ha(-1) in the topsoil of agricultural sys-tems (0.26 mu g U kg(-1) per kg P ha(-1) for arable land and 1.34 mu g U kg(-1) per kg P ha(-1) for grassland). The annual U accumulation per applied kg P ha(-1) being 0.08 (Broadbalk) and 0.17 mu g U (Park Grass) corresponds to around one-third and one-eighth of the worldwide mean U accumulation for their respective agricultural systems, suggesting 'relatively' low U contents of the applied P fertilizers. Our study underscores that fertilizer-derived U accumulation is a persistent problem on the global scale, even if at different rates, and therewith suggests an evaluation of current regulatory limits and acceptable U input levels from P fertilization.
2022 MAY 10
WOS:000779009700001
journalArticle
29
ENVIRONMENTAL SCIENCE AND POLLUTION RESEARCH
DOI 10.1007/s11356-021-17956-8
28
Biswas
Gouranga
Sengupta
Anuradha
Assessment of agricultural prospects in relation to land use change and population pressure on a spatiotemporal framework
The urbanisation process moves quickly in emerging nations like India and Bangladesh, transforming natural landscapes into unsustainable landscapes. Consequently, growing development has had a significant impact on agricultural land as a natural environment. Moreover, there is a scarcity of research on fragmentation probability modelling in the extant literature. Thus, by combining random forest (RF) and bagging with the datasets which are multi-temporal in a GIS framework, the probability of fragmentation of LULC at Jangipur subdivision in India and Bangladesh can be modelled. Parallelepiped, Mohalnobis distance, support vector machines (SVM), spectral angle mapper (SAM), and artificial neural networks (ANN) classifiers were used for LULC classification, where SVM (Kappa coefficient: 0.87) surpassed other classifiers. The LULC maps for 1990, 2000, 2010, and 2020 were created using the best classifier (SVM). During this time, the built-up area grew from 23.769 to 158.125 km(2). Then, using an ANN-based cellular automata model, the future LULC map for 2030 was predicted (CA-ANN). In 2030, the built-up area would be 201.58 km(2). Then the matrices of class and landscape were taken out of the LULC maps utilising FRAGSTAT software and included the patch number (NP), largest patch index (LPI), edge density (ED), contagion index (percentage) (CONTAG), perimeter and area (P/A), aggregation index (AI), landscape percentage (PLAND), the area of class (CA), patch density (PD), edge in total (TE), total core area (TCA), and largest shape index (LSI). The validation results revealed that bagging (0.915 = AUC) and RF (0.874 = AUC) are capable of assessing fragmentation probability, with the bagging model having the greatest precision level of the two. Almost 20% of the total LULC was in a high and very high zone of fragmentation vulnerability, necessitating the use of direct measures to safeguard it. As a result, adequate LULC management is required.
2022 JUN
WOS:000749137700017
43267-43286
journalArticle
24
NICOTINE & TOBACCO RESEARCH
DOI 10.1093/ntr/ntab197
2
Wineman
Ayala
Chilora
Lemekezani
Jayne
Thomas S.
Trends in Tobacco Production and Prices in Malawi
Introduction Diversification away from tobacco production has been identified as a priority for Malawi, historically one of the world's most tobacco-reliant countries. Methods This paper refers to a nationally representative data set to characterize broad trends in production since 2000 to understand whether Malawi is shifting away from tobacco and how production has changed over time. Results From 2004 to 2019, the share of Malawian crop farmers producing tobacco fell from 16% to 5%, and tobacco's share of the total value of crop production also declined sharply. Tobacco farms are generally growing larger (in size and scale of production) over time. However, land productivity remains low, with net returns of 93 000 MWK (128 USD) per hectare at the median. Farm-gate prices for tobacco have declined relative to the prices of maize or fertilizer, rendering tobacco a less lucrative avenue to generate the cash income needed to purchase these key items. In addition, the share of the export price received by farmers has also declined over time, with the median farm-gate price representing 32% of the export price in 2004 and 18% in 2019. Conclusions In some respects, a transition away from tobacco has already occurred. Additional research is needed to understand why the farm-gate share of tobacco export prices has declined over this period and how the livelihoods of smallholder farm-households that exited tobacco production have been affected. Implications To the extent that tobacco prices appear to be declining, there is a need to rigorously assess whether farmers have suitable crop alternatives (with established markets) and other livelihood options. Likely, investments are yet needed to foster strong alternatives to tobacco; such investments include research and development in on-farm technologies to raise the productivity of non-tobacco crops, as well as improvements in non-tobacco value chains to reduce transportation costs and promote private investment.
2022 FEB 1
WOS:000753113600011
227-232
journalArticle
22
SENSORS
DOI 10.3390/s22041571
4
Tagarakis
Aristotelis C.
Filippou
Evangelia
Kalaitzidis
Damianos
Benos
Lefteris
Busato
Patrizia
Bochtis
Dionysis
Proposing UGV and UAV Systems for 3D Mapping of Orchard Environments
During the last decades, consumer-grade RGB-D (red green blue-depth) cameras have gained popularity for several applications in agricultural environments. Interestingly, these cameras are used for spatial mapping that can serve for robot localization and navigation. Mapping the environment for targeted robotic applications in agricultural fields is a particularly challenging task, owing to the high spatial and temporal variability, the possible unfavorable light conditions, and the unpredictable nature of these environments. The aim of the present study was to investigate the use of RGB-D cameras and unmanned ground vehicle (UGV) for autonomously mapping the environment of commercial orchards as well as providing information about the tree height and canopy volume. The results from the ground-based mapping system were compared with the three-dimensional (3D) orthomosaics acquired by an unmanned aerial vehicle (UAV). Overall, both sensing methods led to similar height measurements, while the tree volume was more accurately calculated by RGB-D cameras, as the 3D point cloud captured by the ground system was far more detailed. Finally, fusion of the two datasets provided the most precise representation of the trees.
2022 FEB
WOS:000762098000001
journalArticle
22
SENSORS
DOI 10.3390/s22041326
4
Singh
Ritesh Kumar
Rahmani
Mohammad Hasan
Weyn
Maarten
Berkvens
Rafael
Joint Communication and Sensing: A Proof of Concept and Datasets for Greenhouse Monitoring Using LoRaWAN
In recent years, greenhouse-based precision agriculture (PA) has been strengthened by utilization of Internet of Things applications and low-power wide area network communication. The advancements in multidisciplinary technologies such as artificial intelligence (AI) have created opportunities to assist farmers further in detecting disease and poor nutrition of plants. Neural networks and other AI techniques need an initial set of measurement campaigns along with extensive datasets as a training set to baseline and evolve different applications. This paper presents LoRaWAN-based greenhouse monitoring datasets over a period of nine months. The dataset has both the network and sensing information from multiple sensor nodes for tomato crops in two different greenhouse environments. The goal is to provide the research community with a dataset to evaluate performance of LoRaWAN inside a greenhouse and develop more efficient PA monitoring techniques. In this paper, we carried out an exploratory data analysis to infer crop growth by analyzing just the LoRaWAN signals and without inclusion of any extra hardware. This work uses a multilayer perceptron artificial neural network to predict the weekly plant growth, trained using RSSI value from sensor data and manual measurement of plant height from the greenhouse. We developed this proof of concept of joint communication and sensing by using generated dataset from the "Proefcentrum Hoogstraten" greenhouse in Belgium. Results for the proposed method yield a root mean square error of 10% in detecting the average plant height inside a greenhouse. In future, we can use this concept of landscape sensing for different supplementary use-cases and to develop optimized methods.
2022 FEB
WOS:000765177700001
journalArticle
22
SENSORS
DOI 10.3390/s22041472
4
Rodriguez-Pabon
Carlos
Riva
Guillermo
Zerbini
Carlos
Ruiz-Rosero
Juan
Ramirez-Gonzalez
Gustavo
Carlos Corrales
Juan
An Adaptive Sampling Period Approach for Management of IoT Energy Consumption: Case Study Approach
The Internet of Things (IoT) opens opportunities to monitor, optimize, and automate processes into the Agricultural Value Chains (AVC). However, challenges remain in terms of energy consumption. In this paper, we assessed the impact of environmental variables in AVC based on the most influential variables. We developed an adaptive sampling period method to save IoT device energy and to maintain the ideal sensing quality based on these variables, particularly for temperature and humidity monitoring. The evaluation on real scenarios (Coffee Crop) shows that the suggested adaptive algorithm can reduce the current consumption up to 11% compared with a traditional fixed-rate approach, while preserving the accuracy of the data.
2022 FEB
WOS:000920202200014
journalArticle
29
ENVIRONMENTAL SCIENCE AND POLLUTION RESEARCH
DOI 10.1007/s11356-021-16067-8
8
Mudassir
Muhammad Akhlaq
Rasul
Fahd
Khaliq
Tasneem
Yaseen
Muhammad
Conformance of sowing dates for maximizing heat use efficiency and seed cotton yield in arid to semi-arid cotton zone of Pakistan
Pakistan is placed among the most vulnerable countries with relation to climate change and its impacts on agricultural productivity. Cotton is staged as the cash crop of the country and the main source of raw material for textile, oil, and feed industry. Varying environmental attributes have significant effects on the duration of vegetative and reproductive stages of cotton crop. To evaluate the potential impacts of varied temperatures regimes in different sowing times, field experiments were carried out throughout the cotton growing areas of Pakistan from Faisalabad in Central Punjab to RYK in Southern Punjab and Sakrand in Sindh to Dera Ismail Khan in Khyber Pakhtunkhwa (KPK) Province. Crop was sown on six different sowing dates starting from 1st March towards 15th May with 2-week intervals for two crop seasons (2016 and 2017). The timing of phenological events like emergence, squaring, flowering, and boll opening was recorded on calendar days and cumulative heat units (GDDs) were calculated for flowering and boll opening stages. Heat use efficiency for these sowing times was estimated. Data regarding yield-related parameters like opened bolls per plant, average boll weight, and seed cotton yield were also recorded during the study. Results revealed that duration of the growth stages was significantly affected by variation in mean thermal kinetics in varied sowing times in all four different environments. Seed cotton yield and heat use efficiency were also varied among the locations and sowing dates. The maximum seed cotton yield was recorded in Sakrand location at 15th April sowing date. The dependence of the phenological advancement on temperature and negative impacts of higher thermal stress on cotton productivity were also confirmed throughout the cotton growing zone of Pakistan.
2022 FEB
WOS:000802745300001
11359-11373
journalArticle
19
INTERNATIONAL JOURNAL OF ENVIRONMENTAL RESEARCH AND PUBLIC HEALTH
DOI 10.3390/ijerph19031111
3
Baluch
Khaqan
Kim
Jung-Gyu
Kim
Jong-Gwan
Ko
Young Hun
Jung
Seung-Won
Baluch
Sher Q.
Assessment of Sinkholes Investigations in Jangseong-Gun Area, South Korea, and Recommendations for Similar Studies
This paper reviews the site investigation field data and access work performed between 2016 and 2019 in the study area located close to Gun-dong mine. The research was aimed at defining the cause of sinkholes and their relationship with the underlying karstic limestone bedrock and nearby mining activities. Only a limited number of small sinkholes appeared in 2014, 2016, and 2018 in the agricultural land close to the limestone mine. The previously open pit mine started its underground operations in 2007. Since then, the mine has developed, and is now comprised of, large underground excavations at several levels below the surface. The studies carried out concluded that the appearance of sinkholes may be related to a general lowering of the groundwater table because of nearby agricultural and mining activities and also due to over-extraction of water due to increased urban use. Whilst these are the best determinations, this paper identifies missing elements of the previous investigations mentioned above, some issues with the interpretation of poorly prepared borehole logs and the improper preservation of borehole cores. The authors make recommendations for a systematic approach for implementation of an investigation strategy. This paper concludes that the appearance of sinkholes is a natural phenomenon, developing over geological time. However, human intervention contributes to sinkhole formation, which in urban areas may result in human, property, and economic losses. A better understanding, based on a methodical approach and suitable technologies, can determine the causes of sinkholes and can lead to the formulation of solutions and the implementation of economically and socially acceptable mitigation measures.
2022 FEB
WOS:000757548000001
journalArticle
822
SCIENCE OF THE TOTAL ENVIRONMENT
DOI 10.1016/j.scitotenv.2022.153514
Mendoza Beltran
Angelica
Jepsen
Kelzy
Rufi-Salis
Marti
Ventura
Sergi
Madrid Lopez
Cristina
Villalba
Gara
Mapping direct N2O emissions from peri-urban agriculture: The case of the Metropolitan Area of Barcelona
Geographically explicit datasets reflecting local management of crops are needed to help improve direct nitrous oxide (N2O) emission inventories. Yet, the lack of geographically explicit datasets of relevant factors influencing the emissions make it difficult to estimate them in such way. Particularly, for local peri-urban agriculture, spatially explicit datasets of crop type, fertilizer use, irrigation, and emission factors (EFs) are hard to find, yet necessary for evaluating and promoting urban self-sufficiency, resilience, and circularity. We spatially distribute these factors for the peri-urban agriculture in the Metropolitan Area of Barcelona (AMB) and create N2O emissions maps using crop-specific EFs as well as Tier 1 IPCC EFs for comparison. Further, the role of the soil types is qualitatively assessed. When compared to Tier 1 IPCC EFs, we find 15% more emissions (i.e. 7718 kg N2O-N year(-1)) than those estimated with the crop-specific EFs (i.e. 6533 kg N2O-N year(-1)) for the entire AMB. Emissions for most rainfed crop areas like cereals (e.g. oat and barley) and non-citric fruits (e.g. cherries and peaches), which cover 24% and 13% of AMB's peri-urban agricultural area respectively, are higher with Tier 1 EF. Conversely, crop-specific EFs estimate higher emissions for irrigated horticultural crops (e.g. tomato, artichoke) which cover 33% of AMB's peri-urban agricultural area and make up 70% of the total N2O emissions (4588 kg N2O-N year(-1) using crop-specific EFs). Mapping the emissions helps evaluate spatial variability of key factors such as fertilizer use and irrigation of crops but carry uncertainties due to downscaling regional data to represent urban level data gaps. It also highlighted core emitting areas. Further the usefulness of the outputs on mitigation, sustainability and circularity studies are briefly discussed.
2022 MAY 20
WOS:000766800600009
journalArticle
61
INTEGRATIVE AND COMPARATIVE BIOLOGY
DOI 10.1093/icb/icab114
6
Chandrasekaran
Sriram
Danos
Nicole
George
Uduak Z.
Han
Jin-Ping
Quon
Gerald
Muller
Rolf
Tsang
Yinphan
Wolgemuth
Charles
The Axes of Life: A Roadmap for Understanding Dynamic Multiscale Systems
Synopsis The biological challenges facing humanity are complex, multi-factorial, and are intimately tied to the future of our health, welfare, and stewardship of the Earth. Tackling problems in diverse areas, such as agriculture, ecology, and health care require linking vast datasets that encompass numerous components and spatio-temporal scales. Here, we provide a new framework and a road map for using experiments and computation to understand dynamic biological systems that span multiple scales. We discuss theories that can help understand complex biological systems and highlight the limitations of existing methodologies and recommend data generation practices. The advent of new technologies such as big data analytics and artificial intelligence can help bridge different scales and data types. We recommend ways to make such models transparent, compatible with existing theories of biological function, and to make biological data sets readable by advanced machine learning algorithms. Overall, the barriers for tackling pressing biological challenges are not only technological, but also sociological. Hence, we also provide recommendations for promoting interdisciplinary interactions between scientists.
2022 FEB 5
WOS:000755202100004
2011-2019
journalArticle
816
SCIENCE OF THE TOTAL ENVIRONMENT
DOI 10.1016/j.scitotenv.2021.151518
Rashid
Muhammad Adil
Bruun
Sander
Styczen
Merete Elisabeth
Orum
Jens Erik
Borgen
Signe Kynding
Thomsen
Ingrid Kaag
Jensen
Lars Stoumann
Scenario analysis using the Daisy model to assess and mitigate nitrate leaching from complex agro-environmental settings in Denmark
Nitrate (N) leaching from intensively managed cropping systems is of environmental concern and it varies at local scale. To evaluate the performance of agricultural practices at this scale, there is a need to develop comprehensive assessments of N leaching and the N leaching reduction potential of mitigation measures. A model-based analysis was performed to (i) estimate N leaching from Danish cropping systems, representing 20 crop rotations, 3 soil types, 2 climates and 3-4 levels of manure (slurry)-to-fertilizer ratios, but with same available N (according to regulatory N fertilization norms), and (ii) appraise mitigation potential of on-farm measures (i.e. catch crops, early sowing of winter cereals) to reduce N leaching. The analysis was performed using a process-based agroenvironmental model (Daisy). Simulated average N leaching over 24 years ranged from 16 to 85 kg N/ha/y for different crop rotations. Rotations with a higher proportion of spring crops were more prone to leaching than rotations having a higher proportion of winter cereals and semi-perennial grass-clover leys. N leaching decreased with increasing soil clay content under all conditions. The effect of two climates (different regions, mainly differing in precipitation) on N leaching was generally similar, with slight variation across rotations. Supplying a part of the available N as manure-N resulted in similar N leaching as mineral fertilizer N alone during the simulation period. Among the mitigation measures, both undersown and autumn sown catch crops were effective. Effectiveness of measures also depended on their place and frequency of occurrence in a rotation. Adopting catch crops during the most leaching-prone years and with higher frequency were effective choices. This analysis provided essential data-driven knowledge on N leaching risk, and potential of leaching reduction options. These results can serve as a supplementary guiding-tool for farmers to plan management practices, and for legislators to design farm-specific regulatory measures. (c) 2021 The Authors. Published by Elsevier B.V. This is an open access article under the CC BY license (http:// creativecommons.org/licenses/by/4.0/).
2022 APR 10
WOS:000766809600002
journalArticle
816
SCIENCE OF THE TOTAL ENVIRONMENT
DOI 10.1016/j.scitotenv.2021.151570
O'Donoghue
Cathal
Meng
Yuting
Ryan
Mary
Kilgarriff
Paul
Zhang
Chaosheng
Bragina
Lyubov
Daly
Karen
Trends and influential factors of high ecological status mobility in Irish Rivers
The decline in high ecological water status in rivers is a significant concern in European countries. It is thus important to investigate the factors that cause sites to lose high status in order to undertake measures to protect and restore high status water quality. Analysis of 20 years of water quality data reveals strong mobility between high status and non-high status (especially good status) rivers. Associations between this mobility and socioeconomic and physical environmental variables were estimated by multinomial logistic regression at national scale and regional scale. Based on reported changes in water quality status cross across 1990, 2000 and 2010, four classes of the mobility of high status were defined in this study: those sites that maintain high status (maintain), enter high status (enter), fluctuate between high and non-high status (fluctuate) and exit from high status (exit). The national results indicate that agricultural activity as indicated by variables representing intensity of livestock farming (organic nitrogen) and tillage farming (cereal share) and elevation had significant negative impacts on high status rivers. Meanwhile, significant differences in population density and septic tank density between 'exit', 'maintain', 'fluctuate' and 'enter' classes indicate that these factors played important roles in the stability of high status rivers. The regional outcomes reveal differential significant pressures across regions. For example, rainfall and elevation had positive impacts on high status rivers in the north-west region, while organic nitrogen had a negative effect in the south-west. This paper demonstrates the challenge in achieving the Water Framework Directive goal of maintaining high status rivers, given the sensitive and highly differentiated nature of areas that have lost high status or fluctuated in and out of high status. This paper also suggests the necessity for localised policies and mitigation measures. (c) 2021 Elsevier B.V. All rights reserved.
2022 APR 10
WOS:000766809600001
journalArticle
301
ENVIRONMENTAL POLLUTION
DOI 10.1016/j.envpol.2022.119018
Habran
Sarah
Philippart
Christelle
Jacquemin
Pierre
Remy
Suzanne
Mapping agricultural use of pesticides to enable research and environmental health actions in Belgium
Given the many public health and environmental impacts associated with the use of pesticides, comprehensive pesticide application data are a high priority for environmental and health professionals, government agencies, and community groups in Wallonia (Belgium). In that context, geographic information system (GIS) approaches for mapping estimates of agricultural pesticide use were developed in the present study. Data on pesticide application rates and high-resolution annual datasets of the geographic distribution of crops were used to complete this analysis in Wallonia over the period 2015-2017. The method was implemented in Python in order to allow easy update and improvements of maps, or to segment maps by individual pesticides, chemical groups of pesticides (e.g. insecticides, herbicides), etc. Linked databases were created to classify, select, and possibly weight AIs according to specific requests and criteria. The results provide a first map of agricultural pesticide use in Wallonia, which depicts the best picture up to now of their geographic distribution. Maps of fungicides, herbicides, and plant growth regulators showed quite similar spatial patterns as the map of the combination of all pesticides. In contrast, the insecticide map showed a specific pattern related almost exclusively to dwarf-tree orchards in some municipalities in northern Wallonia. This research work is a preliminary result on the spatial characterization of agricultural pesticide use in Wallonia and give a valuable basis for research and environmental health actions in Belgium. Forthcoming developments will focus on exposure characterization to agricultural pesticides using GIS models. Using this information, policymakers will able to detect potential priority zones and take action to check and reduce agricultural pesticide loads in the environment.
2022 MAY 15
WOS:000789350100005
journalArticle
10
PEERJ
DOI 10.7717/peerj.12870
Traba
Juan
Perez-Granados
Cristian
Extensive sheep grazing is associated with trends in steppe birds in Spain: recommendations for the Common Agricultural Policy
Iberian natural steppes have traditionally been used for extensive sheep grazing, which has been noted to be positively associated with steppe bird abundance and diversity. Sheep numbers in Spain, which harbors the largest European populations of many steppe bird species, decreased by 9.2 million (37.3%) between 1992 and 2020. Steppe birds in Spain have faced dramatic declines during the same period, but there is a lack of knowledge about the potential association between sheep and open-habitat bird declines. We used sheep data from the Spanish Ministry of Agriculture and bird data (1998-2018) from the Spanish Common Bird Monitoring Program to assess the association at the Spanish scale between sheep decline and the Farmland Bird Index (FBI) and the Natural Shrub-steppe Bird Index (SBI). We also used an independent dataset on population trends of the Dupont's Lark (Chersophilus duponti) to assess the relationship between sheep numbers and the decline of this threatened steppe specialist passerine in Spain, whose European population is restricted to Iberian natural steppes. To test for a spurious relationship between temporal series, variables were tested for cointegration. After confirming cointegration, we found a strong positive relationship between sheep abundance and the trends of the FBI and SBI indices during the period 1998-2018. The association between sheep abundance and trends of the Dupont's Lark (2004-2015) was positive although it was not statistically significant. Although the main causes of decline of farmland and steppe birds are mainly related to agricultural intensification and land use changes, the correlation found, using two independent cointegrated datasets, between the reduction in farmland and shrub-steppe birds and sheep numbers at the country scale suggests that the decline of steppe birds in Spain may be also associated with the decline in sheep numbers. This agrees with previous studies that found a positive relationship between intermediate levels of sheep grazing and steppe bird abundance in Iberian steppes. Further research (e.g. experimental studies) is needed to corroborate our study and identify the most appropriate level of grazing intensity for protecting the most farmland and shrub-steppe birds. Our results suggest that the promotion of extensive grazing should be considered as a key factor in future Common Agricultural Policy reforms and conservation programmes to protect steppe birds.
2022 FEB 28
WOS:000766812300002
journalArticle
174
PHYSIOLOGIA PLANTARUM
DOI 10.1111/ppl.13672
2
Wang
Juexin
Sidharth
Sen
Zeng
Shuai
Jiang
Yuexu
Chan
Yen On
Lyu
Zhen
McCubbin
Tyler
Mertz
Rachel
Sharp
Robert E.
Joshi
Trupti
Bioinformatics for plant and agricultural discoveries in the age of multiomics: A review and case study of maize nodal root growth under water deficit
Advances in next-generation sequencing and other high-throughput technologies have facilitated multiomics research, such as genomics, epigenomics, transcriptomics, proteomics, metabolomics, and phenomics. The resultant emerging multiomics data have brought new challenges as well as opportunities, as seen in the plant and agriculture science domains. We reviewed several bioinformatic and computational methods, models, and platforms, and we have highlighted some of our in-house developed efforts aimed at multiomics data analysis, integration, and management issues faced by the research community. A case study using multiomics datasets generated from our studies of maize nodal root growth under water deficit stress demonstrates the power of these datasets and some other publicly available tools. This analysis also sheds light on the landscape of such applied bioinformatic tools currently available for plant and crop science studies and introduces emerging trends and how they may affect the future.
2022 MAR
WOS:000787837300038
journalArticle
46
ECONOMICS & HUMAN BIOLOGY
DOI 10.1016/j.ehb.2022.101122
Angioloni
Simone
Jack
Claire
Farm fatalities in Northern Ireland agriculture: What fifty years of data tell us
Agriculture is one of the most hazardous sectors in terms of fatal and non-fatal accidents. This paper utilises an administrative dataset that recorded farm fatalities in Northern Ireland over a 50 year timeframe (1968-2017) to undertake an age-period analysis of accident related mortality rates by sex, cause of death, season, and day of the week. Public policies aimed to improve farm safety should consider that fatalities due to animals have increased while the incidence of deaths due to vehicles and equipment has substantially decreased over the years although it is still the primary cause of death. With respect to age, elderly still actively involved in farming and children in the spring and at week-ends are most exposed to the risk of a fatal accident. Overall, men die on farms five times more than women.
2022 AUG
WOS:000792184000006
journalArticle
830
SCIENCE OF THE TOTAL ENVIRONMENT
DOI 10.1016/j.scitotenv.2022.154810
Delavar
Majid
Eini
Mohammad Reza
Kuchak
Vahid Shokri
Zaghiyan
Mohammad Reza
Shahbazi
Ali
Nourmohammadi
Farhad
Motamedi
Ali
Model-based water accounting for integrated assessment of water resources systems at the basin scale
Agricultural activities in the concept of integrated water resources management play a vital role. Especially in dry and semi-dry regions, agricultural activities have the largest share of water consumption. By employing a model-based approach using modified Soil and Water Assessment Tool (SWAT agro-hydrological model), this study has prepared Water Accounting Plus (WA+) framework requirements to investigate different conditions of supply and demand in wet (1985-2000) and dry (2001-2015) periods in a semi-dry basin (Karkheh River Basin) in Iran. Our assessments based on WA+ show decreasing 10% (21.65 to 19.29 Billion Cubic Meters (BCM)/year) of precipitation in the dry period caused a 4% (0.13 BCM/year) decline in natural evapotranspiration. However, the basin experienced a 24% increment in evapotranspiration from agricultural activities at the same period, and runoff was approximately halved (2.45 BCM/year). Therefore, especially in downstream parts, surface water withdrawal has decreased by 18%. These new conditions have put pressure on groundwater resources. The aquifer extraction and total withdrawal for irrigation have grown by about 17% and 4%, respectively. Finally, it is evident that the manageable water has diminished due to climate change; not only the managed water consumption in the basin has not reduced, but it has also highly risen. The current study results help water authorities arrange new hydrological and climatic conditions strategies.
2022 JUL 15
WOS:000804452800011
journalArticle
19
INTERNATIONAL JOURNAL OF ENVIRONMENTAL RESEARCH AND PUBLIC HEALTH
DOI 10.3390/ijerph19084753
8
Raza
Muhammad Haseeb
Abid
Muhammad
Faisal
Muhammad
Yan
Tingwu
Akhtar
Shoaib
Adnan
K. M. Mehedi
Environmental and Health Impacts of Crop Residue Burning: Scope of Sustainable Crop Residue Management Practices
The burning of crop residue in the open field has become a significant concern for climate change mitigation efforts worldwide. This practice has led to air quality impairment, smog, haze, heat waves, and different health problems. These could be avoided by adopting sustainable crop residue management practices (SCRMPs) and enabling farmers to engage in SCRMPs. Assessing the health effects at the household level is critical for understanding this problem and finding a solution. Using the primary dataset of 420 farmers from Punjab, Pakistan, we estimated the incurred impacts and costs of crop residue burning. We calculated the health and environmental benefits associated with adopting SCRMPs by comparing the two groups of farmers (adopters and non-adopters). Furthermore, we used a propensity score matching technique to measure the causal impact of SCRMPs adoption on health costs. The findings showed that a surprisingly large number of farmers are all aware of the adverse effects of residue burning, and many do not burn crop residues and instead use SCRMPs. This study found that households with chronic and non-chronic diseases become acute, and the severity increases during the burning period. They spend USD 13.37 to USD 8.79 on chronic and non-chronic diseases during the burning season, respectively. Consequently, the use of SCRMPs has a positive effect on healthcare costs. Our study findings highlight the meaningful implications for developing a new policy to promote the sustainable utilization of crop residues and enhance their adoption in Pakistan.
2022 APR
WOS:000786281700001
journalArticle
7
IEEE Access
DOI 10.1109/ACCESS.2019.2906665
IEEE Access
ISSN 2169-3536
F. Hao
J. Cheng
L. Wang
J. Cao
Agriculture
Economics
Forestry
Fluctuations
Attention adaptation module
Companies
deep neural networks
few-shot learning
Switches
Uncertainty
Instance-Level Embedding Adaptation for Few-Shot Learning
Few-shot learning aims to recognize novel categories from just a few labeled instances. Existing metric learning-based approaches perform classifications by nearest neighbor search in the embedding space. The embedding function is a deep neural network and usually shared by all novel categories. However, these brute approaches lack a fast adaptation mechanism like meta-learning when dealing with novel categories. To tackle this, we present a novel instance-level embedding adaptation mechanism, aiming at rapidly adapting embedding deep features to improve their generalization ability in recognizing novel categories. To this end, we design an Attention Adaptation Module to pull a query instance and its corresponding class center as close as possible. Note that, each query instance is pulled closer to its corresponding class center before performing nearest neighbor classifications. This instance-level reduction of intra-class distance increases the probability of correct classifications, and thus improves the generalization ability to embed deep features and promoting the performance. The extensive experiments are conducted on two benchmark datasets: miniImageNet and CUB. Our approach yields very promising results on both datasets. In addition, in a realistic cross-domain evaluation setting, our method also achieves the-state-of-the-art performance.
2019
100501-100511
journalArticle
10
IEEE Access
DOI 10.1109/ACCESS.2022.3182806
IEEE Access
ISSN 2169-3536
F. Xu
J. Gao
X. Pan
Feature extraction
Neural networks
Capsule network
Correlation coefficient
cow face recognition
Face recognition
individual recognition
Network architecture
one-shot learning
Pearson correlation coefficient
Siamese neural network
Cow Face Recognition for a Small Sample Based on Siamese DB Capsule Network
Dairy cow face recognition using Neural Networks has several hurdles. For example, there are only a few instances of each individual. The positions and angles of the individuals in the image fluctuate considerably, the differences between individuals are not apparent, and the number of individuals that the network has not been trained on is enormous, etc. In this paper, an enhanced Siamese Neural Network is used to overcome these barriers. First, a combination of Dense Block (DB) and Capsule Network is employed as a feature extractor to keep the spatial information of features while expanding the feature extraction capabilities of the Convolutional Neural Network. Second, image pairings are processed through the Siamese Neural Network to obtain bivariate features. Finally, image recognition is achieved via the correlation analysis of bivariate features. We conduct comparison experiments with different networks on a small cow face dataset. The experimental results demonstrate that Siamese DB Capsule Network can learn abstract knowledge about distinct individuals and can be extended to unfamiliar cows for zero-shot learning.
2022
63189-63198
journalArticle
8
IEEE Access
DOI 10.1109/ACCESS.2020.2981950
IEEE Access
ISSN 2169-3536
Y. Peng
Y. Song
W. Huang
H. Deng
Y. Wang
Q. Chen
M. Liao
J. Hua
Feature extraction
Computer vision
Task analysis
Convolution
Image recognition
Ear
Computational efficiency
Cross-layer bilinear
fine-grained recognition
self-layer bilinear
Self-Layer and Cross-Layer Bilinear Aggregation for Fine-Grained Recognition in Cyber-Physical-Social Systems
Cyber-Physical-Social Systems (CPSS) integrates cyber, physical and social spaces together, which makes our lives more convenient and intelligent by providing personalized service. In this paper, we will provide CPSS service for fine-grained recognition. Fine-grained visual recognition is a hot but challenging research in computer vision that aims to recognize object subcategories. The reason why it is challenging is that it extremely depends on the subtle discriminative features of local parts. Recently, some bilinear feature based methods were proposed, and the experimental results show state-of-the-art performance. However, most of them neglect the spatial relationships of part-region feature among multiple layers. In this paper, a novel approach of Self-layer and Cross-layer Bilinear Aggregation(SCBA) is proposed for fine-grained recognition. Firstly, a self-layer bilinear feature fusion module is proposed to model the spatial relationship of feature at the same layer. Secondly, we propose a cross-layer bilinear feature fusion module to capture the inter-layer interreaction of information to boost the ability of feature representation. In summary, the method we proposed not only can learn the correlations among different layers but the same layer, which makes it efficient and the experimental results show that it achieves state-of-the-art accuracy on three common fine-grained image datasets.
2020
55826-55833
journalArticle
7
IEEE Access
DOI 10.1109/ACCESS.2019.2916931
IEEE Access
ISSN 2169-3536
Y. Li
J. Jia
L. Zhang
A. M. Khattak
S. Sun
W. Gao
M. Wang
Feature extraction
Deep learning
Agriculture
Task analysis
Convolution
Neural networks
Convolution neural network
density map
Digital images
Gaussian kernel
pod image
soybean seed counting
Soybean Seed Counting Based on Pod Image Using Two-Column Convolution Neural Network
China’s soybean supply and demand are seriously imbalanced. It is crucial to improve the level of soybean breeding. Hundred-grain weight is one of the most essential phenotypic parameters for crop breeding. Accurate soybean seed counting is a key step for 100-grain weight. There are several seed counting methods, which have their own limitations one way or the other. Among these, manual counting is time-consuming, electronic automatic seed counter devices are expensive and their counting speed is very slow, and the traditional digital image processing techniques are not suitable for seed counting based on individual pod images. This paper attempted to develop a method that would combine the density estimation-based methods and the convolution neural network (CNN)-based methods to accurately estimate the seed count from an individual soybean pod image with a single perspective. In this paper, we first introduced a new large-scale seed counting dataset, named Soybean-pod. The dataset contains 500 annotated pod images with a total of 32 126 seeds and is the largest annotated dataset for soybean seed counting so far. Simultaneously, we used annotation information to generate a ground-truth density map by convolving a Gaussian kernel and, then, devised a simple but effective method that would elucidate pod images to a seed density map using a two-column CNN (TCNN) and thus accomplish seed counting ultimately. We conducted relevant experiments from three aspects on the new dataset to verify the effectiveness of our model and method, which provided 13.21 mean absolute error (MAE) and 17.62 mean squared error (mse). In addition, our research results showed that deep learning techniques can be easily adapted to precision tasks for plant phenotyping and breeding purposes.
2019
64177-64185
journalArticle
C. Wang
J. Xue
K. Lu
Y. Yan
Feature extraction
Computer architecture
Training
Task analysis
attention mechanism
Faces
Face recognition
deep neural network
Facial expression recognition
Videos
Light Attention Embedding for Facial Expression Recognition
Facial expression recognition is important for human–computer interaction and other applications. Several facial expression datasets have been published in recent decades and have enabled improvements in algorithms for classifying emotions. However, recognition of realistic expressions in real-world conditions is still challenging because of uncontrolled conditions, such as lighting, brightness, pose, and occlusion. In this paper, we propose a light attention embedding network based on the spatial attention mechanism (LAENet-SA), which can focus on locations in an image that are relevant to emotion. LAENet-SA allows a small number of attention modules to be embedded and can be constructed from typical convolutional neural networks. The performance of LAENet-SA on facial expression recognition has been validated on three facial expression datasets, including a lab-controlled dataset and two in-the-wild datasets. Experimental results show that LAENet-SA improved the performance on each dataset, compared with state-of-the-art methods, and achieved better generalization when tested on facial images with occlusion.
April 2022
1834-1847
32
IEEE Transactions on Circuits and Systems for Video Technology
DOI 10.1109/TCSVT.2021.3083326
4
IEEE Transactions on Circuits and Systems for Video Technology
ISSN 1558-2205
journalArticle
4
IEEE Robotics and Automation Letters
DOI 10.1109/LRA.2019.2901987
3
IEEE Robotics and Automation Letters
ISSN 2377-3766
X. Liu
S. W. Chen
C. Liu
S. S. Shivakumar
J. Das
C. J. Taylor
J. Underwood
V. Kumar
Vegetation
Cameras
object detection
Semantics
Three-dimensional displays
Pipelines
Robot sensing systems
Robotics in agriculture and forestry
segmentation and categorization
deep learning in robotics and automation
Laser radar
mapping
visual tracking
Monocular Camera Based Fruit Counting and Mapping With Semantic Data Association
In this letter, we present a cheap, lightweight, and fast fruit counting pipeline. Our pipeline relies only on a monocular camera, and achieves counting performance comparable to a state-of-the-art fruit counting system that utilizes an expensive sensor suite including a monocular camera, LiDAR and GPS/INS on a mango dataset. Our pipeline begins with a fruit and tree trunk detection component that uses state-of-the-art convolutional neural networks (CNNs). It then tracks fruits and tree trunks across images, with a Kalman Filter fusing measurements from the CNN detectors and an optical flow estimator. Finally, fruit count and map are estimated by an efficient fruit-as-feature semantic structure from motion algorithm that converts two-dimensional (2-D) tracks of fruits and trunks into 3-D landmarks, and uses these landmarks to identify double counting scenarios. There are many benefits of developing such a low cost and lightweight fruit counting system, including applicability to agriculture in developing countries, where monetary constraints or unstructured environments necessitate cheaper hardware solutions.
July 2019
2296-2303
journalArticle
8
IEEE Internet of Things Journal
DOI 10.1109/JIOT.2021.3050775
21
IEEE Internet of Things Journal
ISSN 2327-4662
K. H. Abdulkareem
M. A. Mohammed
A. Salim
M. Arif
O. Geman
D. Gupta
A. Khanna
Support vector machines
machine learning (ML)
Artificial intelligence
Hospitals
Internet of Things
random forest (RF)
Internet of Things (IoT)
support vector machine
COVID-19
laboratory findings
Medical services
naive Bayes
Pandemics
smart hospital environment
Realizing an Effective COVID-19 Diagnosis System Based on Machine Learning and IoT in Smart Hospital Environment
The aim of this study is to propose a model based on machine learning (ML) and Internet of Things (IoT) to diagnose patients with COVID-19 in smart hospitals. In this sense, it was emphasized that by the representation for the role of ML models and IoT relevant technologies in smart hospital environment. The accuracy rate of diagnosis (classification) based on laboratory findings can be improved via light ML models. Three ML models, namely, naive Bayes (NB), Random Forest (RF), and support vector machine (SVM), were trained and tested on the basis of laboratory datasets. Three main methodological scenarios of COVID-19 diagnoses, such as diagnoses based on original and normalized datasets and those based on feature selection, were presented. Compared with benchmark studies, our proposed SVM model obtained the most substantial diagnosis performance (up to 95%). The proposed model based on ML and IoT can be served as a clinical decision support system. Furthermore, the outcomes could reduce the workload for doctors, tackle the issue of patient overcrowding, and reduce mortality rate during the COVID-19 pandemic.
1 Nov.1, 2021
15919-15928
journalArticle
15
IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
DOI 10.1109/JSTARS.2022.3177235
IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
ISSN 2151-1535
M. Liu
Z. Chai
H. Deng
R. Liu
Feature extraction
remote sensing
Biological system modeling
Task analysis
transformer
Transformers
Decoding
deep learning (DL)
Data mining
Change detection (CD)
cropland
Head
A CNN-Transformer Network With Multiscale Context Aggregation for Fine-Grained Cropland Change Detection
Nonagriculturalization incidents are serious threats to local agricultural ecosystem and global food security. Remote sensing change detection (CD) can provide an effective approach for in-time detection and prevention of such incidents. However, existing CD methods are difficult to deal with the large intraclass differences of cropland changes in high-resolution images. In addition, traditional CNN based models are plagued by the loss of long-range context information, and the high computational complexity brought by deep layers. Therefore, in this article, we propose a CNN-transformer network with multiscale context aggregation (MSCANet), which combines the merits of CNN and transformer to fulfill efficient and effective cropland CD. In the MSCANet, a CNN-based feature extractor is first utilized to capture hierarchical features, then a transformer-based MSCA is designed to encode and aggregate context information. Finally, a multibranch prediction head with three CNN classifiers is applied to obtain change maps, to enhance the supervision for deep layers. Besides, for the lack of CD dataset with fine-grained cropland change of interest, we also provide a new cropland change detection dataset, which contains 600 pairs of 512 × 512 bi-temporal images with the spatial resolution of 0.5–2m. Comparative experiments with several CD models prove the effectiveness of the MSCANet, with the highest F1 of 64.67% on the high-resolution semantic CD dataset, and of 71.29% on CLCD.
2022
4297-4306
journalArticle
8
IEEE Access
DOI 10.1109/ACCESS.2020.3039345
IEEE Access
ISSN 2169-3536
G. Yang
G. Chen
Y. He
Z. Yan
Y. Guo
J. Ding
Feature extraction
Diseases
Object detection
Training
Agriculture
Image classification
Annotations
Fine-grained visual categorization
multi-network
self-supervised
tomato diseases
Self-Supervised Collaborative Multi-Network for Fine-Grained Visual Categorization of Tomato Diseases
Artificial recognition of tomato diseases is often time-consuming, laborious and subjective. For tomato disease images, it is difficult to find small discriminative features between different tomato diseases, which can bring challenges to fine-grained visual categorization of tomato leaf-based images. Therefore, we propose a novel model, which consists of 3 networks, including a Location network, a Feedback network, and a Classification network, named LFC-Net. At the same time, a self-supervision mechanism is proposed in the model, which can effectively detect informative regions of tomato image without the need for manual annotation such as bounding boxes/parts. Based on the consideration of the consistency between category of the image and informativeness of the image, we design a novel training paradigm. The Location network of the model first detects informative regions in the tomato image, and optimizes iterations under the guidance of the Feedback network. Then, the Classification network uses informative regions proposed by the Location network and the full image of the tomato for classification. Our model can be regarded as a multi-network collaboration, and networks can progress together. Compared with the pre-trained model on ImageNet, our model achieves the most advanced performance in the tomato dataset, with accuracy up to 99.7%. This work demonstrates that our model has a high accuracy and has the potential to be applied to other vegetable and fruit datasets, which can provide a reference for the prevention and control of tomato diseases.
2020
211912-211923
journalArticle
G. Guo
H. Wang
C. Shen
Y. Yan
H. -Y. M. Liao
Feature extraction
Computer vision
convolutional neural network
Training
Agriculture
Visualization
cascaded cropping regression
Image cropping
random-ferns regressor
Automatic Image Cropping for Visual Aesthetic Enhancement Using Deep Neural Networks and Cascaded Regression
Despite recent progress, computational visual aesthetic is still challenging. Image cropping, which refers to the removal of unwanted scene areas, is an important step to improve the aesthetic quality of an image. However, it is challenging to evaluate whether cropping leads to aesthetically pleasing results because the assessment is typically subjective. In this paper, we propose a novel cascaded cropping regression (CCR) method to perform image cropping by learning the knowledge from professional photographers. The proposed CCR method improves the convergence speed of the cascaded method, which directly uses random-ferns regressors. In addition, a two-step learning strategy is proposed and used in the CCR method to address the problem of lacking labelled cropping data. Specifically, a deep convolutional neural network (CNN) classifier is first trained on large-scale visual aesthetic datasets. The deep CNN model is then designed to extract features from several image cropping datasets, upon which the cropping bounding boxes are predicted by the proposed CCR method. Experimental results on public image cropping datasets demonstrate that the proposed method significantly outperforms several state-of-the-art image cropping methods.
Aug. 2018
2073-2085
20
IEEE Transactions on Multimedia
DOI 10.1109/TMM.2018.2794262
8
IEEE Transactions on Multimedia
ISSN 1941-0077
journalArticle
21
IEEE Sensors Journal
DOI 10.1109/JSEN.2020.3046295
16
IEEE Sensors Journal
ISSN 1558-1748
M. Kumar
A. Kumar
V. S. Palaparthy
Diseases
Soil moisture
Agriculture
Pathogens
Temperature sensors
Sensors
Artificial neural network
Data analysis
multi-label classification
plant diseases
soil based sensors
Soil Sensors-Based Prediction System for Plant Diseases Using Exploratory Data Analysis and Machine Learning
Plant diseases cause losses to agricultural production and hence, the economy. This necessitates a need to develop prediction models for the plant disease detection and assessment. Fungal infection, the most dominant disease, can be controlled by taking appropriate measures if detected at an early stage. The article aims to develop an expert system for the prediction of various fungal diseases (powdery mildew, anthracnose, rust, and root rot/leaf blight). A multi-layered perceptron model is used for the classification of the diseases which not only detects the plant diseases effectively but can also increase the production drastically. The proposed technique incorporates three significant steps of dataset pre-processing, exploratory data analysis, and detection module. Firstly, the real-time data is captured by the soil sensors system installed at agriculture field at Sardarkrushinagar Dantiwada Agricultural University, Gujarat, India, along with the satellite data for other micro-meteorological factors. Next, an extensive exploratory data analysis has been performed to get insights into the collected data. Finally, the proposed machine learning model has been employed to predict plant diseases. The experimental results indicate that the model outperforms several existing methods in terms of accuracy. Average accuracy in predicting each disease has been found more than 98%. This work also proves the feasibility of using this technique for faster plant disease detection at an affordable cost.
15 Aug.15, 2021
17455-17468
journalArticle
10
IEEE Access
DOI 10.1109/ACCESS.2022.3200688
IEEE Access
ISSN 2169-3536
R. R. Patil
S. Kumar
Crops
Feature extraction
Deep learning
Diseases
Agriculture
Transformers
Data integration
cross attention
data fusion
Image sensors
multimodal
rice diseases
Rice transformer
self attention
Rice Transformer: A Novel Integrated Management System for Controlling Rice Diseases
Rice disease classification is vital during the cultivation of rice crops. However, rice diseases were initially detected by visual examination from agricultural experts. Later the detection process progressed to automation, which involved images. The images captured lead to a lack of supporting information. The traditional approaches are less accurate when used with real time images. To address this limitation, a novel Rice Transformer is proposed in the paper that merges inputs from agricultural sensors and image data captured from the fields simultaneously. The proposed system consists of two branches: the sensor and image branches. Specifically, the attention approach is employed to extract the features from both modalities. Later, the extracted features are sent to the cross-attention module as input in a crisscross fashion, enhancing the ability to identify the features specific to rice diseases. The extracted features are further pooled, merged, and later passed through the Softmax classifier to classify the rice disease precisely. The dataset collected is a customized dataset with 4200 samples collected on a real-time basis from rice farms. The experiments conducted on the dataset represent that the proposed approach outperforms all the other fusion and attention models considered for comparison in this paper. The ablation analysis and performance metrics are measured to determine the effectiveness of the proposed system. The results achieved are quite promising as the proposed Rice transformer model achieves an accuracy of 97.38% for controlling rice disease.
2022
87698-87714
journalArticle
8
IEEE Access
DOI 10.1109/ACCESS.2020.3039011
IEEE Access
ISSN 2169-3536
D. Yao
X. Deng
Biological system modeling
Task analysis
Predictive models
Prediction algorithms
Matrix decomposition
Sparse matrices
Education
course characteristics
FCTR-LFM
sparse evaluation matrix
Teacher characteristics
teaching quality
TOP-N recommendation
Teaching Teacher Recommendation Method Based on Fuzzy Clustering and Latent Factor Model
Colleges and universities attach great importance to the quality of undergraduate teaching. To virtually guarantee the course's teaching quality, the key lies in recommending suitable teachers for the course scientifically. It is a seemingly simple but very complicated problem. Moreover, with the development of colleges and universities, new courses are continually set up, and new teachers are introduced, which further complicates the problem. The problem has not been solved well for many years. Therefore, we propose a course teacher recommendation model (FCTR-LFM) based on fuzzy clustering and the latent factor model (LFM) to solve this problem. Firstly, under the guidance of pedagogy theories and methods, we conduct quantitative modeling for teachers and courses' relevant characteristics and combine the quantitative results with historical teaching scores to establish a large-scale sparse course teaching evaluation matrix as the recommendation dataset. Next, we adopt the improved fuzzy clustering model to realize teachers' automatic clustering according to their characteristics and use the teacher cluster to reconstruct the teaching evaluation matrix, significantly reducing the dataset's size and reducing the sparsity. Then, we used the improved LFM to predict the score items in the evaluation matrix, including the missing score items. Finally, the prediction evaluation scores are sorted according to the course, and the TOP-N recommendation of the course teachers is realized. The experimental results show that FCTR-LFM can realize the prediction and recommendation well using the optimized parameters. It effectively solves the problem that there is no scientific basis for recommending suitable teachers for the course for a long time.
2020
210868-210885
journalArticle
8
IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
DOI 10.1109/JSTARS.2015.2452955
12
IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
ISSN 2151-1535
D. Li
T. Zhao
J. Shi
R. Bindlish
T. J. Jackson
B. Peng
M. An
B. Han
Microwave radiometry
Soil moisture
soil moisture (SM)
Data assimilation
Aquarius
global land data assimilation system (GLDAS)
international soil moisture network (ISMN)
L-band
soil climate analysis network (SCAN)
validation
First Evaluation of Aquarius Soil Moisture Products Using In Situ Observations and GLDAS Model Simulations
L-band satellite remote sensing is one of the most promising techniques for global monitoring of soil moisture (SM). In addition to soil moisture and ocean salinity (SMOS) SM products, another global SM product has been developed using Aquarius, which is the first operational active/passive L-band satellite sensor. The spatial resolution of Aquarius SM products is about 100 km, which presents more challenges to the groundbased validation. This study explores approaches to validate and evaluate the Aquarius SM products in terms of their spatial and temporal distributions, through synergistic use of in situ measurements and model products from the global land data assimilation system (GLDAS). A dense soil moisture/temperature monitoring network over the central Tibetan plateau (CTP-SMTMN) and sparse stations from the soil climate analysis network (SCAN) over United States are used for the reliability assessment of Aquarius SM products. Results show that the Aquarius SM captures the spatial-temporal variability of CTP-SMTMN reference dataset with an overall RMSD of 0.078 m3 · m-3 and correlation coefficient of 0.767. The comparison results with reference to SCAN datasets suggest that the RMSD can reach to the target value of 0.04 m3 · m-3 over specific stations, but the impacts from different orbits, seasons, and land cover types are also found to be significant. The comparison between Aquarius retrievals and GLDAS/common land model (CLM) simulations presents a general well statistical agreement with correlation coefficients above 0.5 for most terrestrial areas. These results are considered to support the use of Aquarius SM products in future applications.
Dec. 2015
5511-5525
journalArticle
8
IEEE Access
DOI 10.1109/ACCESS.2020.2998839
IEEE Access
ISSN 2169-3536
B. Liu
C. Tan
S. Li
J. He
H. Wang
Feature extraction
Diseases
Generative adversarial networks
data augmentation
Training
convolutional neural networks
Generators
Pipelines
Gallium nitride
grape leaf disease identification
A Data Augmentation Method Based on Generative Adversarial Networks for Grape Leaf Disease Identification
The identification of grape leaf diseases based on deep learning is critical to controlling the spread of diseases and ensuring the healthy development of the grape industry. Focusing on the lack of training images of grape leaf diseases, this paper proposes a novel model named Leaf GAN, which is based on generative adversarial networks (GANs), to generate images of four different grape leaf diseases for training identification models. A generator model with degressive channels is first designed to generate grape leaf disease images; then, the dense connectivity strategy and instance normalization are fused into an efficient discriminator to identify real and fake disease images by utilizing their excellent feature extraction capability on grape leaf lesions. Finally, the deep regret gradient penalty method is applied to stabilize the training process of the model. Using a total of 4,062 grape leaf disease images, the Leaf GAN model ultimately generates 8,124 grape leaf disease images. The generated grape leaf disease images based on Leaf GAN model can obtain better performance than DCGAN and WGAN in terms of the Fréchet inception distance. The experimental results show that the proposed Leaf GAN model generates sufficient grape leaf disease images with prominent lesions, providing a feasible solution for the data augmentation of grape leaf disease images. For the eight prevailing classification models with the expanded dataset, the identification performance based on CNNs indicated higher accuracies, whereby all the accuracies were better than those of the initial dataset with other data augmentation methods. Among them, Xception achieves a recognition accuracy of 98.70% on the testing set. The results demonstrate that the proposed data augmentation method represents a new approach to overcoming the overfitting problem in disease identification and can effectively improve the identification accuracy.
2020
102188-102198
journalArticle
15
IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
DOI 10.1109/JSTARS.2022.3206399
IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
ISSN 2151-1535
W. Liu
K. Quijano
M. M. Crawford
Feature extraction
Deep learning
Object detection
Agriculture
transfer learning
Transfer learning
Head
CenterNet
Neck
SimAM attention module
small tassel detection
YOLOv5
YOLOv5-Tassel: Detecting Tassels in RGB UAV Imagery With Improved YOLOv5 Based on Transfer Learning
Unmanned aerial vehicles (UAVs) equipped with lightweight sensors, such as RGB cameras and LiDAR, have significant potential in precision agriculture, including object detection. Tassel detection in maize is an essential trait given its relevance as the beginning of the reproductive stage of growth and development of the plants. However, compared with general object detection, tassel detection based on RGB imagery acquired by UAVs is more challenging due to the small size, time-dependent variable shape, and complexity of the objects of interest. A novel algorithm referred to as YOLOv5-tassel is proposed to detect tassels in UAV-based RGB imagery. A bidirectional feature pyramid network is adopted for the path-aggregation neck to effectively fuse cross-scale features. The robust attention module of SimAM is introduced to extract the features of interest before each detection head. An additional detection head is also introduced to improve small-size tassel detection based on the original YOLOv5. Annotation is performed with guidance from center points derived from CenterNet to improve the selection of the bounding boxes for tassels. Finally, to address the issue of limited reference data, transfer learning based on the VisDrone dataset is adopted. Testing results for our proposed YOLOv5-tassel method achieved the mAP value of 44.7%, which is better than well-known object detection approaches, such as FCOS, RetinaNet, and YOLOv5.
2022
8085-8094
journalArticle
10
IEEE Access
DOI 10.1109/ACCESS.2022.3196935
IEEE Access
ISSN 2169-3536
X. Xie
R. Zhang
L. Peng
S. Peng
Convolutional neural networks
Feature extraction
convolutional neural network
Image segmentation
Real-time systems
Convolution
Semantics
Object segmentation
semantic segmentation
Appearance defect detection
small defect samples
A Four-Stage Product Appearance Defect Detection Method With Small Samples
With the automation of industrial production, appearance defect detection based on machine vision plays an important role in product quality control. The scarcity of defect samples and real-time requirement are the main challenges in this field. Many existing studies are based on semantic segmentation network, but they cannot provide a classification confidence score for each image and only report the segmentation tasks metrics, which ignore that the positive or negative decisions are the key of defect detection. Therefore, this paper proposes a four-stage appearance defect detection model: contrast enhancement, segmentation, correction, and decision, which can achieve high detection accuracy with a severe shortage of positive samples. Since the proposed model simplifies U-Net to segment those candidate defect regions, and constructs a lightweight decision network based on the candidate regions and segmented mask, the proposed method not only achieves fast inference speed, but also obtain good performance with fewer defect samples. Experiments are implemented on three public datasets: magnetic tile dataset, Kolektor surface defect dataset and DAGM2007 dataset. The influence of each module on the detection accuracy is analyzed. Experimental results show that the proposed model achieves excellent performance comparing with other state-of-art methods.
2022
83740-83754
journalArticle
10
IEEE Access
DOI 10.1109/ACCESS.2022.3211961
IEEE Access
ISSN 2169-3536
Y. Du
H. Liu
S. Chen
Convolutional neural networks
Image edge detection
Semantics
Image reconstruction
Learning systems
Cognition
Image recognition
Collaboration
contrastive learning
generative model
Image inpainting
semantic reasoning
Collaborative Contrastive Learning-Based Generative Model for Image Inpainting
The critical challenge of image inpainting is to infer reasonable semantics and textures for a corrupted image. Typical methods for image inpainting are built upon some prior knowledge to synthesize the complete image. One potential limitation is that those methods often remain undesired blurriness or semantic mistakes in the synthesized image while handling images with large corrupted areas. In this paper, we propose a Collaborative Contrastive Learning-based Generative Model (C2LGM), which learns the content consistency in the same image to ensure that the inferred content of corrupted areas is reasonable compared to the known content by pixel-level reconstruction and high-level semantic reasoning. C2LGM leverages the encoder-decoder based framework to directly learn the mapping from the corrupted image to the intact image and perform the pixel-level reconstruction. To perform semantic reasoning, our C2LGM introduces a Collaborative Contrastive Learning (C2L) mechanism that learns high-level semantic consistency between inferred and known content. Specifically, C2L mechanism introduces the high-frequency edge maps to participate in the process of typical contrastive learning and enables the deep model to ensure the semantic reasonableness between high-frequency structures and pixel-level content by pushing the representations of inferred content and known content close and keeping unrelated semantic content away in the latent feature space. Moreover, C2LGM also directly absorbs the prior knowledge of structural information from the proposed structural spatial attention module, and leverages the texture distribution sampling to improve the quality of synthesized content. As a result, our C2LGM achieves a 0.42 dB improvement over competing methods in terms of the PSNR metric while coping with a $40\thicksim 50$ % corruption ratio in the Places2 dataset. Extensive experiments on three benchmark datasets, including Paris Street View, CelebA-HQ, and Places2, demonstrate the advantages of our proposed C2LGM over other state-of-the-art methods for image inpainting both qualitatively and quantitatively.
2022
106641-106654
journalArticle
8
IEEE Access
DOI 10.1109/ACCESS.2020.3023690
IEEE Access
ISSN 2169-3536
L. Wei
Z. Wang
C. Huang
Y. Zhang
Z. Wang
H. Xia
L. Cao
Monitoring
Vegetation
hyperspectral imagery
Hyperspectral imaging
Rivers
extreme gradient boosting
Transparency
UAV-borne
Water pollution
Transparency Estimation of Narrow Rivers by UAV-Borne Hyperspectral Remote Sensing Imagery
Urban rivers are often narrow, and general remote sensing data cannot meet the needs of water quality monitoring. In the process of monitoring of river water quality by remote sensing, the spectral and spatial dimension of satellite-borne images cannot be taken into consideration at the same time, making fine pollution monitoring of urban rivers difficult. Transparency is one of the core indicators for evaluating water quality, and hyperspectral remote sensing data are rich in spectral information and can be used for quantitative transparency estimation. The application of unmanned aerial vehicles (UAV)remote sensing effectively makes up for the deficiencies in satellite remote sensing monitoring. Aiming at this problem, this paper proposed the use of the eXtreme Gradient Boosting (XGBoost) regression algorithm for the quantitative inversion of urban river transparency. The spatial resolution of the collected imagery is 18.5 cm, which is suitable for urban rivers that are almost ten meters wide. Compared with five traditional empirical models, integrated algorithms such as gradient regression and random forest get much better results. Moreover, the accuracy of transparency estimation using the XGBoost regression algorithm was significantly improved, and the inversion model R2 in both study areas reached over 0.97. Finally, the established transparency inversion models were used to generate transparency distribution maps of the two study areas. The results showed that the distribution of the water transparency was consistent with the results of the field monitoring, indicating that it is feasible to use the XGBoost algorithm for the inversion of urban river transparency in UAV-borne hyperspectral imagery.
2020
168137-168153
journalArticle
6
IEEE Access
DOI 10.1109/ACCESS.2018.2875400
IEEE Access
ISSN 2169-3536
M. Lin
Q. Zhan
Z. Xu
R. Chen
Indexes
Numerical models
Iterative methods
Decision making
consensus
consistency
Fuzzy sets
Hesitant fuzzy set
hesitant multiplicative preference relation
Investment
Laboratories
Group Decision-Making Model With Hesitant Multiplicative Preference Relations Based on Regression Method and Feedback Mechanism
The hesitant multiplicative preference relation (HMPR) was initially put forward in 2013. Utilizing the HMPR, the decision makers can give some possible preference values from the Saaty's 1-9 scale for pairwise comparisons over alternatives. However, until now, there is little research on the consistency and consensus of HMPRs. In this paper, we focus on exploiting the regression method and the feedback mechanism to improve the consistency and consensus for HMPRs and developing an efficient group decision-making model with HMPRs. First, a regression method based on complete consistency is developed to reduce HMPRs to multiplicative preference relations (MPRs). After that, a novel consistency checking and revising method based on the threshold estimation method and the feedback mechanism is given to improve the consistency level of the reduced MPRs. Then, a group consensus index is put forward to calculate the deviation degree between the reduced MPR and the group MPR and it is utilized to develop a consensus reaching process based on the feedback mechanism to improve the group consensus level of the reduced MPRs. Next, a complete group decision-making model with HMPRs is developed to rank all the alternatives and select the best one. Finally, a numerical example with respect to the investment of shared bikes is presented to demonstrate the proposed group decision-making model and then we also compare our proposed model with the existing one.
2018
61130-61150
journalArticle
10
IEEE Access
DOI 10.1109/ACCESS.2022.3196338
IEEE Access
ISSN 2169-3536
X. Y. Kek
C. S. Chin
Y. Li
Convolutional neural networks
convolutional neural network
Adaptation models
Complexity theory
Convolution
Neural networks
Acoustic scene classification
Acoustics
Scattering
wavelet scattering
mobile network
An Intelligent Low-Complexity Computing Interleaving Wavelet Scattering Based Mobile Shuffling Network for Acoustic Scene Classification
The key towards a low complexity model for convolution neural network is in controlling the number of parameters of the network and ensuring that the input representation is not extremely large. Hence, to tackle low complexity for acoustic scene classification (ASC), this paper proposed an enhanced wavelet scattering representation with a combination of mobile network modules and shuffling modules. While wavelet scattering comprises wavelet transform with multiple wavelet scales, the averaging operation to make the wavelet scattering invariant to translation limit the maximum timescale. Hence, wavelet scattering is affected by Heisenberg’s Uncertainty Principle. However, creating an input representation with multiple timescales does not meet the brief of low complexity modelling. Hence, we proposed a simple mixing of the first and second order with different timescales. The result is an input representation with nearly the same dimension as the usual wavelet scattering but with enhanced multiscale. To further leverage the ‘interleaved’ wavelet scattering, this paper presents sub-spectral shuffling inspired by shuffling modules that use stochasticity to improve the model’s generalization. Unlike channel shuffle that shuffles channel-wise and spatial shuffle that shuffles pixel-wise, sub-spectral shuffle aims at shuffling the feature maps frequency-wise with the concept of binning. Each bin is shuffled, so the high-frequency spectrum is shuffled to low-frequency spectrum position. As such, the model learns the general acoustic profile of a scene rather than memorizing what is happening at the low-frequency or high-frequency spectrum is erratic for ASC. In addition, this paper also studied temporal shuffling, which shuffles the feature maps temporal-wise, and evaluated sub-spectral shuffling, temporal shuffling, and channel shuffling individually. Our results demonstrated the superiority of sub-spectral shuffling and the modularity of shuffling modules. We then evaluate various combinations of the three shuffling modules on three acoustic scene classification datasets. Our best model combines the three shuffling modules and achieves 70.6% classification accuracy on DCASE 2021 Task 1a dataset, 82.15% on ESC-50 dataset, 81% on Urbansound8K, with ~65K parameters and a size of 126.6KB. In addition, the inclusion of shuffling modules has increased the model performance. Sub-spectral shuffling is especially useful in improving logloss, a metric used to determine the confidence level of the model.
2022
82185-82201
journalArticle
15
IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
DOI 10.1109/JSTARS.2022.3191544
IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
ISSN 2151-1535
C. Robinson
B. Chugg
B. Anderson
J. M. L. Ferres
D. E. Ho
Convolutional neural networks
deep learning
Training
Agriculture
Image segmentation
Semantics
Standards
convolutional neural networks (CNNs)
semantic segmentation
Concentrated animal feeding operations (CAF- Os)
National Agricultural Imagery Program (NAIP)
poultry barns
Public healthcare
Mapping Industrial Poultry Operations at Scale With Deep Learning and Aerial Imagery
Concentrated animal feeding operations (CAFOs) pose serious risks to air, water, and public health, but have proven to be challenging to regulate. The U.S. Government Accountability Office notes that a basic challenge is the lack of comprehensive location information on CAFOs. We use the U.S. Department of Agriculture's National Agricultural Imagery Program 1 m/pixel aerial imagery to detect poultry CAFOs across the continental USA. We train convolutional neural network models to identify individual poultry barns and apply the best-performing model to over 42 TB of imagery to create the first national open-source dataset of poultry CAFOs We validate the model predictions against held-out validation set on poultry CAFO facility locations from ten hand-labeled counties in California and demonstrate that this approach has significant potential to fill gaps in environmental monitoring.
2022
7458-7471
journalArticle
A. Abdalla
H. Cen
L. Wan
K. Mehmood
Y. He
Feature extraction
Image color analysis
Machine learning
image processing
Fertilizers
plant phenotyping
Stress
Deep feature (DF)
long short-term memory
nutrient status
Potassium
Nutrient Status Diagnosis of Infield Oilseed Rape via Deep Learning-Enabled Dynamic Model
The symptoms of the nutrient stress in plant canopies differ among different growth stages. It is a challenge to develop individual diagnosis models to evaluate the nutrient status for a specific growth stage in time. Therefore, this article encoded spatiotemporal information of plants in a single time-series model to evaluate the nutrient status of oilseed rape more efficiently. Specifically, in this article, we combined the convolutional neural network (CNN) and long short-term memory (LSTM) to classify the oilseed rape crops according to their nutrient status. The model was validated on a large number of sequential images acquired from oilseed rape canopies at different growth stages during a two-year experiment. Different pretrained CNNs were used to extract distinctive features from every time step of sequential images and then, these features were considered as the input of LSTM to classify the oilseed rape into nine classes of nutrient statuses. We demonstrated that the LSTM outperformed the traditional machine-learning method and the deep features showed better performance compared with hand-crafted features. The Inceptionv3-LSTM obtained the highest overall classification accuracy of 95% when tested on the dataset of 2017/2018 and it also provided a good generalization when using a cross-dataset validation, with the highest overall accuracy of 92%. Our proposed approach presents a pathway toward automatic nutrient status diagnosis during the whole life cycle of the plants, and the LSTM technique would play an essential role in the near future for time-series analysis for precision agriculture.
June 2021
4379-4389
17
IEEE Transactions on Industrial Informatics
DOI 10.1109/TII.2020.3009736
6
IEEE Transactions on Industrial Informatics
ISSN 1941-0050
journalArticle
Y. Shen
Y. Zhang
W. Xue
Z. Yue
Genomics
anti-cancer drug sensitivity
Cancer
database
Drugs
Mutation marker
Precision medicine
prediction algorithm
Prediction methods
Sensitivity
dbMCS: A Database for Exploring the Mutation Markers of Anti-Cancer Drug Sensitivity
The identification of mutation markers and the selection of appropriate treatment for patients with specific genome mutations are important steps in the development of targeted therapies and the realization of precision medicine for human cancers. To investigate the baseline characteristics of drug sensitivity markers and develop computational methods of mutation effect prediction, we presented a manually curated online-based database of mutation Markers for anti-Cancer drug Sensitivity (dbMCS). Currently, dbMCS contains 1271 mutations and 4427 mutation-disease-drug associations (3151 and 1276 for sensitivity and resistance, respectively) with their PubMed indexed articles. By comparing the mutations in dbMCS with the putative neutral polymorphisms, we investigated the characteristics of drug sensitivity markers. We found that the mutation markers tend to significantly impact on high-conservative regions both in DNA sequences and protein domains. And some of them presented pleiotropic effects depending on the tumor context, appearing concurrently in the sensitivity and resistance categories. In addition, we preliminarily explored the machine learning-based methods for identifying mutation markers of anti-cancer drug sensitivity and produced optimistic results, which suggests that a reliable dataset may provide new insights and essential clues for future cancer pharmacogenomics studies. dbMCS is available at http://bioinfo.aielab.cc/dbMCS/.
Nov. 2021
4229-4237
25
IEEE Journal of Biomedical and Health Informatics
DOI 10.1109/JBHI.2021.3100424
11
IEEE Journal of Biomedical and Health Informatics
ISSN 2168-2208
journalArticle
9
IEEE Access
DOI 10.1109/ACCESS.2021.3124525
IEEE Access
ISSN 2169-3536
S. Yoa
S. Lee
C. Kim
H. J. Kim
Data models
Feature extraction
computer vision
deep learning
Training
Task analysis
machine learning
Anomaly detection
Uncertainty
self-supervised learning
Supervised learning
Self-Supervised Learning for Anomaly Detection With Dynamic Local Augmentation
Anomaly detection is an important problem for recent advances in machine learning. To this end, many attempts have emerged to detect unknown anomalies of the images by learning representations and designing score functions. In this paper, we propose a simple yet effective framework for unsupervised anomaly detection using self-supervised learning. We extend conventional self-supervised learning for an anomaly detection problem. In anomaly detection, anomalous patterns appear in the local regions of an image, so we employ dynamic local augmentation to generate a negative pair of the images from the normal training dataset. Specifically, in addition to learning the global representation of an image, our framework contrasts a normal sample to a locally augmented sample. To effectively apply the local augmentations regardless of a category or a random location of an image, we use dynamically weighted local augmentations to generate more suitable negative samples. We also present a novel scoring function for detecting unseen anomalous patterns. Our experiment demonstrates the effectiveness of our method, and we show that our framework achieves competitive performance compared to state-of-the-art methods on MVTec Anomaly Detection dataset.
2021
147201-147211
journalArticle
7
IEEE Access
DOI 10.1109/ACCESS.2019.2917063
IEEE Access
ISSN 2169-3536
M. P. Christiansen
N. Teimouri
M. S. Laursen
B. F. Mikkelsen
R. N. Jørgensen
C. A. G. Sørensen
Monitoring
Synthetic aperture radar
Agriculture
Remote sensing
machine learning
Satellites
image classification
Python
Web services
data acquisition
Preprocessed Sentinel-1 Data via a Web Service Focused on Agricultural Field Monitoring
ESA provides Sentinel-1 synthetic aperture radar satellite data freely for research and industry. The Sentinel-1 data have shown the potential for remotely monitoring conditions in individual agricultural fields on a weekly basis. Researchers have access to the same Sentinel-1 dataset, so independent validation should be possible. Well documented studies performed with Sentinel-1 will allow other researchers the ability to reproduce the experiments and either validate or repudiate the presented findings. Based on the current state-of-the-art study, a web service was provided for the agricultural domain, which can be downloaded freely from Github. The running web service provides the ability to monitor local conditions by using the recorded Sentinel-1 information, combined with a priori knowledge from broad acre fields. Correlating the Sentinel-1 data to actual conditions related to a specific application is still a task that individual researchers must perform to utilize the service. In this paper, we present our methodology for converting the Sentinel-1 data to a form that is more accessible to researchers in the agricultural domain. Therefore, the goal of the current study was to make the Sentinel-1 data available efficiently, so that the experts in this field can focus on correlating and comparing it to reference data and measurements collected in the field. The function of the web service is illustrated with concrete application examples in the agricultural domain.
2019
65139-65149
journalArticle
9
IEEE Access
DOI 10.1109/ACCESS.2021.3050296
IEEE Access
ISSN 2169-3536
X. Jin
J. Che
Y. Chen
deep learning
Deep learning
Image color analysis
Training
Agriculture
Image segmentation
Indexes
image processing
color index
genetic algorithms
Image processing
Weed identification
Weed Identification Using Deep Learning and Image Processing in Vegetable Plantation
Weed identification in vegetable plantation is more challenging than crop weed identification due to their random plant spacing. So far, little work has been found on identifying weeds in vegetable plantation. Traditional methods of crop weed identification used to be mainly focused on identifying weed directly; however, there is a large variation in weed species. This paper proposes a new method in a contrary way, which combines deep learning and image processing technology. Firstly, a trained CenterNet model was used to detect vegetables and draw bounding boxes around them. Afterwards, the remaining green objects falling out of bounding boxes were considered as weeds. In this way, the model focuses on identifying only the vegetables and thus avoid handling various weed species. Furthermore, this strategy can largely reduce the size of training image dataset as well as the complexity of weed detection, thereby enhancing the weed identification performance and accuracy. To extract weeds from the background, a color index-based segmentation was performed utilizing image processing. The employed color index was determined and evaluated through Genetic Algorithms (GAs) according to Bayesian classification error. During the field test, the trained CenterNet model achieved a precision of 95.6%, a recall of 95.0%, and a $F_{1}$ score of 0.953, respectively. The proposed index −19R + 24G −2B ≥ 862 yields high segmentation quality with a much lower computational cost compared to the wildly used ExG index. These experiment results demonstrate the feasibility of using the proposed method for the ground-based weed identification in vegetable plantation.
2021
10940-10950
journalArticle
10
IEEE Access
DOI 10.1109/ACCESS.2022.3181970
IEEE Access
ISSN 2169-3536
H. R. Seireg
Y. M. K. Omar
F. E. A. El-Samie
A. S. El-Fishawy
A. Elmahalawy
Crops
Data models
Feature extraction
Computational modeling
Predictive models
Meteorology
Stacking
Bayesian optimization
cascading technique
EMLA
GBR
LGBM
Ridge
stacking technique
wild blueberry yield
XGBoost
Ensemble Machine Learning Techniques Using Computer Simulation Data for Wild Blueberry Yield Prediction
Precision agriculture is a challenging task to achieve. Several studies have been conducted to forecast agricultural yields using machine learning algorithms (MLA), but few studies have used ensemble machine learning algorithms (EMLA). In the current study, we use a dataset generated by a computer simulation program, and meteorological data obtained over 30 years from Maine, United States (USA). The primary goal of this research is to increase the forecast accuracy of the best characteristics for overcoming hunger challenges. We adopted stacking regression (SR) and cascading regression (CR) with a novel combination of MLA based on the wild blueberry dataset. We used features that indicated the best regulation for wild blueberry agroecosystems. Four feature engineering selection techniques are applied, namely variance inflation factor (VIF), sequential forward feature selection (SFFS), sequential backward elimination feature selection (SBEFS), and extreme gradient boosting based on feature importance (XFI). We applied Bayesian optimization on popular MLA to obtain the best hyperparameters to achieve accurate wild blueberry yield prediction. The SR used a two-layer structure: level-0 containing light gradient boosting machine (LGBM), gradient boost regression (GBR) and extreme gradient boosting (XGBoost), and level-1 providing the output prediction using a Ridge. The CR topology is the same MLA used in SR, but in a series form that takes the new prediction as a feeder to each MLA and removes the previous prediction in each stage. We assessed the CR, and SR with outcomes according to the root mean square error (RMSE) and coefficient of determination ( $R^{2}$ ). In the results, the proposed SR showed the best performance with $R^{2}$ of 0.984 and RMSE of 179.898 compared with another study that reported $R^{2}$ of 0.938 and RMSE of 343.026 on the seven features selected by XFI. The SR achieved the highest $R^{2}$ of 0.985 on all features and the features that were selected by the SBEFS. Our SR outperformed CR, and another study on wild blueberry yield prediction.
2022
64671-64687
journalArticle
12
IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
DOI 10.1109/JSTARS.2019.2955513
12
IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
ISSN 2151-1535
M. Pieri
M. Chiesi
P. Battista
L. Fibbi
L. Gardin
B. Rapi
M. Romani
F. Sabatini
L. Angeli
C. Cantini
A. Giovannelli
F. Maselli
Agriculture
Remote sensing
Ecosystems
Vegetation mapping
MODIS
Moderate Resolution Imaging Spectroradiometer (MODIS)
Normalized Difference Vegetation Index (NDVI)
Thematic Mapper (TM), Enhanced Thematic Mapper Plus (ETM+), Operational Land Imager (OLI)
Estimation of Actual Evapotranspiration in Fragmented Mediterranean Areas by the Spatio-Temporal Fusion of NDVI Data
Actual evapotranspiration (ETA) is a fundamental component of the land water cycle that can be predicted by the combination of meteorological data and remotely sensed normalized difference vegetation index (NDVI) observations. The proficient application of this approach to the retrospective study of fragmented areas, however, depends on the preliminary use of spatio-temporal fusion (STF) methods capable of integrating different satellite datasets. One of these methods is the Spatial Enhancer of Vegetation Index image Series (SEVIS), which has been recently developed to improve the annual NDVI datasets based on one or a few high spatial resolution images. This STF method is currently applied to moderate resolution imaging spectroradiometer (MODIS) and TM/ETM+/OLI imagery taken over three fragmented areas in Tuscany (Central Italy), representative of different Mediterranean ecosystems, i.e., an urban grassland, a tomato field, and an olive grove. The performance of SEVIS is evaluated by comparing the ETA estimates obtained from the original (MODIS) and synthetic (MODIS plus TM/ETM+/OLI) NDVI datasets to ground ETA observations. The experimental results indicate that the original MODIS NDVI data cannot properly characterize the seasonal vegetation evolutions of the three study sites, which negatively affects the performance of ETA simulation. In contrast, such evolutions are reasonably reproduced by the synthetic NDVI datasets, which improves the accuracy of the ETA estimates both in terms of correlation and errors. The improvements are particularly evident during the summer dry period when the MODIS images are incapable of characterizing the actual vegetation response to water stress.
Dec. 2019
5108-5117
journalArticle
12
IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
DOI 10.1109/JSTARS.2019.2902479
7
IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
ISSN 2151-1535
A. E. Santamaría-Artigas
B. Franch
P. Guillevic
J. -C. Roger
E. F. Vermote
S. Skakun
Agriculture
Earth
Remote sensing
Ocean temperature
Temperature distribution
Atmospheric modeling
Meteorology
winter wheat
Global surface summary of the day (GSOD)
growing degree day (GDD)
near-surface air temperature
reanalysis
yield forecast
Evaluation of Near-Surface Air Temperature From Reanalysis Over the United States and Ukraine: Application to Winter Wheat Yield Forecasting
In this paper, we evaluate the near-surface air temperature datasets from the ERA-Interim (ERAI), Japanese 55-Year Reanalysis, Modern-Era Retrospective Analysis for Research and Applications Version 2, NCEP1, and NCEP2 reanalysis projects. Reanalysis data were first compared to observations from weather stations located on wheat areas of the United States and Ukraine, and then evaluated in the context of a winter wheat yield forecast model. Results from the comparison with weather station data showed that all datasets performed well (r2 > 0.95) and that more modern reanalysis, such as ERAI, had lower errors [root-mean-square difference (RMSD) ~0.9 °C than the older, lower resolution datasets, such as NCEP1 (RMSD ~2.4 °C). We also analyze the impact of using surface air temperature data from different reanalysis products on the estimations made by a winter wheat yield forecast model. The forecast model uses information of the accumulated growing degree day (GDD) during the growing season to estimate the peak normalized difference vegetation index signal. When the temperature data from the different reanalysis projects were used in the yield model to compute the accumulated GDD and forecast the winter wheat yield, the results showed smaller variations between obtained values, with differences in yield forecast error of around 2% in the most extreme case. These results suggest that the impact of temperature discrepancies between datasets in the yield forecast model get diminished as the values are accumulated through the growing season.
July 2019
2260-2269
journalArticle
7
IEEE Access
DOI 10.1109/ACCESS.2019.2927107
IEEE Access
ISSN 2169-3536
J. Wu
X. Guo
G. Yang
S. Wu
H. Hassan
J. Wu
Task analysis
Optimization
Planning
Buildings
History
quality of service
service composition
Service-based system
Service-oriented architecture
subgraph query
web service
Subgraph Query for Building Service-Based Systems
Given the broad applications of service-oriented architecture (SOA) in service-oriented software engineering, service-based systems (SBSs) built from existing Web services are becoming increasingly popular. As a result, the selection of the appropriate component services to include in SBSs has become a crucial step in the SBS-engineering process. Unfortunately, most of the existing methods require that system engineers have a detailed knowledge of the corresponding SOA techniques, which can incur several limitations, including excessively demanding development conditions and a lengthy development cycle. To address this issue, we propose to use subgraph queries for SBSs (SQS), which is an efficient approach that allows system engineers to build SBSs based on previous development experience. The SQS converts the SBS engineering problem into a subgraph isomorphism problem and uses a customized algorithm inspired by the VF2 algorithm to build SBSs with quality constraints and optimization goals for system quality. The SQS offers a new paradigm for efficient SBS engineering that significantly reduces the time and effort required in the system-engineering process. We discuss a series of experiments that use two real-world Web service datasets to demonstrate the practicality, effectiveness, and efficiency of this approach.
2019
97566-97581
journalArticle
31
IEEE Transactions on Image Processing
DOI 10.1109/TIP.2022.3163851
IEEE Transactions on Image Processing
ISSN 1941-0042
X. Shi
X. Chai
J. Xie
T. Sun
Feature extraction
multi-scale
Task analysis
Semantics
Faces
Prototypes
Face recognition
contrastive information
graph convolutional
image set
Media
MC-GCN: A Multi-Scale Contrastive Graph Convolutional Network for Unconstrained Face Recognition With Image Sets
In this paper, a Multi-scale Contrastive Graph Convolutional Network (MC-GCN) method is proposed for unconstrained face recognition with image sets, which takes a set of media (orderless images and videos) as a face subject instead of single media (an image or video). Due to factors such as illumination, posture, media source, etc., there are huge intra-set variances in a face set, and the importance of different face prototypes varies considerably. How to model the attention mechanism according to the relationship between prototypes or images in a set is the main content of this paper. In this work, we formulate a framework based on graph convolutional network (GCN), which considers face prototypes as nodes to build relations. Specifically, we first present a multi-scale graph module to learn the relationship between prototypes at multiple scales. Moreover, a Contrastive Graph Convolutional (CGC) block is introduced to build attention control model, which focuses on those frames with similar prototypes (contrastive information) between pair of sets instead of simply evaluating the frame quality. The experiments on IJB-A, YouTube Face, and an animal face dataset clearly demonstrate that our proposed MC-GCN outperforms the state-of-the-art methods significantly.
2022
3046-3055
journalArticle
22
IEEE Sensors Journal
DOI 10.1109/JSEN.2022.3219594
24
IEEE Sensors Journal
ISSN 1558-1748
C. Li
L. Minati
K. K. Tokgoz
M. Fukawa
J. Bartels
A. Sihan
K. -I. Takeda
H. Ito
Monitoring
data augmentation
Training
Time series analysis
time series
Sensors
Cows
imbalanced dataset
Sensor phenomena and characterization
Accelerometer
animal behavior
Behavioral sciences
Fourier surrogates
sensor data processing
Integrated Data Augmentation for Accelerometer Time Series in Behavior Recognition: Roles of Sampling, Balancing, and Fourier Surrogates
The behavioral monitoring of farmed animals such as cattle is a fundamental element of precision farming in which it enables unobtrusive ongoing health monitoring. This application presents two ubiquitous challenges typical of sensing applications of the Internet of Things: limited dataset size and dataset imbalance. Recently, data augmentation has emerged as a way of addressing their negative influences on the training process without overburdening the data acquisition phase. However, there remains no consensus regarding which methods should be applied to time series and in what combination. Here, we present the first comprehensive analysis that synergistically combines multiple approaches. These approaches are benchmarked on a dataset of triaxial accelerometer time series, which were acquired from six freely roaming cows through a collar-mounted sensor and labeled by experienced human observers according to five behaviors. Our results indicate that integrating data augmentation with the training process can substantially improve the time-series classification performance while retaining a fixed convolutional neural network architecture. The improvement is maximized when the dataset is balanced by applying a suitable sampling scheme and the negative influence of data duplication is reduced via generating synthetic time series with Fourier surrogates. With the proposed approach, the overall accuracy is improved from 90% to 96%, and the classification accuracy of an under-represented behavior, namely, grazing, is elevated from 45% to 91%. This work provides a direction toward a general methodology, motivating research on other datasets and applications.
15 Dec.15, 2022
24230-24241
journalArticle
7
IEEE Access
DOI 10.1109/ACCESS.2019.2914929
IEEE Access
ISSN 2169-3536
P. Jiang
Y. Chen
B. Liu
D. He
C. Liang
Convolutional neural networks
Feature extraction
deep learning
Deep learning
Diseases
Training
Agriculture
convolutional neural networks
Real-time systems
feature fusion
Apple leaf diseases
real-time detection
Real-Time Detection of Apple Leaf Diseases Using Deep Learning Approach Based on Improved Convolutional Neural Networks
Alternaria leaf spot, Brown spot, Mosaic, Grey spot, and Rust are five common types of apple leaf diseases that severely affect apple yield. However, the existing research lacks an accurate and fast detector of apple diseases for ensuring the healthy development of the apple industry. This paper proposes a deep learning approach that is based on improved convolutional neural networks (CNNs) for the real-time detection of apple leaf diseases. In this paper, the apple leaf disease dataset (ALDD), which is composed of laboratory images and complex images under real field conditions, is first constructed via data augmentation and image annotation technologies. Based on this, a new apple leaf disease detection model that uses deep-CNNs is proposed by introducing the GoogLeNet Inception structure and Rainbow concatenation. Finally, under the hold-out testing dataset, using a dataset of 26,377 images of diseased apple leaves, the proposed INAR-SSD (SSD with Inception module and Rainbow concatenation) model is trained to detect these five common apple leaf diseases. The experimental results show that the INAR-SSD model realizes a detection performance of 78.80% mAP on ALDD, with a high-detection speed of 23.13 FPS. The results demonstrate that the novel INAR-SSD model provides a high-performance solution for the early diagnosis of apple leaf diseases that can perform real-time detection of these diseases with higher accuracy and faster detection speed than previous methods.
2019
59069-59080
journalArticle
11
IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
DOI 10.1109/JSTARS.2018.2796546
3
IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
ISSN 2151-1535
Y. Gao
J. P. Walker
N. Ye
R. Panciera
A. Monerris
D. Ryu
C. Rüdiger
T. J. Jackson
Monitoring
Microwave radiometry
Soil moisture
Calibration
Atmospheric modeling
Land surface
Vegetation mapping
soil moisture
validation
passive microwave
retrieval
Evaluation of the Tau–Omega Model for Passive Microwave Soil Moisture Retrieval Using SMAPEx Datasets
The parameters used for passive soil moisture retrieval algorithms reported in the literature encompass a wide range, leading to a large uncertainty in the applicability of those values. This paper presents an evaluation of the proposed parameterizations of the tau-omega model from 1) the soil moisture active passive (SMAP) algorithm theoretical basis document (ATBD) for global condition and 2) calibrated parameters from the National Airborne Field Experiment (NAFE'05) for Australian conditions, with special focus on the vegetation parameter b and roughness parameter HR. This study uses airborne L-band data and field observations from the SMAP experiments conducted in south-eastern Australia. Results show that the accuracy with the proposed parameterizations from SMAP ATBD was satisfactory at 100-m spatial resolution for maize (0.07 m3/m3) and pasture (0.07 m3/m3 ), while it decreased to 0.19 m3/m3 for wheat. Calibrated parameters from the NAFE'05 did not provide better results, with the accuracy of wheat degrading to 0.23 m3/m3. After a comprehensive site-specific calibration and validation at 100-m spatial resolution, this result was improved to 0.10 m3/m3. Further calibration and validation were performed at 1-km resolution against intensive ground sampling and at 3-km against in situ monitoring stations. Results showed an accuracy over grassland and cropland of 0.04 m3/m3 and 0.05 m3/m3 , respectively. This study also suggests that the parameters from SMAP ATBD show an underestimation of soil moisture, with the roughness parameter HR being too low for south-eastern Australian condition. Therefore, a new set of b and HR parameters for ten different land cover types was proposed in this study.
March 2018
888-895
journalArticle
9
IEEE Access
DOI 10.1109/ACCESS.2021.3058582
IEEE Access
ISSN 2169-3536
W. Haider
A. -U. Rehman
N. M. Durrani
S. U. Rehman
artificial intelligence
Diseases
Insects
Agriculture
Production
machine learning
Machine learning algorithms
Agricultural DSS
agricultural knowledge management
classification of crop diseases
Genetics
Knowledge based systems
wheat crop diseases
A Generic Approach for Wheat Disease Classification and Verification Using Expert Opinion for Knowledge-Based Decisions
Crop diseases have mainly affected crop production due to the lack of modern approaches for disease identification. For many years, farmers have identified various crop diseases and have local knowledge about disease management. However, the local knowledge of one agricultural region is not utilized in other regions due to the unavailability of knowledge sharing platforms. Agricultural research also suggests that crop production has mainly decreased due to diseases, methods of cultivation, irrigation, and lack of local agricultural knowledge. In this research, the experience of agricultural experts, farmers, and cultivators is gathered through a crowd-sourced platform. The data is then processed for various disease identification. Hence, timely identification of various crop diseases can benefit farmers to apply relevant management methods. In literature, researchers have proposed various methods for disease management, mostly based on the classification of crop diseases using Machine Learning (ML) algorithms. However, these algorithms are unable to give trustful results due to static data provisioning and the dynamic nature of various diseases in different agricultural regions. Further, the agricultural expert's experience is also not considered in verifying the classification results. To identify the dynamic nature of wheat diseases, we acquired high-quality images and symptoms-based text data from farmers, domain experts, and users using a crowd-sourced platform. Different augmentation techniques were also used to enhance the size of training data. In this paper, a modern generic approach has been proposed for the identification and classification of wheat diseases using Decision Trees (DT) and different deep learning models. Also, results of both algorithms were then verified by domain experts that improved the decision trees accuracy by 28.5%, CNN accuracy by 4.3% (leading to 97.2%), and resulted in decision rules for wheat diseases in a knowledge-based system.
2021
31104-31129
journalArticle
60
IEEE Transactions on Geoscience and Remote Sensing
DOI 10.1109/TGRS.2021.3119667
IEEE Transactions on Geoscience and Remote Sensing
ISSN 1558-0644
L. Zhao
K. Yang
J. He
H. Zheng
D. Zheng
Soil moisture
Earth
Calibration
Land surface
Satellites
Soil
soil moisture
Land surface model
Noah-MP
Soil Moisture Active Passive (SMAP)
Soil properties
soil texture type
Potential of Mapping Global Soil Texture Type From SMAP Soil Moisture Product: A Pilot Study
Soil texture and associated thermal and hydraulic parameters are key to land surface processes. Current global soil datasets are derived from limited soil samples, which are not only very costly but also prone to large uncertainties. While it is difficult to directly retrieve soil properties through satellite remote sensing, this study explores the feasibility of mapping global soil type and thereby corresponding soil texture through the Soil Moisture Active Passive (SMAP) soil moisture product without reference to soil samples. Specifically, for each grid-cell, 12 U.S. Department of Agriculture (USDA) soil types are first used to drive the Noah-MP land surface model and then the optimal one is obtained by referring to a four-year (2015–2018) SMAP soil moisture time series. The proposed scheme can reasonably map the global distribution of soil types in terms of sand/clay content and porosity that are close to the Global Soil Dataset for Earth System Models (GSDE) dataset and outperform the one used in the Global Land Data Assimilation System (GLDAS)/Noah model. The result of this pilot study is very encouraging as it purely relies on satellite data, which is especially important for remote areas where few soil samples are available and conventional soil datasets may have large biases. Further improvements may be achieved upon improved soil organic matter parameterization, through land data assimilation, and by considering additional satellite information.
2022
1-10
journalArticle
M. Xiao
H. Li
Q. Huang
S. Yu
W. Susilo
Task analysis
Software
Cloud computing
Encryption
Periodic structures
Logic gates
Access control
Attribute-based encryption
extendable policy
hierarchical access control
Attribute-Based Hierarchical Access Control With Extendable Policy
Attribute-based encryption scheme is a promising mechanism to realize one-to-many fine-grained access control which strengthens the security in cloud computing. However, massive amounts of data and various data sharing requirements bring great challenges to the complex but isolated and fixed access structures in most of the existing attribute-based encryption schemes. In this paper, we propose an attribute-based hierarchical encryption scheme with extendable policy, called Extendable Hierarchical Ciphertext-Policy Attribute-Based Encryption (EH-CP-ABE), to improve the data sharing efficiency and security simultaneously. The scheme realizes the function of hierarchical encryption, in which, data with hierarchical access control relationships could be encrypted together flexibly to improve the efficiency. The scheme also achieves external and internal extension of the access structure to further encrypt newly added hierarchical data without updating the original ciphertexts or with only a minor update depending on the data sharing requirements, which simplifies the encryption process and greatly reduces the computation overhead. We formally prove the security of the scheme is IND-CCA secure in the random oracle model based on bilinear Diffie-Hellman assumption, and we also implement our scheme to demonstrate its efficiency and practicality.
2022
1868-1883
17
IEEE Transactions on Information Forensics and Security
DOI 10.1109/TIFS.2022.3173412
IEEE Transactions on Information Forensics and Security
ISSN 1556-6021
journalArticle
60
IEEE Transactions on Geoscience and Remote Sensing
DOI 10.1109/TGRS.2021.3096999
IEEE Transactions on Geoscience and Remote Sensing
ISSN 1558-0644
J. Jia
J. Chen
X. Zheng
Y. Wang
S. Guo
H. Sun
C. Jiang
M. Karjalainen
K. Karila
Z. Duan
T. Wang
C. Xu
J. Hyyppä
Y. Chen
Agriculture
Forestry
Hyperspectral imaging
Spatial resolution
Signal resolution
Hyperspectral imager
Instruments
parameter optimization
Signal to noise ratio
system design
tradeoff
Tradeoffs in the Spatial and Spectral Resolution of Airborne Hyperspectral Imaging Systems: A Crop Identification Case Study
Airborne hyperspectral images are used for crop identification with a high classification accuracy because of their high spectral resolution, spatial resolution, and signal-to-noise ratio (SNR). However, the tradeoffs between the three core parameters of a hyperspectral imager (SNR, spatial resolution, and spectral resolution) should be considered for designing an efficient imaging system. Only a few reported studies on the analysis of the impact of SNR on identification accuracy are available. Further, the tradeoffs and mutual interactions among these parameters are rarely considered. In this empirical study, our aim was to understand the relationship among the core parameters and their effects on crop identification accuracy by analyzing the tradeoffs and mutual interactions among these parameters. We analyzed the hyperspectral images of a typical plain agricultural area in Xiongan, China, acquired by the newly developed sensor airborne multimodular imaging spectrometer (AMMIS). The fundamental images were transformed to form datasets with different ranges of spectral resolution, spatial resolution, and SNR using data reconstruction methods. We adopted the classification and regression tree (CART), random forest (RF), and k-nearest neighbor (kNN) classifiers, and observed the overall accuracy (OA) across the degraded hyperspectral datasets. The experimental results indicated that the OA decreased with a decreasing SNR. As the spectral resolution became coarser, the OA first increased, plateaued, and then decreased. However, the OA increased with decreasing spatial resolution. This study was performed with the goal of bridging the knowledge gap between the back-end hyperspectral sensor designing and its front-end applications.
2022
1-18
journalArticle
9
IEEE Access
DOI 10.1109/ACCESS.2021.3058947
IEEE Access
ISSN 2169-3536
C. Zhou
S. Zhou
J. Xing
J. Song
Feature extraction
Diseases
Agriculture
Support vector machines
Image segmentation
Convolution
Machine learning algorithms
agricultural artificial intelligence
leaf disease identification
Residual dense network
tomato leaf diseases
Tomato Leaf Disease Identification by Restructured Deep Residual Dense Network
As COVID-19 spread worldwide, many major grain-producing countries have adopted measures to restrict their grain exports; food security has aroused great concern from various parties. How to improve grain production has become one of the most important issues facing all countries. However, crop diseases are a difficult problem for many farmers so it is important to master the severity of crop diseases timely and accurately to help staff take further intervention measures to minimize plants being further infected. In this paper, a restructured residual dense network was proposed for tomato leaf disease identification; this hybrid deep learning model combines the advantages of deep residual networks and dense networks, which can reduce the number of training process parameters to improve calculation accuracy as well as enhance the flow of information and gradients. The original RDN model was first used in image super resolution, so we need to restructure the network architecture for classification tasks through adjusted input image features and hyper parameters. Experimental results show that this model can achieve a top-1 average identification accuracy of 95% on the Tomato test dataset in AI Challenger 2018 datasets, which verifies its satisfactory performance. The restructured residual dense network model can obtain significant improvements over most of the state-of-the-art models in crop leaf identification, as well as requiring less computation to achieve high performance.
2021
28822-28831
journalArticle
14
IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
DOI 10.1109/JSTARS.2020.3032011
IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
ISSN 2151-1535
J. Cui
M. Liu
Z. Zhang
S. Yang
J. Ning
Agriculture
Remote sensing
Distortion
Unmanned aerial vehicles
Tools
unmanned aerial vehicle (UAV)
Image stitching
overlap ratio prior
Strain
thermal infrared remote sensing (TIRS)
Robust UAV Thermal Infrared Remote Sensing Images Stitching Via Overlap-Prior-Based Global Similarity Prior Model
The main problem of stitching unmanned aerial vehicle (UAV) thermal infrared remote sensing (TIRS) images lies in that the cumulative error caused by the inaccurate alignment of image matching pairs easily leads to deformation and even failure. Few studies in the literature are reported in stitching TIRS images. For the first time, we propose a simple and robust TIRS image stitching method by exploring prior information during flight. First, according to the position and orientation system information and parameter of camera, the overlap ratio of adjacent images is estimated, and the image pairs with high overlap ratio and high matching confidence in different directions are selected. Then, they are added into the alignment term of global similarity prior (GSP) model. Therefore, each image has more matching pairs constraints compared to the traditional construction method of matching pairs, which greatly improves the local registration capability of GSP and then prevents it from converging to the local optimal solution. The proposed method was extensively evaluated on a dataset including to 24 groups of large-scale farmland TIRS images collected in four experimental areas under different crop growth periods and meteorological conditions. Compared with two commercial tools and two representative stitching algorithms, the proposed method significantly improves the local alignment ability and overall stitching quality on both qualitative and quantitative evaluation. Besides, when the front overlap ratio is reduced from 85% to 70%, the proposed method still shows obvious advantages over the related methods and commercial tools, which improves the acquisition efficiency of UAV TIRS images.
2021
270-282
journalArticle
19
IEEE Geoscience and Remote Sensing Letters
DOI 10.1109/LGRS.2021.3079317
IEEE Geoscience and Remote Sensing Letters
ISSN 1558-0571
L. Feng
Z. Zhang
Y. Ma
Y. Sun
Q. Du
P. Williams
J. Drewry
B. Luck
Computer architecture
Agriculture
hyperspectral imagery
Hyperspectral imaging
Task analysis
Predictive models
Mathematical model
Logic gates
unmanned aerial vehicle (UAV)
Alfalfa
multitask learning
nutritive value
Multitask Learning of Alfalfa Nutritive Value From UAV-Based Hyperspectral Images
Alfalfa is a valuable and widely adapted forage crop, and its nutritive value directly affects animal performance and ultimately affects the profitability of livestock production. Traditional nutritive value measurement method is labor-intensive and time-consuming and thus hinders the determination of alfalfa nutritive values over large fields. The adoption of unmanned aerial vehicles (UAVs) facilitates the generation of images with high spatial and temporal resolutions for field-level agricultural research. Additionally, compared with other imaging modalities, hyperspectral data usually consist of hundreds of narrow spectral bands and allow the accurate detection, identification, and quantification of crop quality. Although various machine-learning methods have been developed for alfalfa quality prediction, they were all single-task models that learned independently for each quality trait and failed to utilize the underlying relatedness between each task. Inspired by the idea of multitask learning (MTL), this study aims to develop an approach that simultaneously predicts multiple quality traits. The algorithm first extracts shared information through a long short-term memory (LSTM)-based common hidden layer. To enhance the model flexibility, it is then divided into multiple branches, each containing the same or different number of task-specific fully connected hidden layers. Through comparison with multiple mainstream single-task machine-learning models, the effectiveness of the model is illustrated based on the measured alfalfa quality data and multitemporal UAV-based hyperspectral imagery.
2022
1-5
journalArticle
12
IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
DOI 10.1109/JSTARS.2019.2937398
10
IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
ISSN 2151-1535
D. H. T. Minh
Q. C. Tran
Q. N. Pham
T. T. Dang
D. A. Nguyen
I. El-Moussawi
T. Le Toan
Synthetic aperture radar
synthetic aperture radar (SAR)
Strain
Atmosphere
Atmospheric phase screen (APS)
Decorrelation
Geologic measurements
ground subsidence
groundwater
Ha Noi
JV-LOTUSat
multitemporal synthetic aperture radar interferometry (InSAR)
permanent scatterers/distributed scatterers (PS/DS) processing
Spaceborne radar
tropical region
Urban areas
X-band
Measuring Ground Subsidence in Ha Noi Through the Radar Interferometry Technique Using TerraSAR-X and Cosmos SkyMed Data
Multitemporal synthetic aperture radar (SAR) interferometry (InSAR) is a widely used technique to measure the ground subsidence and has already shown its ability to map such phenomena on a large spatial scale with millimetric accuracy from space. In Vietnam, to have independent SAR data for surface risk applications, a new X-band SAR mission (JV-LOTUSat) has been scheduled for launch for the 2019-2020 timeframe. However, Vietnam is located in tropical regions where their conditions are impacted by strong atmosphere. The aim of this article is to provide a better understanding of the capabilities of the X-band for estimating the ground subsidence under tropical atmospheric conditions. Analysis is carried out on two stacks, TerraSAR-X and Cosmos SkyMed X-band, from 2011 to 2014 in Ha Noi. We show that the results on the ground subsidence from InSAR processing can describe consistently the subsidence area based on ground measurements. This article demonstrates that the InSAR technique can be effective at detecting and estimating the subsidence phenomena even with the X-band and under conditions typical of tropical regions. The displacement results from TerraSAR-X and Cosmos SkyMed datasets are consistent, with a correlation coefficient (R2) of 0.91 for the period during which their coverage overlaps. Groundwater overexploitation is one of the main causes of the ground subsidence in Ha Noi. This study provides strong support for the scientific potential of the X-band SAR space-borne mission in Vietnam and other tropical countries because it demonstrates the feasibility of the ground subsidence estimates by the X-band SAR, even in conditions impacted by strong atmosphere.
Oct. 2019
3874-3884
journalArticle
9
IEEE Access
DOI 10.1109/ACCESS.2021.3066255
IEEE Access
ISSN 2169-3536
M. H. Mughal
Z. A. Shaikh
A. I. Wagan
Z. H. Khand
S. Hassan
Data models
Irrigation
Semantics
Ontologies
ontology
Rivers
Knowledge based systems
Disaster management
flood mitigation
inference
irrigation system
knowledge base
semantic interpretation
semantic reasoner
Semantic web
ORFFM: An Ontology-Based Semantic Model of River Flow and Flood Mitigation
The provision of the heterogeneous information acquisition and managing of emerging technologies with IoT, cloud-based storage, and improved communication services have filled the data scarcity gap on one hand but raised the challenge to extract, process, and comprehend relevant data of complex integrated multiple domains involving a large number of participants with diverse spatial terminologies and methodologies. To resolve this challenge various big data and natural language processing techniques were applied. Another widely used approach to resolve the challenges of heterogeneity, interoperability, and complexity of integrated domain is ontology-based semantic modeling. We proposed Ontology for River Flow and Flood Mitigation (ORFFM) for semantic knowledge formalization with semantic understandability of irrigation, disaster management, related administrative and agricultural domain concepts by humans and machines. The semantic modeling of distributed river flow network and associated flood disaster mitigation for effective coordination, collaborative response activities leads to reduce the impact of a disaster and improve information representation among stakeholders. Furthermore, semantic formalization and inference are supported by explicitly annotated information. We populated ORFFM with Pakistan's Indus river system, flood disaster management, and Sindh administrative authorities to develop a knowledgebase for knowledge sharing and representation. The formal semantically enriched knowledgebase would contribute towards streamflow optimization and flood mitigation through effective coordination and common conceptualization during disaster management phases. The semantic model of irrigation networks would also be useful for academic purposes to acquire domain knowledge for new entrants in the irrigation and disaster management field.
2021
44003-44031
journalArticle
7
IEEE Access
DOI 10.1109/ACCESS.2019.2938194
IEEE Access
ISSN 2169-3536
F. Ren
W. Liu
G. Wu
Deep learning
Insects
Training
Agriculture
Task analysis
Benchmark testing
Convolution
residual network
feature reuse
Insect pest recognition
Feature Reuse Residual Networks for Insect Pest Recognition
Insect pests are one of the main threats to the commercially important crops. An effective insect pest recognition method can avoid economic losses. In this paper, we proposed a new and simple structure based on the original residual block and named as feature reuse residual block which combines feature from the input signal of a residual block with the residual signal. In each feature reuse residual block, it enhances the capacity of representation by learning half and reuse half feature. By stacking the feature reuse residual block, we obtained the feature reuse residual network (FR-ResNet) and evaluated the performance on IP102 benchmark dataset. The experimental results showed that FR-ResNet can achieve significant performance improvement in terms of insect pest classification. Moreover, to demonstrate the adaptive of our approach, we applied it to various kinds of residual networks, including ResNet, Pre-ResNet, and WRN, and we tested the performance on a series of benchmark datasets: CIFAR-10, CIFAR-100, and SVHN. The experimental results showed that the performance can be improved obviously than original networks. Based on these experiments on CIFAR-10, CIFAR-100, SVHN, and IP102 benchmark datasets, it demonstrates the effectiveness of our approach.
2019
122758-122768
journalArticle
15
IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
DOI 10.1109/JSTARS.2022.3165078
IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
ISSN 2151-1535
A. Monsiváis-Huertero
D. E. Constantino-Recillas
J. C. Hernández-Sánchez
H. E. Huerta-Bátiz
J. Judge
P. A. López-Estrada
J. C. Jiménez-Escalona
E. Arizmendi-Vasconcelos
M. A. García-Bernal
C. F. Zambrano-Gallardo
A. A. López-Caloca
E. Zempoaltécatl-Ramirez
I. E. D. l. Rosa-Montero
R. I. Villalobos-Martínez
R. S. Aparicio-García
C. R. Sánchez-Villanueva
L. Arizmendi-Vasconcelos
R. Cotero-Manzo
J. H. Puebla-Lomas
V. M. Saúce-Rangel
Soil measurements
Soil moisture
Vegetation mapping
Soil
soil moisture active passive (SMAP)
Uncertainty
Urban areas
Agricultural region
Hydrology
L-band passive microwave
Mexico
multiscale soil moisture (SM)
terrestrial hydrology experiments in Mexico 2018 (THEXMEX-18)
terrestrial hydrology experiments in Mexico 2019 (THEXMEX-19)
Assessment of NASA SMAP Soil Moisture Products for Agricultural Regions in Central Mexico: An Analysis Based on the THEXMEX Dataset
Accurate knowledge of soil moisture (SM) is crucial in hydrological, micrometeorological, and agricultural applications; however, the SM estimation is particularly challenging in agricultural regions due to high spatial variability and dynamic vegetation conditions. The need for information about SM conditions is even more evident in developing countries with limited monitoring infrastructure. Satellite SM products are a useful tool as a proxy for SM conditions on the ground, but they need to be evaluated for specific regions. In this study, we assess the quality of the soil moisture active passive (SMAP) SM retrievals at 36, 9, and 3 km in an agricultural region in Central Mexico using in situ measurements during the Terrestrial Hydrology Experiments in Mexico 2018 and 2019. In addition, we provide insights into soil and vegetation parameters in the retrieval algorithms compared to those observed in the region. It was found that the SM spatial variability at the SMAP pixel grids was well represented by upscaled in situ SM measurements (SM$_{\text{up}}$) from five monitoring stations using the soil-weighted averaging and the Voronoï diagrams. Overall, the SMAP SM retrievals are highly correlated with SM$_{\text{up}}$ at all scales, but they estimated wetter conditions and the average root-mean-square difference (RMSD) $>$ 0.045 m$^{3}$/m$^{3}$. The lowest RMSD was obtained for the SM product at 36 km, while the highest RMSD was found for the SM product at 3 km. In addition, the single-channel algorithm using H-polarization provided the lowest RMSD for the products at 36 and 9 km. The main sources of uncertainty in the region may arise from the higher clay fraction used in the SMAP retrieval algorithm, by 13% compared to that observed, and a nonrepresentative characterization of land cover heterogeneity for vegetation water content estimation. The incorporation of in situ values into an SM retrieval algorithm resulted in differences $< $0.04 m$^{3}$/m$^{3}$ between SM estimates and in situ SM for the complete growing season. Particularly, the use of in situ information helped in improving SM estimation when optimizing V- and dual-polarization brightness temperature observations.
2022
3421-3443
journalArticle
H. Cheng
H. Wang
X. Liu
Y. Fang
M. Wang
X. Zhang
Cameras
Servers
Surveillance
Videos
Cryptography
Hamming distance
Merkle hash tree
person re-identification
Privacy-preserving
secret sharing
secure Hamming distance
Person Re-Identification over Encrypted Outsourced Surveillance Videos
Person re-identification (Re-ID) has attracted extensive attention due to its potential to identify a person of interest from different surveillance videos. With the increasing amount of the surveillance videos, high computation and storage costs have posed a great challenge for the resource-constrained users. In recent years, the cloud storage services have made a large volume of video data outsourcing become possible. However, person Re-ID over outsourced surveillance videos could lead to a security threat, i.e., the privacy leakage of the innocent person in these videos. Therefore, we propose an efFicient privAcy-preseRving peRson Re-ID Scheme (FARRIS) over outsourced surveillance videos, which can ensure the privacy of the detected person while providing the person Re-ID service. Specifically, FARRIS exploits the convolutional neural network (CNN) and kernels based supervised hashing (KSH) to extract the efficient person Re-ID feature. Then, we design a secret sharing based Hamming distance computation protocol to allow cloud servers to calculate similarities among obfuscated feature indexes. Furthermore, a dual Merkle hash trees based verification is proposed, which permits users to validate the correctness of the matching results. The extensive experimental results and security analysis demonstrate that FARRIS can work efficiently, without compromising the privacy of the involved person.
1 May-June 2021
1456-1473
18
IEEE Transactions on Dependable and Secure Computing
DOI 10.1109/TDSC.2019.2923653
3
IEEE Transactions on Dependable and Secure Computing
ISSN 1941-0018
journalArticle
15
IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
DOI 10.1109/JSTARS.2021.3139155
IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
ISSN 2151-1535
D. Cavaliere
S. Senatore
Monitoring
Agriculture
Earth
Sensors
Vegetation mapping
Satellites
Satellite broadcasting
ontology
precision agriculture (PA)
Harmonic analysis
phenological context
Incremental Knowledge Extraction From IoT-Based System for Anomaly Detection in Vegetation Crops
Precision agriculture systems collect spectral images from satellites, from which vegetation indices (VIs) can be assessed to monitor vegetation and soil condition. It requires a near-daily data acquisition to perform robust crop monitoring and data analysis. Satellites provide a periodic data acquisition that need a further data integration using multiple satellite sources along with camera-equipped drones to achieve an accurate data collection on a selected area. Moreover, VIs are not enough for a proper vegetation evaluation of the monitored areas due to differences among cultivars, the phenological season in which the vegetation is evaluated, the latitude of the areas, etc. This article introduces a system model to detect anomalies regarding the vegetation and soil conditions according to the area phenology and the historical vegetation trends. The system collects spectral images of the regions of interest (ROIs) from satellites and drones, harmonized to calculate VIs and feeds a dataset of near-daily high-resolution integrated images. The harmonic analysis allows phenological data extraction about the ROIs, hence the territorial observation model (TOM) has been extended to represent phenological stages and build knowledge on the ROIs and their phenology that is stored on a triple store. The system selects the VI values, calculated during the learned growing seasons of the ROIs, and classifies them to detect vegetation anomalies affecting those ROIs. The collected knowledge can be used by end-users (e.g., agronomists, experts, etc.) to analyze the anomalies correlated to historical results and vegetation trends.
2022
876-888
journalArticle
7
IEEE Access
DOI 10.1109/ACCESS.2019.2933060
IEEE Access
ISSN 2169-3536
J. Cowton
I. Kyriazakis
J. Bacardit
Deep learning
Training
Agriculture
Cameras
Machine learning
Visualization
object detection
Animals
multi-object tracking
Measurement
behaviour analysis
re-identification
Automated Individual Pig Localisation, Tracking and Behaviour Metric Extraction Using Deep Learning
Individual pig tracking is key to stepping away from group-level treatment and towards individual pig care. By doing so we can monitor individual pig behaviour changes over time and use these as indicators of health and well-being, which, in turn, will assist in the early detection of disease allowing for earlier and more effective intervention. However, it is a much more computationally challenging than performing this task at group level; mistakes in identification and tracking accumulate and, over time, provide noise measures. We combine a deep CNN object localisation method, Faster Region-based convolutional neural network (R-CNN), with two potential real-time multi-object tracking methods in order to create a complete system that can autonomously localise and track individual pigs allowing for the extraction of metrics pertaining to individual pig behaviours from RGB cameras. We evaluate two different transfer learning strategies to adapt Faster R-CNN to our pig detection dataset that is more challenging than conventional tracking benchmark datasets. We are able to localise pigs in individual frames with 0.901 mean average precision (mAP), which then allows us to track individual pigs across video footage with 92% Multi-Object Tracking Accuracy (MOTA) and 73.4% Identity F1-Score (IDF1), and re-identify them after occlusions and dropped frames with 0.862 mAP (0.788 Rank 1 cumulative matching characteristic (CMC)). From these tracks we extract individual behavioural metrics for total distance travelled, time spent idle, and average speed with less than 0.015 mean squared error (MSE) for each. Changes in all these behavioural metrics have value in the detection of pig health and wellbeing.
2019
108049-108060
journalArticle
8
IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
DOI 10.1109/JSTARS.2015.2423681
5
IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
ISSN 2151-1535
S. Biswas
K. D. Lasko
K. P. Vadrevu
Remote sensing
Spatial resolution
Correlation
Meteorology
Vegetation mapping
MODIS
moderate resolution imaging spectroradiometer (MODIS)
Fire
Fires
gross primary productivity (GPP)
Myanmar
tropics
vegetation disturbance
Fire Disturbance in Tropical Forests of Myanmar—Analysis Using MODIS Satellite Datasets
In this study, we quantified the relationship between fires and vegetation disturbance at varied spatial scales using moderate resolution imaging spectroradiometer (MODIS) datasets for the period 2003-2012. We report satellite-derived fire characteristics (frequency, extent, seasonality, and type of vegetation burnt) in Myanmar, the extent of fire disturbance, and the impact of the fires on gross primary productivity (GPP) at multiple scales. Results suggested March as the peak fire season with burnt areas (BAs) of 12900 km2 and 95000 fire counts. Forests accounted for 41.3% of the total BAs followed by shrub lands (33.6%) and agriculture (24.7%). The “low” vegetation disturbance category accounted for 9.2% of total fires, whereas the medium and high categories accounted for about 89.7%. We found relatively higher negative correlation between BA and GPP for deciduous forests (r = 0.49, p ~ 0) than for evergreen forests (r = 0.36, p ~ 0). A maximum decrease in 29% of original GPP (2007-2012) was observed in the evergreen forest patches. The scale-dependent correlation analysis suggested significant BA-GPP correlation at 1 × 1 degree compared to finer resolutions. Our results highlight the impact of fire disturbance on vegetation greenness and GPP in tropical forests of Myanmar.
May 2015
2273-2281
journalArticle
11
IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
DOI 10.1109/JSTARS.2018.2864897
12
IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
ISSN 2151-1535
V. A. Walker
B. K. Hornbuckle
M. H. Cosh
Soil measurements
Soil moisture
Agriculture
Ocean temperature
Rough surfaces
Soil Moisture Ocean Salinity (SMOS)
U. S. corn belt
A Five-Year Evaluation of SMOS Level 2 Soil Moisture in the Corn Belt of the United States
We compare Soil Moisture Ocean Salinity Level 2 Soil Moisture (L2SM) retrievals to the five-year in situ soil moisture dataset available for the predominately agricultural South Fork Iowa River (SFIR) watershed in the U. S. Corn Belt. SMOS L2SM is 0.039 m3 m-3 drier than the SFIR network soil moisture and has an unbiased RMSE (ubRMSE) of 0.062 m3 m-3 for the period of April 2013 to November 2017 (excluding DJF). The bias is 11% of the range of in situ soil moisture. The largest monthly dry biases occur in April (0.052 m3 m-3), July (0.072 m3 m-3), and November (0.061 m3 m-3). Potential sources of the dry bias we discuss are: bias in auxiliary modeled temperatures; errors in soil texture maps; and nonrepresentative parameterizations of single scattering albedo and soil surface roughness. Auxiliary skin temperature was colder than expected and may explain why SMOS L2SM has a slightly drier bias for evening overpasses. Increasing the parameterized soil surface roughness produces wetter SMOS L2SM retrievals but also decreases the range of SMOS L2SM. Random error in auxiliary surface temperature, edge-of-field locations of in situ sensors, and differences in sensing volume between SMOS and in situ sensors contribute to the soil moisture ubRMSE. ubRMSE can be decreased by using a nonzero single scattering albedo more representative of a corn and soybean canopy at the cost of increasing the dry bias.
Dec. 2018
4664-4675
journalArticle
14
IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
DOI 10.1109/JSTARS.2021.3096063
IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
ISSN 2151-1535
S. Ranjbar
M. Akhoondzadeh
B. Brisco
M. Amani
M. Hosseini
Monitoring
Soil measurements
Soil moisture
Synthetic aperture radar
synthetic aperture radar (SAR)
Climate change
Vegetation mapping
soil moisture
L-band
Change detection
interferometric phase
Sea measurements
Soil Moisture Change Monitoring from C and L-band SAR Interferometric Phase Observations
The soil moisture changes ($\Delta {{\boldsymbol{M}}_{\boldsymbol{v}}}$) have a significant influence on forestry, hydrology, meteorology, agriculture, and climate change. Interferometric synthetic aperture radar (InSAR), as a potential remote sensing tool for change detection, was relatively less investigated for monitoring this parameter. DInSAR phase (${\boldsymbol{\varphi }}$) is sensitive to the changes in soil moisture (${{\boldsymbol{M}}_{\boldsymbol{v}}}$), and thus, can be potentially used for monitoring $\Delta {{\boldsymbol{M}}_{\boldsymbol{v}}}$. In this article, the relations between ${\boldsymbol{\varphi }}$ and $\Delta {{\boldsymbol{M}}_{\boldsymbol{v}}}$ over wheat, canola, corn, soybean, weed, peas, and bare fields were investigated using an empirical regression technique. To this end, dual-polarimetric C-band Sentinel-1A and quad-polarimetric L-band uninhabited aerial vehicle synthetic aperture radar (UAVSAR) airborne datasets were employed. The regression model showed the coefficient of determination (R2) of 40% to 56% and RMSE of 4.3 vol.% to 6.1 vol.% between the measured and estimated $\Delta {{\boldsymbol{M}}_{\boldsymbol{v}}}$ for different crop types when the temporal baseline ($\Delta {\boldsymbol{T}}$) was very short. As expected, higher accuracies were obtained using UAVSAR given its very short $\Delta {\boldsymbol{T}}$ and its longer wavelength with R2 of 47% to 59% and RMSE of 4.1 vol.% to 6.7 vol.% for different crop types. However, using the Sentinel-1 data with the long $\Delta {\boldsymbol{T}}$ and shorter wavelength (5.6 cm), the accuracies of ${{\bf \Delta }}{{\boldsymbol{M}}_{\boldsymbol{v}}}$ estimations decreased significantly. The results of this study demonstrated that using the ${\boldsymbol{\varphi }}$ information from Sentinel-1 data is a promising approach for monitoring ${{\bf \Delta }}{{\boldsymbol{M}}_{\boldsymbol{v}}}$ at an early growing season or before the crop starts growing, but using L-band SAR data and lower temporal baselines are recommended once the biomass increases.
2021
7179-7197
journalArticle
60
IEEE Transactions on Geoscience and Remote Sensing
DOI 10.1109/TGRS.2022.3142288
IEEE Transactions on Geoscience and Remote Sensing
ISSN 1558-0644
J. Hu
Y. Zhang
D. Zhao
G. Yang
F. Chen
C. Zhou
W. Chen
Monitoring
deep learning
Vegetation
Agriculture
Remote sensing
Autonomous aerial vehicles
Laser radar
Crown measurement
shape clustering
unmanned aerial vehicle (UAV) images
volume estimation
Volume measurement
A Robust Deep Learning Approach for the Quantitative Characterization and Clustering of Peach Tree Crowns Based on UAV Images
The accurate large-scale measurement of peach crowns is vital in horticultural science and the optimization of orchard management. Nowadays, numerous crown parameters (e.g., crown area, height, and volume) can be obtained via the analysis of point clouds or photographs. Current laser-based sensors provide the required reliable and accurate information; however, they are costly and time-consuming. Therefore, a simpler approach for crown measurement is required. For this purpose, this study presents a pipeline for the monitoring and clustering of 259 peach tree crowns based on unmanned aerial vehicle (UAV) images of a peach orchard in Southeast China. Considering the limitation that the original aerial image dataset contains little information, a data augmentation process is adopted, and an efficient deep learning architecture based on conditional generative adversarial networks (cGANs) was designed to extract the crown area. Then, the shape of the crown area was clustered using an edge detection process and a $k$ -means algorithm. Finally, an ellipsoid volume method (EVM) was applied to estimate the crown volume. Five indicators—namely, $Q_{\mathrm {seg}}$ , $S_{\mathrm {r}}$ , Precision, Recall, and F-measure—were employed to evaluate the crown extraction effects, and the average results for testing samples were 0.832, 0.847, 0.851, 0.828, and 0.846, respectively. Compared with other approaches—namely, fully convolutional network (FCN), U-Net, SegNet21, the excess green index (ExG), and the color index of vegetation extraction (CIVE)—the proposed cGAN model performs better, achieving an accuracy improvement of 5%–25%. For the estimation of crown volume, using measurements from a light detection and ranging (LIDAR) scanner as a reference, the correlation coefficient and relative-root-mean-square error (R-RMSE) were found to be 0.836% and 14.93%, respectively. Overall, the results demonstrate that the proposed method is feasible for measuring peach tree crowns. The wide application of such technology would facilitate applied research in plant phenotyping and precision horticulture.
2022
1-13
journalArticle
6
IEEE Access
DOI 10.1109/ACCESS.2018.2868970
IEEE Access
ISSN 2169-3536
D. Lien Minh
A. Sadeghi-Niaraki
H. D. Huy
K. Min
H. Moon
Feature extraction
Deep learning
Machine learning
Dictionaries
Internet
Market research
natural language processing
sentiment analysis
Sentiment analysis
stock trends
Deep Learning Approach for Short-Term Stock Trends Prediction Based on Two-Stream Gated Recurrent Unit Network
Financial news has been proven to be a crucial factor which causes fluctuations in stock prices. However, previous studies heavily relied on analyzing shallow features and ignored the structural relation among words in a sentence. Several sentiment analysis studies have tried to point out the relationship between investors' reaction and news events. However, the sentiment dataset was usually constructed from the lingual dataset which is unrelated to the financial sector and led to poor performance. This paper proposes a novel framework to predict the directions of stock prices by using both financial news and sentiment dictionary. The original contributions of this paper include the proposal of a novel two-stream gated recurrent unit network and Stock2Vec-a sentiment word embedding trained on financial news dataset and Harvard IV-4. Two main experiments are conducted: the first experiment predicts S&P 500 index stock price directions using the historical S&P 500 prices and the articles crawled from Reuters and Bloomberg, and the second experiment forecasts the price trends of VN-index using VietStock news and stock prices from cophieu68. Results show that: 1) two-stream GRU outperforms state-of-the-art models; 2) Stock2Vec is more efficient in dealing with financial datasets; and 3) applying the model, a simulation scenario proves that our model is effective for the stock sector.
2018
55392-55404
journalArticle
10
IEEE Access
DOI 10.1109/ACCESS.2022.3227712
IEEE Access
ISSN 2169-3536
T. T. M. Huynh
T. M. Le
L. T. That
L. V. Tran
S. V. T. Dao
Crops
Feature extraction
Agriculture
Support vector machines
Random forests
feature selection
Optimization
Classification algorithms
feature extraction
adaptive particle grey wolf optimization
fruits recognition
Metaheuristics
Wrapper
A Two-Stage Feature Selection Approach for Fruit Recognition Using Camera Images With Various Machine Learning Classifiers
Fruit and vegetable identification and classification system is always necessary and advantageous for the agriculture business, the food processing sector, as well as the convenience shops and hypermarkets where these products are sold. Therefore, it is necessary to build an effective automated tool to meet the needs of the market by boosting the outcome, in order to improve economic efficiency. In this paper, a two-stage model is proposed to recognize fruits using camera images. We employed a Densnet121 to get the features from the fruits dataset in the first module. In the second stage, we utilize a feature subset selection method to choose the most significant features for recognizing fruits from the images of the fruits. In this study, Adaptive particle - Grey Wolf Optimization (APGWO) has been applied for choosing the most pertinent features. The final subset feature has been used for recognizing fruits using several machine learning classifiers, namely K-Nearest Neighbor (KNN), Support Vector Machine (SVM), Decision Tree (DT), Random Forest (RF), and Multilayer Perceptron (MLP). The proposed research’s experimental results are highly effective; the training time of proposed models is reduced to over 50%, and the classification accuracy reaches 99%.
2022
132260-132270
journalArticle
19
IEEE Geoscience and Remote Sensing Letters
DOI 10.1109/LGRS.2022.3190507
IEEE Geoscience and Remote Sensing Letters
ISSN 1558-0571
Y. Luo
L. Huang
B. Sun
W. Sun
S. Li
Feature extraction
Training
Image segmentation
deep learning (DL)
Encoding
Cropland segmentation
Fuses
Micromechanical devices
remote sensing (RS) images
spectral–spatial priors
Sun
Deep Fusion of Spectral–Spatial Priors for Cropland Segmentation in Remote Sensing Images
Cropland segmentation is one of the critical techniques in agriculture remote sensing (RS). Although the deep learning (DL) methods have achieved remarkable performance in natural vision, the cropland segmentation of RS images still suffers from cropland adhesion due to interference from the surrounding environment and the cropland cover. To tackle this problem, this letter proposes a two-stage DL method with spectral–spatial priors. In the first stage, the multifeature extraction module (MEM) is designed to predict the boundary, an important spatial prior of the cropland. In the second stage, the spatial prior is further fused with the spectral prior by MEMs to get accurate cropland prediction. To evaluate the effectiveness and robustness of the proposed method, we construct a dataset called Jiaxiang Cropland Set (JCS) and propose a region-level evaluation indicator namely the plot mean intersection over union (PMIoU). The experimental results on the JCS demonstrate that the proposed method is both qualitatively and quantitatively competitive compared with the state-of-the-art methods.
2022
1-5
journalArticle
8
IEEE Access
DOI 10.1109/ACCESS.2020.3032955
IEEE Access
ISSN 2169-3536
Z. Ren
E. Y. Lam
J. Zhao
Deep learning
Object detection
Training
Agriculture
Cameras
Visualization
object detection
Sensors
machine vision
Clustering methods
machine learning algorithms
Real-Time Target Detection in Visual Sensing Environments Using Deep Transfer Learning and Improved Anchor Box Generation
Visual perception is critical and essential to understand phenomenon and environments of the world. Pervasively configured devices like cameras are key in dynamic status monitoring, object detection and recognition. As such, visual sensor environments using one single or multiple cameras must deal with a huge amount of high-resolution images, videos or other multimedia. In this paper, to promote smart advancement and fast detection of visual environments, we propose a deep transfer learning strategy for real-time target detection for situations where acquiring large-scale data is complicated and challenging. By employing the concept of transfer learning and pre-training the network with established datasets, apart from the outstanding performance in target localization and recognition can be achieved, time consumption of training a deep model is also significantly reduced. Besides, the original clustering method, k-means, in the You Only Look Once (YOLOv3) detection model is sensitive to the initial cluster centers when estimating the initial width and height of the predicted bounding boxes, thereby processing large-scale data is extremely time-consuming. To handle such problems, an improved clustering method, mini batch k-means++ is incorporated into the detection model to improve the clustering accuracy. We examine the sustainable outperformance in three typical applications, digital pathology, smart agriculture and remote sensing, in vision-based sensing environments.
2020
193512-193522
journalArticle
7
IEEE Access
DOI 10.1109/ACCESS.2019.2896201
IEEE Access
ISSN 2169-3536
Z. Chen
L. Zhang
A. M. Khattak
W. Gao
M. Wang
Feature extraction
Computer architecture
Object detection
Task analysis
Semantics
Detectors
feature fusion
competitive attention
Pedestrian detection
Proposals
semantic supervision
Deep Feature Fusion by Competitive Attention for Pedestrian Detection
Pedestrian detection is a key problem for automatic driving, and the results have been improved significantly via deep convolutional networks. However, there is still room to improve the performance of pedestrian detection by carefully dealing with some critical issues. To take advantages of more discriminative information for pedestrian detection, we propose a novel architecture to auto-choose semantic as well as specific information among the feature maps at different levels and integrate valuable information among the feature maps in multi-scales. Particularly, our architecture consists of feature maps concatenating in different levels and feature maps integrating with multi-scales. Both the operations are equipped with a competitive attention block. The architecture has the ability to obtain more efficient and discriminating features for pedestrian detection. In comparison with the other prevailing models, our architecture provides superior performance. The promising results achieved through experimentation with this architecture achieve a new state-of-the-art on Caltech dataset.
2019
21981-21989
journalArticle
7
IEEE Access
DOI 10.1109/ACCESS.2019.2946589
IEEE Access
ISSN 2169-3536
Y. Shen
Y. Yin
C. Zhao
B. Li
J. Wang
G. Li
Z. Zhang
Convolutional neural networks
Training
Classification algorithms
convolution neural network
Image recognition
Agricultural machinery
Impurities
impurity recognition
Wheat images
WheNet network
Image Recognition Method Based on an Improved Convolutional Neural Network to Detect Impurities in Wheat
Impurities in wheat seriously affect wheat quality and food security. They are mainly produced during the operational process of combine harvesters. To solve the recognition and classification problems associated with impurities in wheat, a recognition method using an improved convolutional neural network is proposed in this article. A labeled dataset of normal wheat and five impurities is constructed, using which the Wiener filtering algorithm and the multi-scale Retinex enhancement algorithm are employed for image preprocessing. Based on network research using Inception_v3, improvement and optimization are undertaken before designing the WheNet convolutional neural network, which is intended for automatic recognition of wheat images. Under the same conditions, comparative experiments using the WheNet, ResNet_101 and Inception_v3 networks are conducted. Indexes such as receiver operating characteristic, area under curve (AUC), and recall rate are adopted to evaluate the experimental outcomes. Experimental results indicate that the WheNet network achieved the most efficient results. It also shows a shorter training time, and its recognition accuracies for Top_1 and Top_5 of the test set are 98.59% and 99.98%, respectively. The mean values of both the AUC and recall rate of the network on the recognition of various images of impurities are higher than those of the ResNet_101 and Inception_v3 networks. Consequently, the WheNet network can be a useful tool in recognizing impurities in wheat. Furthermore, this method can be used to detect impurities in other fields.
2019
162206-162218
journalArticle
8
IEEE Access
DOI 10.1109/ACCESS.2020.3023894
IEEE Access
ISSN 2169-3536
M. Faisal
M. Alsulaiman
M. Arafah
M. A. Mekhtiche
date fruit classification
deep learning
Image color analysis
neural networks
Robots
Vegetation
Agriculture
Machine learning
Task analysis
Maturity detection
IHDS: Intelligent Harvesting Decision System for Date Fruit Based on Maturity Stage Using Deep Learning and Computer Vision
Date is the main fruit crop of the Kingdom of Saudi Arabia (KSA), approximately covering 72% of the total area under permanent crops. The Food and Agriculture Organization states that date production worldwide was 3,430,883 tons in 1990, which increases yearly, reaching 8,526,218 tons in 2018. Date production in KSA was around 527,881 tons in 1990, approximately reaching 1,302,859 tons in 2018. Harvesting date fruits at an appropriate time according to a specific maturity stage or level is a critical decision that significantly affects profit. In the present study, we proposed an intelligent harvesting decision system (IHDS) based on date fruit maturity level. The proposed decision system used computer vision and deep learning (DL) techniques to detect seven different maturity stages/levels of date fruit (Immature stage 1, Immature stage 2, Pre-Khalal, Khalal, Khalal with Rutab, Pre-Tamar, and Tamar). In the IHDS, we developed six different DL systems, and each one produced different accuracy levels in terms of the seven aforementioned maturity stages. The IHDS used datasets that have been collected by the Center of Smart Robotics Research. The maximum performance metrics of the proposed IHDS were 99.4%, 99.4%, 99.7%, and 99.7% for accuracy, F1 score, sensitivity (recall), and precision, respectively.
2020
167985-167997
journalArticle
10
IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
DOI 10.1109/JSTARS.2017.2713039
12
IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
ISSN 2151-1535
J. Zhang
Y. Huang
Z. Li
P. Liu
L. Yuan
Feature extraction
Noise
Wavelet transforms
Noise measurement
Continuous wavelet transforms
Hyperspectral sensors
Informatics
parameter estimation
Parameter estimation
Pigments
vegetation
wavelet transforms
Noise-Resistant Spectral Features for Retrieving Foliar Chemical Parameters
Foliar chemical constituents are important indicators for understanding vegetation growing status and ecosystem functionality. Provided the noncontact and nondestructive traits, the hyperspectral analysis is a superior and efficient method for deriving these parameters. In practice, the spectral noise issue significantly impacts the performance of the hyperspectral retrieving system. To systematically investigate this issue, by introducing varying levels of noise to spectral signals, an assessment on noise-resistant capability of spectral features and models for retrieving concentrations of chlorophyll, carotenoids, and leaf water content was conducted. Given the continuous wavelet analysis (CWA) showed superior performance in extracting critical information associating plants biophysical and biochemical status in recent years, both wavelet features (WFs) and some conventional features (CFs) were chosen for the test. Two datasets including a leaf optical properties experiment dataset (n = 330), and a corn leaf spectral experiment dataset (n = 213) were used for analysis and modeling. The results suggested that the WFs had stronger correlations with all leaf chemical parameters than the CFs. According to an evaluation by decay rate of retrieving error that indicates noise-resistant capability, both WFs and CFs exhibited strong resistance to spectral noise. Particularly for WFs, the noise-resistant capability is relevant to the scale of the features. Based on the identified spectral features, both univariate and multivariate retrieving models were established and achieved satisfactory accuracies. Synthesizing the retrieving accuracy, noise resistivity, and model's complexity, the optimal univariate WF-models were recommended in practice for retrieving leaf chemical parameters.
Dec. 2017
5369-5380
journalArticle
11
IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
DOI 10.1109/JSTARS.2017.2751148
1
IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
ISSN 2151-1535
I. Ben Slimene Ben Amor
N. Chehata
J. -S. Bailly
I. R. Farah
P. Lagacherie
Training
Agriculture
Remote sensing
Entropy
random forest (RF)
agriculture
Labeling
Measurement
Uncertainty
Active learning (AL)
diversity
mean-shift clustering
multispectral
object based
uncertainty
Parcel-Based Active Learning for Large Extent Cultivated Area Mapping
This paper focuses on agricultural land cover mapping at a high-resolution scale and over large areas from an operational point of view and from a high-resolution monodate image. In this context, training data are assumed to be collected by successive journeys of held surveys and, thus, are very limited. Supervised learning techniques are generally used, assuming that the classes distribution is constant over the whole image. However, in practice, a data shift often occurs on large areas due to various acquisition conditions. To alleviate these issues, active learning (AL) techniques dehne an efhcient training set by iteratively adapting it through adding the most informative unlabeled instances. They can improve the classihcation process efhciency while keeping a limited training dataset. The novelty in this paper is the application of AL techniques on multispectral images for agricultural land cover mapping, using held sampling instead of pixel sampling, which is rarely done in the literature. Besides, we proposed a parcel-based AL scheme that is suitable for an operational land cover mapping in cultivated areas since the parcel is an agricultural unit and held observations are processed at parcel scale. Random forests classiher was used. Results were processed on a 6 m multispectral Spot6 image over a 35 km2 Mediterranean cultivated area, in Lebna Catchment, north eastern Tunisia. The contribution of AL techniques was assessed with comparison to a random and stratihed random strategies for sampling new instances. For iterative sample selection, two criteria are used and often coupled: uncertainty and diversity. For diversity metric, a new clustering-based metric was proposed based on a mean-shift clustering, which improved the classihcation accuracy. AL techniques showed to be efhcient with complex data and hne land cover legend improving random-based selection up to 10%. Besides, the maximum of classihcation accuracy is reached using mean-shift breaking ties metric in just 5-day held survey, i.e., 30 days less compared to the random selection. Finally, results showed that the hner the dehnition of land cover classes, the more crucial is the choice of AL metrics.
Jan. 2018
79-88
journalArticle
9
IEEE Access
DOI 10.1109/ACCESS.2021.3056577
IEEE Access
ISSN 2169-3536
M. Tufail
J. Iqbal
M. I. Tiwana
M. S. Alam
Z. A. Khan
M. T. Khan
Feature extraction
Image color analysis
Agriculture
Support vector machines
Shape
precision agriculture
Automation
Crop and weed detection
machine-learning
Spraying
Identification of Tobacco Crop Based on Machine Learning for a Precision Agricultural Sprayer
Agrochemicals, which are very efficacious in protecting crops, also cause environmental pollution and pose serious threats to farmers’ health upon exposure. In order to cut down the environmental and human health risks associated with agrochemical application, there is a need to develop intelligent application equipment that could detect and recognize crops/weeds, and spray precise doses of agrochemical at the right place and right time. This paper presents a machine-learning based crop/weed detection system for a tractor-mounted boom sprayer that could perform site-specific spraying on tobacco crop in fields. An SVM classifier with a carefully chosen feature combination (texture, shape, and color) for tobacco plant has been proposed and 96% classification accuracy has been achieved. The algorithm has been trained and tested on a real dataset collected in local fields with diverse changes in scale, orientation, background clutter, outdoor lighting conditions, and variation between tobacco and weeds. Performance comparison of the proposed algorithm has been made with a deep learning based classifier (customized for real-time inference). Both algorithms have been deployed on a tractor-mounted boom sprayer in tobacco fields and it has been concluded that the SVM classifier performs well in terms of accuracy (96%) and real-time inference (6 FPS) on an embedded device (Raspberry Pi 4). In comparison, the customized deep learning-based classifier has an accuracy of 100% but performs much slower (0.22 FPS) on the Raspberry Pi 4.
2021
23814-23825
journalArticle
8
IEEE Access
DOI 10.1109/ACCESS.2020.3031914
IEEE Access
ISSN 2169-3536
T. N. Pham
L. V. Tran
S. V. T. Dao
Feature extraction
Diseases
Training
Agriculture
Plants (biology)
feature selection
precision agriculture
Artificial neural networks
image classification
Neural network
plant disease
Early Disease Classification of Mango Leaves Using Feed-Forward Neural Network and Hybrid Metaheuristic Feature Selection
Plant disease, especially crop plants, is a major threat to global food security since many diseases directly affect the quality of the fruits, grains, and so on, leading to a decrease in agricultural productivity. Farmers have to observe and determine whether a leaf was infected by naked eyes. This process is unreliable, inconsistent, and error prone. Several works on deep learning techniques for detecting leaf diseases had been proposed. Most of them built their models based on limited resolution images using convolutional neural networks (CNNs). In this research, we aim at detecting early disease on plant leaves with small disease blobs, which can only be detected with higher resolution images, by an artificial neural network (ANN) approach. After a pre-processing step using a contrast enhancement method, all the infested blobs are segmented for the whole dataset. A list of several measurement-based features that represents the blobs are chosen and then selected based on their influences on the model's performance using a wrapper-based feature selection algorithm, which is built based on a hybrid metaheuristic. The chosen features are used as inputs for an ANN. We compare the results obtained using our methods with another approach using popular CNN models (AlexNet, VGG16, ResNet-50) enhanced with transfer learning. The ANN's results are better than those of CNNs using a simpler network structure (89.41% vs 78.64%, 79.92%, and 84.88%, respectively). This shows that our approach can be implemented on low-end devices such as smartphones, which will be of great assistance to farmers on the field.
2020
189960-189973
journalArticle
9
IEEE Transactions on Network Science and Engineering
DOI 10.1109/TNSE.2021.3103602
6
IEEE Transactions on Network Science and Engineering
ISSN 2327-4697
M. Afrin
J. Jin
A. Rahman
A. Gasparri
Y. -C. Tian
A. Kulkarni
Cloud computing
Internet of Things
Robot sensing systems
Cyber-physical systems
Resource management
Social factors
Edge computing
cloud computing
Energy consumption
Quality of service
Quality-of-Service.
resource allocation
Service robots
Smart manufacturing
Robotic Edge Resource Allocation for Agricultural Cyber-Physical System
Cloud-aided robots are increasingly adopted in realizing Cyber-Physical-Social System (CPSS) to reduce human efforts and enhance the system performance with diverse robotic applications. However, the multi-hop distance from robot to cloud data centre elevates the data transfer delay that often inhibits the deadline-satisfied task execution of robotic applications. Thanks to edge computing, this issue can be well addressed by harnessing computing resources in proximity of data sources. As edge resources are constrained in energy and processing capacity, sharing resources among the tasks of multiple robotic applications is critical to ensure. Therefore, in this paper, we develop a congestion game-theoretic robotic edge resource allocation mechanism for CPSS, which not only maintains the Quality-of-Service (QoS) by meeting task completion deadlines but also satisfies the energy constraints of resources. Here, Agriculture 4.0 is considered as a use case for the proposed mechanism which can be extended for other domains. Nevertheless, the performance evaluation of proposed mechanism is conducted in an iFogSim simulated edge computing environment. In comparison with existing greedy, heuristic, and evolutionary benchmarks, our mechanism is proven to offer overall 20% improvement in deadline satisfaction, energy consumption, and resource utilization.
1 Nov.-Dec. 2022
3979-3990
journalArticle
13
IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
DOI 10.1109/JSTARS.2020.2990104
IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
ISSN 2151-1535
Z. Sun
L. Di
H. Fang
A. Burgess
Feature extraction
Agriculture
Artificial satellites
Earth
Remote sensing
Task analysis
Satellites
image classification
Landsat
Agricultural remote sensing
crop mapping
deep neural network (dnn)
geoprocessing workflow
North Dakota
Deep Learning Classification for Crop Types in North Dakota
Recently, agricultural remote sensing community has endeavored to utilize the power of artificial intelligence (AI). One important topic is using AI to make the mapping of crops more accurate, automatic, and rapid. This article proposed a classification workflow using deep neural network (DNN) to produce high-quality in-season crop maps from Landsat imageries for North Dakota. We use historical crop maps from the agricultural department and North Dakota ground measurements as training datasets. Processing workflows are created to automate the tedious preprocessing, training, testing, and postprocessing workflows. We tested this hybrid solution on new images and received accurate results on major crops such as corn, soybean, barley, spring wheat, dry beans, sugar beets, and alfalfa. The pixelwise overall accuracy in all three test regions is over 82% for all land types (including noncrop land), which is the same level of accuracy as the U.S. Department of Agriculture Cropland Data Layer. The texture of DNN maps is more consistent with fewer noises, which is more comfortable to read. We find DNN is better on recognizing big farmlands than recognizing the scattered wetlands and suburban regions in North Dakota. The model trained on multiple scenes of multiple years and months yields higher accuracy than any of the models trained only on a single scene, a single month, or a single year. These results reflect that DNN can produce reliable in-season maps for major crops in North Dakota big farms and could provide a relatively accurate reference for the minor crops in scattered wetland fields.
2020
2200-2213
journalArticle
10
IEEE Access
DOI 10.1109/ACCESS.2022.3154350
IEEE Access
ISSN 2169-3536
S. P. Raja
B. Sawicka
Z. Stamenkovic
G. Mariammal
Crops
Data models
Monitoring
Agriculture
Temperature sensors
classification
feature selection
Security
Soil
Zigbee
crop prediction
Crop Prediction Based on Characteristics of the Agricultural Environment Using Various Feature Selection Techniques and Classifiers
Agriculture is a growing field of research. In particular, crop prediction in agriculture is critical and is chiefly contingent upon soil and environment conditions, including rainfall, humidity, and temperature. In the past, farmers were able to decide on the crop to be cultivated, monitor its growth, and determine when it could be harvested. Today, however, rapid changes in environmental conditions have made it difficult for the farming community to continue to do so. Consequently, in recent years, machine learning techniques have taken over the task of prediction, and this work has used several of these to determine crop yield. To ensure that a given machine learning (ML) model works at a high level of precision, it is imperative to employ efficient feature selection methods to preprocess the raw data into an easily computable Machine Learning friendly dataset. To reduce redundancies and make the ML model more accurate, only data features that have a significant degree of relevance in determining the final output of the model must be employed. Thus, optimal feature selection arises to ensure that only the most relevant features are accepted as a part of the model. Conglomerating every single feature from raw data without checking for their role in the process of making the model will unnecessarily complicate our model. Furthermore, additional features which contribute little to the ML model will increase its time and space complexity and affect the accuracy of the model’s output. The results depict that an ensemble technique offers better prediction accuracy than the existing classification technique.
2022
23625-23641
journalArticle
9
IEEE Access
DOI 10.1109/ACCESS.2021.3109015
IEEE Access
ISSN 2169-3536
S. I. Moazzam
U. S. Khan
W. S. Qureshi
M. I. Tiwana
N. Rashid
W. S. Alasmary
J. Iqbal
A. Hamza
Agriculture
Semantics
Sensors
Drones
Spraying
Autonomous weed detection
Convolutional codes
deep learning in agriculture
drone weed detection
multispectral image processing
Sugar industry
A Patch-Image Based Classification Approach for Detection of Weeds in Sugar Beet Crop
Weeds affects crops health as it shares water and nutrients from the soil, as a result it decreases crop yield. Manual weedicide spray through bag-pack is hazardous to human health. Localized autonomous weedicide spray through aerial spraying units can help save water, weedicide chemical and effect less on human health. Such systems require multi-spectral cues to classify crop, weed, and soil surface. Our focus in this paper is on the detection of weeds in the sugar beet crop, using air-borne multispectral camera sensors, which is considered as an alternative crop to sugarcane to obtain sugar in Pakistan. We developed a new framework for weed identification; a patch-based classification approach as appose to semantic segmentation that is more realistic for real-time intelligent aerial spraying systems. Our approach converts 3-class pixel classification problem into a 2-class crop-weed patch classification problem which in turns improves crop and weed classification accuracy. For classification, we developed a new VGG-Beet convolutional neural network (CNN), which is based on generic VGG16 (visual graphics group) CNN model with 11 convolutional layers. For experiments, we captured a sugar beet dataset with 3-channel multispectral sensor with a ground sampling distance (GSD) of 0.2 cm/pixel and a height of 4 meters. For better comparison, we used two publicly available sugar beet crop aerial imagery datasets, captured using a 5-channel multispectral sensor and a 4-Channel multispectral sensor with a ground sampling distance of 1cm and a height of 10 meters. We observed that patch-based method is more robust to different lighting conditions. To produce low cost weed detection system usage of Agrocam sensor is recommended, for higher accuracy Red Edge and Sequoia multispectral sensors with more channels should be deployed. We observed higher crop-weed accuracy and lower testing time for our patch-based approach as compared to U-Net and Deeplab based semantic segmentation networks.
2021
121698-121715
journalArticle
53
IEEE Transactions on Geoscience and Remote Sensing
DOI 10.1109/TGRS.2015.2428197
10
IEEE Transactions on Geoscience and Remote Sensing
ISSN 1558-0644
S. Basu
S. Ganguly
R. R. Nemani
S. Mukhopadhyay
G. Zhang
C. Milesi
A. Michaelis
P. Votava
R. Dubayah
L. Duncanson
B. Cook
Y. Yu
S. Saatchi
R. DiBiano
M. Karki
E. Boyda
U. Kumar
S. Li
Feature extraction
Vegetation
Image resolution
Image segmentation
machine learning
Accuracy
Laser radar
Aerial imagery
conditional random field (CRF)
high-performance computing (HPC)
NASA
National Agriculture Imagery Program (NAIP)
neural network (NN)
statistical region merging (SRM)
A Semiautomated Probabilistic Framework for Tree-Cover Delineation From 1-m NAIP Imagery Using a High-Performance Computing Architecture
Accurate tree-cover estimates are useful in deriving above-ground biomass density estimates from very high resolution (VHR) satellite imagery data. Numerous algorithms have been designed to perform tree-cover delineation in high-to-coarse-resolution satellite imagery, but most of them do not scale to terabytes of data, typical in these VHR data sets. In this paper, we present an automated probabilistic framework for the segmentation and classification of 1-m VHR data as obtained from the National Agriculture Imagery Program (NAIP) for deriving tree-cover estimates for the whole of Continental United States, using a high-performance computing architecture. The results from the classification and segmentation algorithms are then consolidated into a structured prediction framework using a discriminative undirected probabilistic graphical model based on conditional random field, which helps in capturing the higher order contextual dependence relations between neighboring pixels. Once the final probability maps are generated, the framework is updated and retrained by incorporating expert knowledge through the relabeling of misclassified image patches. This leads to a significant improvement in the true positive rates and reduction in false positive rates (FPRs). The tree-cover maps were generated for the state of California, which covers a total of 11 095 NAIP tiles and spans a total geographical area of 163 696 sq. miles. Our framework produced correct detection rates of around 88% for fragmented forests and 74% for urban tree-cover areas, with FPRs lower than 2% for both regions. Comparative studies with the National Land-Cover Data algorithm and the LiDAR high-resolution canopy height model showed the effectiveness of our algorithm for generating accurate high-resolution tree-cover maps.
Oct. 2015
5690-5708
journalArticle
10
IEEE Access
DOI 10.1109/ACCESS.2022.3219160
IEEE Access
ISSN 2169-3536
K. Agrawal
M. Aggarwal
S. Tanwar
G. Sharma
P. N. Bokoro
R. Sharma
Agriculture
security
Blockchain
Blockchains
agriculture
privacy
Taxonomy
trust
Medical services
Cryptography
banking
e-voting
Electronic voting
ethereum
healthcare
Intellectual property
Power capacitors
Trust computing
An Extensive Blockchain Based Applications Survey: Tools, Frameworks, Opportunities, Challenges and Solutions
Many security standards and cryptographic solutions exist for different applications such as agriculture, aircraft, banking systems and etc. but a more effective and efficient solution can be given by combining existing technologies with blockchain. This work addresses the problems of previous works such as scalability, immutability, robustness, network latency, auditability, and traceability. Satoshi Nakamoto introduced Blockchain (BC) to tackle the Address Resolution Protocol (ARP) spoofing attacks, Distributed Denial of Service (DDoS), phishing problems and various security issues. Blockchain is a technology that stores the data using a chain of blocks in an encrypted form with hashing algorithms. It uses the decentralized architecture to store the information that helps users and customers to have transparency on records. The data is stored in a distributed ledger that is tamperproof and immutable. To amalgamate the research done so far, this paper presents a systematic review of ten different applications and tools used in blockchain. The applications include academics and education, agriculture, aircraft, banking, car sharing, e-voting, healthcare, Internet of Things (IoT), Intellectual Property Rights (IPR), and Supplychain (SC). Moreover, this paper presented a taxonomy for these applications and analyzed the implementation of tools used in different domains. Different open issues and challenges and key takeaways of blockchain technology were also highlighted. Hence, this paper helps give a new insight into working with blockchain and deciding on appropriate tools and approaches for a particular application.
2022
116858-116906
journalArticle
7
IEEE Access
DOI 10.1109/ACCESS.2019.2907383
IEEE Access
ISSN 2169-3536
U. P. Singh
S. S. Chouhan
S. Jain
S. Jain
Convolutional neural networks
Deep learning
Diseases
Training
Agriculture
Biological system modeling
Real-time systems
precision agriculture
image classification
Convolutional neural network
plant pathology
Multilayer Convolution Neural Network for the Classification of Mango Leaves Infected by Anthracnose Disease
Fungal diseases not only influence the economic importance of the plants and its products but also abate their ecological prominence. Mango tree, specifically the fruits and the leaves are highly affected by the fungal disease named as Anthracnose. The main aim of this paper is to develop an appropriate and effective method for diagnosis of the disease and its symptoms, therefore espousing a suitable system for an early and cost-effective solution of this problem. Over the last few years, due to their higher performance capability in terms of computation and accuracy, computer vision, and deep learning methodologies have gained popularity in assorted fungal diseases classification. Therefore, for this paper, a multilayer convolutional neural network (MCNN) is proposed for the classification of the Mango leaves infected by the Anthracnose fungal disease. This paper is validated on a real-time dataset captured at the Shri Mata Vaishno Devi University, Katra, J&K, India consists of 1070 images of the Mango tree leaves. The dataset contains both healthy and infected leaf images. The results envisage the higher classification accuracy of the proposed MCNN model when compared to the other state-of-the-art approaches.
2019
43721-43729
journalArticle
60
IEEE Transactions on Geoscience and Remote Sensing
DOI 10.1109/TGRS.2022.3162726
IEEE Transactions on Geoscience and Remote Sensing
ISSN 1558-0644
F. Zhao
W. Ma
P. Köhler
X. Ma
H. Sun
W. Verhoef
J. Zhao
Y. Huang
Z. Li
A. K. Ratul
Absorption
Atmospheric modeling
Satellites
retrieval
Instruments
Sea measurements
Atmospheric measurements
Data-driven approach
Fluorescence
red Solar-Induced chlorophyll Fluorescence (SIF)
SIF
TROPOspheric Monitoring Instrument (TROPOMI)
Retrieval of Red Solar-Induced Chlorophyll Fluorescence With TROPOMI on the Sentinel-5 Precursor Mission
Solar-Induced chlorophyll Fluorescence (SIF) retrieved from spaceborne hyperspectral measurements can provide a synoptic perspective on the functioning of photosynthetic active vegetation and algae. The TROPOspheric Monitoring Instrument (TROPOMI) onboard the Sentinel-5 precursor mission provides data for the retrieval of SIF with an unprecedented resolution in the spatial and temporal dimensions. In this study, we propose an approach for the retrieval of the red SIF peak value (at around 685 nm) over both land and ocean from TROPOMI measurements. This approach exploits the solar Fraunhofer lines located in the spectral window of 669–686 nm to disentangle SIF from the solar radiation reflected by the surface–atmosphere system. First, through simulated TROPOMI-like datasets, we determine the proper parameter settings and demonstrate the feasibility of the approach for the red SIF retrieval from TROPOMI data. Then, the approach is applied to real TROPOMI measurements. The red SIF retrieved with the proposed approach for two months’ TROPOMI data is compared with another TROPOMI red SIF dataset and the marine normalized fluorescence line height (nFLH) product of the Aqua Moderate Resolution Imaging Spectroradiometer (MODIS). The comparisons display similar spatial distributions over both land and ocean for the weekly global composites. Especially, the comparison of the two red SIF datasets demonstrates good agreement overall, indicating consistency of the two retrieval approaches. The retrieval uncertainty for the weekly global composite is about 13% and 10% of the peak SIF value over land/ocean, respectively, which can be considered as satisfactory error thresholds for global SIF observations.
2022
1-14
journalArticle
8
IEEE Access
DOI 10.1109/ACCESS.2020.2969451
IEEE Access
ISSN 2169-3536
Y. Li
Z. Huang
Z. Cao
H. Lu
H. Wang
S. Zhang
Feature extraction
Image color analysis
Agriculture
Image segmentation
Indexes
Vegetation mapping
Green products
Crop segmentation
performance evaluation
pixel-based classification
region-based classification
Performance Evaluation of Crop Segmentation Algorithms
This paper presents a thorough evaluation of twenty-one state-of-the-art widely-used crop segmentation algorithms, motived by their significance in vision tasks for further analysis. An ideal crop segmentation algorithm can effectively extract crop information, thus providing an important precondition for the application of intelligent agriculture analytics. In order to enable researchers in this field to fully understand various crop segmentation methods, this paper proposes a new classification strategy of object segmentation by dividing the algorithms into pixel-based and region-based approaches at first, and then systematically evaluating various crop segmentation methods with a unified data benchmark and four common metrics. A new dataset which incorporates crop variety, environment condition and observation distance into consideration is constructed for demonstrating the experiments and comparisons. The effectiveness and robustness of these algorithms were evaluated by three sets of comparative experiments. Based on the quantitative results, we summarize the advantages and disadvantages of the evaluated algorithms from the segmentation performances with four metric indicators. Furthermore, the discussion and evaluation results will provide great support for precision agriculture analysis.
2020
36210-36225
journalArticle
10
IEEE Access
DOI 10.1109/ACCESS.2022.3176643
IEEE Access
ISSN 2169-3536
H. Yang
T. Wen
X. Yang
H. Lin
Crops
Deep learning
Training
Classification algorithms
Semantics
Internet of Things
agricultural information classification
economic management
forward and reverse generation algorithm
Text categorization
Deep Learning Agricultural Information Classification Combined With Internet of Things Technology in Agricultural Production and Economic Management
This study aims to explore the application of agricultural information classification combined with the Internet of Things technology in agricultural production and economic management in the context of deep learning (DL). The agricultural information classification system is built based on DL. In terms of experimental methods, qualitative and quantitative methods are used to compare the extractive forward and the generative reverse generation algorithm in the abstract generation method. Typical extraction methods that directly extract important sentences are relatively ineffective. The model parameter tuning and training of generative (regenerating new sentences) are difficult, and the effect does not reach the level of agricultural scientific research. Qualitative and quantitative evaluation practice proves that the effect is better. In the data training effect of Rice Digest, after nine days of iterative training for about 1400 steps, the loss value is 1.33, which is equal to the standard data set. In the data training effect of Wheat Digest, after nine days of iterative training for about 1400 steps, the loss value is 1.496, which is equal to the standard data set. Later, the existing original model is adjusted to fit the model of the agricultural dataset scale. Among them, the minimum learning rate is reduced from 0.01 to 0.003 to expand the learning rate drop rate. In the visual training comparison, when training to about 1400 steps, the cross-entropy loss function values are about 1.43 and 1.29, respectively. The curve smoothing factor is set to 0.97 to observe the overall change in target loss value. The results show that when the parameter settings remain unchanged, the loss value of the model starts to increase linearly at about 1400 steps, and the effect reaches the expected value. This study improves the relevance, completeness, and accuracy of information acquisition in the field of agricultural science and technology information and improves the utilization of agricultural information.
2022
54713-54719
journalArticle
7
IEEE Robotics and Automation Letters
DOI 10.1109/LRA.2022.3217000
4
IEEE Robotics and Automation Letters
ISSN 2377-3766
A. Siddique
A. Tabb
H. Medeiros
Data models
Training
Computational modeling
Task analysis
Predictive models
object detection
Semantics
Agricultural automation
segmentation and categorization
incremental learning
Self-supervised learning
semantic scene understanding
Self-Supervised Learning for Panoptic Segmentation of Multiple Fruit Flower Species
Convolutional neural networks trained using manually generated labels are commonly used for semantic or instance segmentation. In precision agriculture, automated flower detection methods use supervised models and post-processing techniques that may not perform consistently as the appearance of the flowers and the data acquisition conditions vary. We propose a self-supervised learning strategy to enhance the sensitivity of segmentation models to different flower species using automatically generated pseudo-labels. We employ a data augmentation and refinement approach to improve the accuracy of the model predictions. The augmented semantic predictions are then converted to panoptic pseudo-labels to iteratively train a multi-task model. The self-supervised model predictions can be refined with existing post-processing approaches to further improve their accuracy. An evaluation on a multi-species fruit tree flower dataset demonstrates that our method outperforms state-of-the-art models without computationally expensive post-processing steps, providing a new baseline for flower detection applications.
Oct. 2022
12387-12394
journalArticle
7
IEEE Access
DOI 10.1109/ACCESS.2019.2895243
IEEE Access
ISSN 2169-3536
C. -W. Lin
Q. Ding
W. -H. Tu
J. -H. Huang
J. -F. Liu
Feature extraction
Vegetation
Forestry
Vegetation mapping
unmanned aerial vehicle
Hyperspectral sensors
Biomedical optical imaging
convolutional network
fast Fourier
Optical imaging
Plant classification
Fourier Dense Network to Conduct Plant Classification Using UAV-Based Optical Images
Plant classification is a science that is used to assess the quality of forest resources and has been studied extensively. In this paper, we proposed a novel convolutional neural network known as the Fourier Dense Network (FDN) which is a data-driven method to classify the optical aerial images of plants. To efficiently classify plants, the FDN learns and extracts the features of plants in time and frequency domains from the optical images captured using an unmanned aerial vehicle (UAV). In FDN, we designed a fast Fourier dense block (FF-dense block) that describes the features of the plants by using the magnitude and phase information in the frequency domain. Moreover, we used a transition layer to reduce the dimension of feature maps between two FF-dense blocks in the time domain. The primary contributions of this study are as follows: (1) an FF-dense block that considers frequency information and transfers the information into various layers of a block was designed; and (2) the characteristics between the time and frequency domains were repeatedly extracted and combined to more effectively describe the characteristics of tree species. To evaluate our study, we established a novel dataset comprising the UAV-based optical images of plants-vegetational optical aerial image dataset-for conducting plant classification and information retrieval. The dataset contains more than 21863 images of 12 plants. To the best of our knowledge, this is the largest publicly available dataset of the UAV-based optical images of plants. The experimental results demonstrated that the FDN can achieve state-of-the-art performance in terms of plant classification.
2019
17736-17749
journalArticle
8
IEEE Access
DOI 10.1109/ACCESS.2020.3038396
IEEE Access
ISSN 2169-3536
C. Wang
S. He
H. Wu
G. Teng
C. Zhao
J. Li
Convolutional neural networks
Feature extraction
convolutional neural network
Object detection
Robustness
Chemicals
Semantics
Cotton
Cotton topping
lightweight
multi-scale features
target detection
YOLOv3
Identification of Growing Points of Cotton Main Stem Based on Convolutional Neural Network
Identification of growing points of cotton main stem is the key to realize intelligent and precise machine topping and chemical topping. The identification of growing points by applying the traditional target detection model is subject to a series of shortcomings such as low accuracy, slow identification speed, large number of model parameters, huge storage cost and high calculation workload. On the basis of the advantages and disadvantages of YOLOv3, this paper proposed a modified YOLOv3 lightweight model for identifying the growing points of cotton main stem, which realized the multiplexing integration of low-level semantic features and high-level semantics features by adding dense connection modules and modifying the nonlinear transformation within the dense modules. This model significantly reduced the number of model parameters by utilizing deep separable convolution and improved the learning ability of multi-scale features by applying the hierarchical multi-scale method. Our model achieved an accuracy rate of 90.93% based on a self-prepared dataset, which is higher than the accuracy of the original YOLOv3 model by 1.64%, while the number of training parameters was significantly reduced by 48.90%. Compared with other target detection models under different illumination conditions and actual complex environments, the modified YOLOv3 model proposed in this paper showed better robustness, higher accuracy and higher speed in identifying the growing points of cotton main stem.
2020
208407-208417
journalArticle
9
IEEE Access
DOI 10.1109/ACCESS.2021.3131002
IEEE Access
ISSN 2169-3536
S. Barburiceanu
S. Meza
B. Orza
R. Malutan
R. Terebes
Convolutional neural networks
Feature extraction
Diseases
Support vector machines
Transfer learning
Task analysis
image classification
Object oriented modeling
Applied convolutional neural networks
leaf disease detection
texture classification
texture feature extraction
Convolutional Neural Networks for Texture Feature Extraction. Applications to Leaf Disease Classification in Precision Agriculture
This paper studies the use of deep-learning models (AlexNet, VggNet, ResNet) pre-trained on object categories (ImageNet) in applied texture classification problems such as plant disease detection tasks. Research related to precision agriculture is of high relevance due to its potential economic impact on agricultural productivity and quality. Within this context, we propose a deep learning-based feature extraction method for the identification of plant species and the classification of plant leaf diseases. We focus on results relevant to real-time processing scenarios that can be easily transferred to manned/unmanned agricultural smart machinery (e.g. tractors, drones, robots, IoT smart sensor networks, etc.) by reconsidering the common processing pipeline. In our approach, texture features are extracted from different layers of pre-trained Convolutional Neural Network models and are later applied to a machine-learning classifier. For the experimental evaluation, we used publicly available datasets consisting of RGB textured images and datasets containing images of healthy and non-healthy plant leaves of different species. We compared our method to feature vectors derived from traditional handcrafted feature extraction descriptors computed for the same images and end-to-end deep-learning approaches. The proposed method proves to be significantly more efficient in terms of processing times and discriminative power, being able to surpass traditional and end-to-end CNN-based methods and provide a solution also to the problem of the reduced datasets available for precision agriculture.
2021
160085-160103
journalArticle
7
IEEE Access
DOI 10.1109/ACCESS.2019.2953085
IEEE Access
ISSN 2169-3536
Y. Zhao
F. Lin
S. Liu
Z. Hu
H. Li
Y. Bai
Feature extraction
Deep learning
Diseases
Training
Agriculture
Image segmentation
Neural networks
class imbalance
convolutional neural networks (CNN)
focal Loss
hard example
Constrained-Focal-Loss Based Deep Learning for Segmentation of Spores
The statistics of disease spores is significant for early strategy design of disease control in precision agriculture. To obtain the statistics information of spores in microscopic images, it is crucial to segment spores from images. In this paper, we research a deep learning based method to segment spores, taking anthrax spores as the research objects. We first built an anthrax spore dataset consisting of more than 40,000 spores with accurate labeled spore boundaries to advance the state of the art technology of spore statistics. Then on consideration of the complex class imbalances in actual anthrax spore images, we investigate how class imbalances and hard examples simultaneously influence the loss during training and we discover that hard examples are more likely to appear at the pixels of rare pixels, such as small class pixels and contour pixels. Based on this discovery, we propose Constrained Focal Loss (CFL), which focuses on small class objects, and has a constrained term related to hard examples. In addition, we further propose CFL*, where high importance is put on the pixels surrounding spore contours to improve classification accuracy. The results show that the mean IoU of the DeepLabv3+ trained with CFL* (called as CFL*Net) achieves 91.0%, higher than original DeepLabv3+ with cross-entropy by 8.6 points, and the DeepLabv3+ with Focal Loss by 10.4 points. Moreover, CFLNet* can achieve better performance than original DeepLabv3+, using less than one-third of the training samples and half of the training steps.
2019
165029-165038
journalArticle
12
IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
DOI 10.1109/JSTARS.2019.2903642
10
IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
ISSN 2151-1535
R. Jalal
Z. Iqbal
M. Henry
G. Franceschini
M. S. Islam
M. Akhter
Z. T. Khan
M. A. Hadi
M. A. Hossain
M. G. Mahboob
T. S. Udita
T. Aziz
S. M. Masum
L. Costello
C. R. Saha
A. A. M. Chowdhury
A. Salam
F. Shahrin
F. R. Sumon
M. Rahman
M. A. Siddique
M. M. Rahman
M. N. Jahan
M. F. Shaunak
M. S. Rahman
M. R. Islam
N. Mosca
R. D’Ánnunzio
S. Hira
A. D. Gregorio
Earth
Forestry
Image segmentation
Remote sensing
Conferences
Consistency
harmonization
interoperability
land cover ontology
Organizations
standardization
Standards organizations
Toward Efficient Land Cover Mapping: An Overview of the National Land Representation System and Land Cover Map 2015 of Bangladesh
In response to prevailing classification inconsistency between land cover maps, developed by different organizations in different times at different scales, an object-based National Land Representation System (NLRS) for Bangladesh has been developed. The process, which began in 2013 and was completed in 2016, brought together several national organizations and involved an extensive process of consultation, data collection, translation, and analysis of existing land cover/use classification systems. The process focused on the interpretation of three legends from historic national land cover/use maps. Field inventory data were collected from over 1000 sites across the country to assist the process of land characterization and the development of a dynamic and representative overview of land cover and land use in Bangladesh. The system has been applied to the development of a wall-to-wall national land cover map for the year 2015. In this article, the methodological process and results of NLRS formulation and land cover map 2015 are presented. We also provide examples of how this interoperable system and the land cover dataset are being used for variety of applications including national forest resources assessment, estimation of REDD+ activity data, integration of biophysical and socioeconomic information, and semantic similarity assessment.
Oct. 2019
3852-3861
journalArticle
11
IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
DOI 10.1109/JSTARS.2018.2813263
5
IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
ISSN 2151-1535
A. Habib
T. Zhou
A. Masjedi
Z. Zhang
J. Evan Flatt
M. Crawford
Agriculture
Hyperspectral imaging
Calibration
Sensors
Unmanned aerial vehicles
Satellites
hyperspectral imaging
unmanned aerial vehicles (UAVs)
Boresight calibration
direct georeferencing
integrated global navigation satellite system/inertial navigation system (GNSS/INS)
push-broom scanner
Boresight Calibration of GNSS/INS-Assisted Push-Broom Hyperspectral Scanners on UAV Platforms
Low-cost unmanned aerial vehicles (UAVs) utilizing push-broom hyperspectral scanners are poised to become a popular alternative to conventional remote sensing platforms such as manned aircraft and satellites. In order to employ this emerging technology in fields such as high-throughput phenotyping and precision agriculture, direct georeferencing of hyperspectral data using onboard integrated global navigation satellite systems (GNSSs) and inertial navigation systems (INSs) is required. Directly deriving the scanner position and orientation requires the spatial and rotational relationship between the coordinate systems of the GNSS/INS and hyperspectral scanner to be measured. The spatial offset (lever arm) between the scanner and GNSS/INS unit can be measured manually. However, the angular relationship (boresight angles) between the scanner and GNSS/INS coordinate systems, which is more critical for accurate generation of georeferenced products, is difficult to establish. This paper presents three calibration approaches to estimate the boresight angles relating hyperspectral push-broom scanner and GNSS/INS coordinate systems. For reliable/practical estimation of the boresight angles, this paper starts with establishing the optimal/minimal flight and control/tie point configuration through a bias impact analysis starting from the point positioning equation. Then, an approximate calibration procedure utilizing tie points in overlapping scenes is presented after making some assumptions about the flight trajectory and topography of covered terrain. Next, two rigorous approaches are introduced – one using ground control points and other using tie features. The approximate/rigorous approaches are based on enforcing the collinearity and coplanarity of the light rays connecting the perspective centers of the imaging scanner, object point, and the respective image points. To evaluate the accuracy of the proposed approaches, estimated boresight angles are used for orthorectification of six hyperspectral UAV dataset acquired over an agricultural field. Qualitative and quantitative evaluations of the results have shown significant improvement in the derived orthophotos to a level equivalent to the ground sampling distance of the used scanner (namely, 3–5 cm when flying at 60 m).
May 2018
1734-1749
journalArticle
11
IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
DOI 10.1109/JSTARS.2018.2805775
5
IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
ISSN 2151-1535
V. Brancato
I. Hajnsek
Soil measurements
Soil moisture
Synthetic aperture radar
Agriculture
Vegetation mapping
soil moisture
biomass
Biomass
differential SAR interferometry (DInSAR)
Interferometry
polarimetry
synthetic aperture radar
Analyzing the Influence of Wet Biomass Changes in Polarimetric Differential SAR Interferometry at L-Band
The displacement estimated with differential SAR interferometry (DInSAR) might not be unique when more than one polarization channel is available. For the case of agricultural areas, these ambiguities have been mainly related to complex vegetation dynamics, i.e., vegetation growth. This study intends to explore the potential of a synergistic use of DInSAR with SAR Polarimetry (PolDInSAR) in tracking changes within agricultural vegetation covers. The connection between the PolDInSAR observables (i.e., herein, the DInSAR phases at various polarization channels and/or their linear combinations) with wet biomass and soil water content changes is empirically investigated with linear regression techniques. This is done in the frame of an L-band airborne DInSAR dataset. The impact of vegetation vigor differs depending on the type of crop analyzed. For those crops exhibiting a birefringent electromagnetic propagation (i.e., barley, wheat, and rapeseed), the influence of wet biomass is particularly pronounced in the VV DInSAR phase but also in the HH-VV phase difference. Contrarily to the former, the latter shows also a scarce sensitivity to changes in soil water content. Therefore, this PolDInSAR observable is used to generate biomass maps of the analyzed test site. The predicted biomass variations are in good agreement with the collected in situ measurements, i.e., the coefficient of determination varies between 0.8 and 0.9.
May 2018
1494-1508
journalArticle
9
IEEE Access
DOI 10.1109/ACCESS.2021.3119655
IEEE Access
ISSN 2169-3536
M. Ahmad
M. Abdullah
H. Moon
D. Han
Convolutional neural networks
Crops
Feature extraction
Deep learning
Diseases
Training
convolutional neural networks
transfer learning
Transfer learning
image classification
Disease detection
Internet-of-Things
MobileNet
Plant Disease Detection in Imbalanced Datasets Using Efficient Convolutional Neural Networks With Stepwise Transfer Learning
Convolutional neural networks have demonstrated state-of-the-art performance in image classification and various other computer vision tasks. Plant disease detection is an important area of deep learning which has been addressed by many recent methods. However, there is a dire need to optimize these solutions for resource-constrained portable devices such as smartphones. This is a challenging problem because deep learning models are resource extensive in nature. This paper proposes an efficient method to systematically classify plant disease symptoms using convolutional neural networks. These networks are memory efficient and when coupled with the proposed training configuration it enables rapid development of industrial applications by reducing the training times. Another critical problem arises with the improper distribution of samples among classes known as the class imbalance problem, which is addressed by employing a simple statistical methodology. Transfer learning is a known technique for training small datasets which transfers pre-trained weights learned on a large dataset. However, during transfer learning, negative transfer learning is a common problem. Therefore, a stepwise transfer learning approach is proposed which can help in fast convergence, while reducing overfitting and preventing negative transfer learning during knowledge transfer across domains. The system is trained and evaluated on two plant disease datasets i.e., PlantVillage (a publicly available dataset) and pepper disease dataset provided by the National Institute of Horticultural and Herbal Science, Republic of Korea. The pepper dataset is particularly challenging as it contains images from different parts of the plant such as the leaf, pulp, and stem. The proposed system has dominated the previous works on the PlantVillage dataset and achieved 99% and 99.69% accuracy on the Pepper dataset and PlantVillage datasets, respectively.
2021
140565-140580
journalArticle
14
IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
DOI 10.1109/JSTARS.2021.3087555
IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
ISSN 2151-1535
Z. Hong
T. Yang
X. Tong
Y. Zhang
S. Jiang
R. Zhou
Y. Han
J. Wang
S. Yang
S. Liu
Synthetic aperture radar
Object detection
Optical sensors
Optical imaging
“you only look once”version 3 (YOLOv3)
Adaptive optics
Deep learning-based object detection
Marine vehicles
Optical reflection
ship detection
synthetic aperture radar (SAR) and optical imagery
Multi-Scale Ship Detection From SAR and Optical Imagery Via A More Accurate YOLOv3
Deep learning detection methods use in ship detection remains a challenge, owing to the small scale of the objects and interference from complex sea surfaces. In addition, existing ship detection methods rarely verify the robustness of their algorithms on multisensor images. Thus, we propose a new improvement on the “you only look once” version 3 (YOLOv3) framework for ship detection in marine surveillance, based on synthetic aperture radar (SAR) and optical imagery. First, improved choices are obtained for the anchor boxes by using linear scaling based on the k-means++ algorithm. This addresses the difficulty in reflecting the advantages of YOLOv3's multiscale detection, as the anchor boxes of a single detection target type between different detection scales have small differences. Second, we add uncertainty estimators for the positioning of the bounding boxes by introducing a Gaussian parameter for ship detection into the YOLOv3 framework. Finally, four anchor boxes are allocated to each detection scale in the Gaussian-YOLO layer instead of three as in the default YOLOv3 settings, as there are wide disparities in an object's size and direction in remote sensing images with different resolutions. Applying the proposed strategy to "YOLOv3-spp” and "YOLOv3-tiny,” the results are enhanced by 2%-3%. Compared with other models, the improved-YOLOv3 has the highest average precision on both the optical (93.56%) and SAR (95.52%) datasets. The improved-YOLOv3 is robust, even in the context of a mixed dataset of SAR and optical images comprising images from different satellites and with different scales.
2021
6083-6101
journalArticle
15
IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
DOI 10.1109/JSTARS.2022.3197794
IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
ISSN 2151-1535
V. Senyurek
M. M. Farhad
A. C. Gurbuz
M. Kurum
A. Adeli
Remote sensing
Land surface
Vegetation mapping
soil moisture (SM)
Global Positioning System
precision agriculture (PA)
Sea measurements
Cyclone global navigation satellite system (CYGNSS)
global navigation satellite system reflectometry (GNSS-R)
Microwave measurement
Probes
reflectometry
unmanned aircraft system (UAS)
Fusion of Reflected GPS Signals With Multispectral Imagery to Estimate Soil Moisture at Subfield Scale From Small UAS Platforms
This study proposes a low-cost and “proof-of-concept” methodology to obtain high spatial resolution soil moisture (SM) via processing reflected global positioning system (GPS) and a multispectral camera data acquired by small unmanned aircraft system (UAS) platforms. An SM estimation model is developed using a random forest (RF) machine-learning (ML) algorithm by combining features obtained from reflected GPS signals (collected by smartphones and commercial off-the-shelf receivers) in conjunction with ancillary vegetation indices from the multispectral camera data. The proposed ML algorithm uses in situ SM measurements acquired via SM probes as labels. A preliminary field experiment was conducted on 210 by 110 m (2.31 ha) crop fields (corn and cotton) in 2020 (from January to November, including crop planting through senescence time period) at Mississippi State University (MSU)’s the heavily instrumented North Farm to acquire data needed for the ML model to train and test. Our results showed that both fields could be covered by GPS reflectometry measurements with about 13 min of flight time at a 15-m altitude, and SM can be mapped with 5 × 5 m spatial resolution (corresponding to the elongated first Fresnel zone). The model is trained with and validated against eight in situ SM station datasets via tenfold and leave-one-probe-out cross-validation techniques. Overall, root-mean-square errors (RMSE) of 0.013 m $^{3}$ m$^{-3}$ volumetric SM and R-value of 0.95 [-] are obtained for tenfold cross validation. The proposed model reached an RMSE of 0.033 m$^{3}$ m$^{-3}$ and an R-value of 0.5 [-] in leave-one-probe-out cross validation. While having limited data, the results indicate that high-resolution SM measurement can be achieved with a low-cost GPS reflectometry system onboard a small UAS platform for use in precision agriculture applications.
2022
6843-6855
journalArticle
10
IEEE Access
DOI 10.1109/ACCESS.2022.3190618
IEEE Access
ISSN 2169-3536
H. Son
J. W. Lim
S. Park
B. Park
J. Han
H. B. Kim
M. C. Lee
K. -J. Jang
G. Kim
J. H. Chung
Support vector machines
Machine learning
machine learning
Statistics
Aging
Agricultural worker
fall-detection
human behavior recognition
Inertial sensors
Older adults
Sociology
wearable sensor
A Machine Learning Approach for the Classification of Falls and Activities of Daily Living in Agricultural Workers
Population aging is a global trend, and the highest proportion of elderly people in the workforce per unit of population is found in agricultural areas. However, few systematic studies have been conducted on farmer falls in the field of agricultural machinery. This study focuses on the application of classification methods for monitoring devices to detect fall/nonfall movements of farmworkers, where agricultural biomechanical factors are considered in detecting activities of daily living. In this study, we recorded and analyzed original acquisition datasets of signals obtained from two accelerometers and one gyroscope for 40 healthy individuals who performed various falls and activities of daily living (ADLs). Spatial characteristics were used to train the machine-learning classifiers to distinguish between fall and non-fall events. Supervised machine learning experiments evaluated the effectiveness of the proposed approach: the k-nearest neighbors (kNN) and support vector machine (SVM) algorithms achieved roc auc-scores of 0.999 in distinguishing falls and ADLs (binary-class classification). Moreover, an artificial neural network (ANN) classifier showed the highest performance in terms of classification roc auc-scores of 1.0. The evaluation metric demonstrated the highest performance in the analysis and evaluation of the signal obtained from the S2 acceleration sensor with a measurement range of ±16 g. The proposed SVM classifier evaluations showed a 0.988 roc auc-score for sensor tests in multi-class classification, along with the highest performance in terms of the F1-score and Matthews Correlation Coefficient (MCC) over 84% in the multi-class classification model for distinguishing each of ADLs and Fall using ±16 g acceleration sensor.
2022
77418-77431
journalArticle
60
IEEE Transactions on Geoscience and Remote Sensing
DOI 10.1109/TGRS.2022.3175635
IEEE Transactions on Geoscience and Remote Sensing
ISSN 1558-0644
T. Colligan
D. Ketchum
D. Brinkerhoff
M. Maneta
Crops
neural networks
Training
Artificial satellites
Earth
Remote sensing
Irrigation
Radio frequency
Landsat
A Deep Learning Approach to Mapping Irrigation Using Landsat: IrrMapper U-Net
Accurate maps of irrigation are essential for understanding and managing water resources. We present a new method of mapping irrigation based on an ensemble of convolutional neural networks that use reflectance information from Landsat imagery to classify irrigated pixels. The methodology does not rely on extensive feature engineering and does not condition the classification with land-use information from existing geospatial datasets. The ensemble does not need exhaustive hyperparameter tuning, and the analysis pipeline is lightweight enough to be implemented on a personal computer. Furthermore, the proposed methodology provides an estimate of the uncertainty associated with the classification. We evaluated our methodology and the resulting irrigation maps using a highly accurate novel spatially explicit ground-truth dataset, using county-scale United States Department of Agriculture (USDA) surveys of irrigation extent, and using cadastral surveys. We demonstrate the accuracy of the method by mapping irrigation over the state of Montana from 2000 to 2019. We found that our method outperforms other methods that use satellite remote-sensing information in terms of overall accuracy (OA) and precision. We found that our method agrees better statewide with the USDA National Agricultural Statistics Survey estimates of irrigated areas compared to other methods and has far fewer errors of commission in rainfed agriculture areas. This methodology has the potential to be applied across the entire United States and for the complete Landsat record.
2022
1-11
journalArticle
9
IEEE Access
DOI 10.1109/ACCESS.2021.3135536
IEEE Access
ISSN 2169-3536
R. Agarwal
N. S. Shekhawat
S. Kumar
A. Nayyar
B. Qureshi
Feature extraction
Agriculture
Support vector machines
feature selection
Optimization
Prediction algorithms
Soil
smart agriculture
Perturbation methods
perturbation rate
Soil prediction
spider monkey optimization
Improved Feature Selection Method for the Identification of Soil Images Using Oscillating Spider Monkey Optimization
Precision agriculture is the process that uses information and communication technology for farming and cultivation to improve overall productivity, efficient utilization of resources. Soil prediction is one of the primary phases in precision agriculture, resulting in good quality crops. In general, farmers perform the soil prediction manually. However, the efficiency of soil prediction may be enhanced by using current digital technologies. One effective way to automate soil prediction is image processing techniques in which soil images may be analyzed to determine the soil. This paper presents an efficient image analysis technique to predict the soil. For the same, a robust feature selection technique has been incorporated in the image analysis of soil images. The developed feature selection technique uses a new oscillating spider monkey optimization algorithm (OSMO) for the selection of features that are relevant and non-redundant. The new oscillating spider monkey optimization algorithm increases precision and convergence behavior by using an oscillating perturbation rate. A set of standard benchmark functions was deployed to visualize the performance of the new optimization technique (OSMO), and results were compared based on mean and standard deviation. Furthermore, the soil prediction approach is validated on a soil dataset, having seven categories. The proposed feature selection method selects the 41% relevant features, which provide the highest accuracy of 82.25% with 2.85% increase.
2021
167128-167139
journalArticle
19
IEEE Geoscience and Remote Sensing Letters
DOI 10.1109/LGRS.2021.3086117
IEEE Geoscience and Remote Sensing Letters
ISSN 1558-0571
R. Zhang
J. Chen
L. Feng
S. Li
W. Yang
D. Guo
Feature extraction
Agriculture
Image segmentation
Image edge detection
Semantics
Decoding
convolutional neural network (CNN)
semantic segmentation
Agricultural areas
polarimetric synthetic aperture radar (PolSAR)
Radar polarimetry
A Refined Pyramid Scene Parsing Network for Polarimetric SAR Image Semantic Segmentation in Agricultural Areas
Polarimetric synthetic aperture radar (PolSAR) image semantic segmentation is currently of great importance for synthetic aperture radar (SAR) image interpretation, especially in agricultural applications. Several convolutional neural networks (CNNs) have been implemented for SAR image semantic segmentation in urban or land cover applications. However, existing CNNs often break one semantic area into several pieces or confuse the adjacent semantic area in a PolSAR image. To address these issues uniformly, a refined pyramid scene parsing network (PSPNet) is proposed for PolSAR image semantic segmentation in an agricultural areas. Compared to conventional PSPNet architecture, the refined PSPNet adopts a multilevel feature fusion design in its decoder to effectively exploit the features learned from its different encoder branches. Besides, a polarimetric channel attention module is incorporated into the network to capture rich polarimetric features in a PolSAR image. Furthermore, an edge-aware loss function is devised to guide the network to refine pixel-level edge information directly from semantic segmentation prediction, separating easily confused agriculture area with sharp contours. Experimental results on one airborne millimeter-wave PolSAR dataset verify that the proposed network achieves promising semantic segmentation accuracy and preferable spatial consistency.
2022
1-5
journalArticle
15
IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
DOI 10.1109/JSTARS.2022.3194537
IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
ISSN 2151-1535
Z. Hong
Z. Li
X. Tong
H. Pan
R. Zhou
Y. Zhang
Y. Han
J. Wang
S. Yang
Z. Ma
Feature extraction
deep learning
Object detection
Training
Remote sensing
Task analysis
Image edge detection
Interference
Center positioning
circular mark
high-speed videogrammetry
saliency detection
A High-Precision Recognition Method of Circular Marks Based on CMNet Within Complex Scenes
Accurate recognition of circular marks is crucial for calibration, object tracking, and three-dimensional reconstruction in videogrammetry. However, most existing studies were designed under single or relatively simple scenes. When the existing algorithms are applied to more complex scenarios, it will result in higher false detection and miss-detection rate. In this article, we present a high-precision recognition method based on a novel deep learning model, circular-MarkNet (CMNet) to solve this problem. The proposed network consists of three main steps: first, circular marks are detected using the improved YOLOv4 model to narrow the search region of the circular contour; the contour of the circular marks is then extracted based on the saliency object detection model BASNet; and finally, least square fitting is used to calculate the central pixel coordinate of the identified contour on the saliency map. The proposed method was tested under three complex scenarios with different characteristics and disturbances. The experimental results demonstrated that: the proposed CMNet can effectively recognize of circular marks within complex scenes, which reveals the superiority and generalization ability of the proposed method; the improved YOLOv4 can significantly enhance the detection accuracy of circular marks, which is crucial to the subsequent saliency courter detection and circle center identification; and CMNet achieved the best performance, with an RMSE of 0.0713 pixel, compared to the state-of-the-art methods.
2022
7431-7443
journalArticle
H. Cheng
X. Liu
H. Wang
Y. Fang
M. Wang
X. Zhao
Training
Cloud computing
Anomaly detection
Protocols
Servers
CNN
Additives
Cryptography
Privacy-preserving
secret sharing
anomaly detection
Bloom filter
SecureAD: A Secure Video Anomaly Detection Framework on Convolutional Neural Network in Edge Computing Environment
Anomaly detection offers a powerful approach to identifying unusual activities and uncommon behaviors in real-world video scenes. At present, convolutional neural networks (CNN) have been widely used to tackle anomalous events detection, which mainly rely on its stronger ability of feature representation than traditional hand-crafted features. However, massive video data and high cost of CNN model training are a challenge to achieve satisfactory detection results for resource-limited users. In this article, we propose a secure video anomaly detection framework (SecureAD) based on CNN. Specifically, we introduce additive secret sharing to design several calculation protocols for achieving safe CNN training and video anomaly detection. Besides, we propose a Bloom filter based fine-grained access control policy to authenticate legitimate users, without leaking the privacy of raw personal attributes. In addition, edge computing instead of cloud computing is integrated into the architecture to reduce response time between servers and users in an outsourced environment. Finally, we prove that the proposed SecureAD achieves secure video anomaly detection without compromising the privacy of the related data. Also, the simulation results demonstrate the effectiveness and security of our SecureAD.
1 April-June 2022
1413-1427
10
IEEE Transactions on Cloud Computing
DOI 10.1109/TCC.2020.2990946
2
IEEE Transactions on Cloud Computing
ISSN 2168-7161
journalArticle
M. Xiao
Q. Huang
Y. Miao
S. Li
W. Susilo
Cloud computing
Encryption
Blockchain
blockchain
Companies
Access control
Cryptography
access control
Authorization
fine-grained
KP-ABE
revocation
Blockchain Based Multi-Authority Fine-Grained Access Control System With Flexible Revocation
Traditional data sharing systems are facing new challenges when implementing access control with more and more complex data sharing requirements. Flexibility of user revocation in completely decentralized environments needs to be taken into account. In this article, we propose a Key-Policy Attribute-Based Encryption scheme with Multiple and Flexible Revocation (MAFR-KP-ABE) to achieve the features of decentralized authorization and flexible revocation. We prove the security of our MAFR-KP-ABE scheme in the standard model and provide the comparison with relevant schemes to demonstrate its efficiency. Then we propose a fine-grained access control system based on MAFR-KP-ABE scheme and blockchain that matches the need of paid data sharing services with several security properties enhanced. Security analysis and system implementation are given subsequently to demonstrate our system efficient and secure.
1 Nov.-Dec. 2022
3143-3155
15
IEEE Transactions on Services Computing
DOI 10.1109/TSC.2021.3086023
6
IEEE Transactions on Services Computing
ISSN 1939-1374
journalArticle
Y. Tao
F. Chang
Y. Huang
L. Ma
L. Xie
H. Su
Convolutional neural networks
computer vision
Computer vision
deep learning
Diseases
Transformers
Cotton
Residual neural networks
convolution neural network
smart agriculture
Smart agriculture
Cotton disease detection
Quadrupedal robots
Radiofrequency identification
Cotton Disease Detection Based on ConvNeXt and Attention Mechanisms
Cotton diseases cause low cotton production and fiber quality. Disease detection methods based on deep learning can integrate feature extraction and improve identification accuracy. We present an automatic cotton disease detection method to improve the identification accuracy of cotton disease. Cotton images are collected using a quadruped robot. ConvNeXt integrates the convolution neural network architecture with intrinsic superiority of transformer. The multiscale spatial pyramid attention (MSPA) module can help ConvNeXt concentrate on important regions of feature maps. ConvNeXt with the MSPA module shows the best recognition results of 97.2%, 99.7% and 100.0% on one competition dataset and two cotton datasets, respectively, with little increase in inference time. It indicates that the proposed model performs well in recognition accuracy with fast detection speed.
2022
805-809
6
IEEE Journal of Radio Frequency Identification
DOI 10.1109/JRFID.2022.3206841
IEEE Journal of Radio Frequency Identification
ISSN 2469-7281
journalArticle
22
IEEE Sensors Journal
DOI 10.1109/JSEN.2021.3129173
1
IEEE Sensors Journal
ISSN 1558-1748
N. Rangappa
Y. R. V. Prasad
S. R. Dubey
Crops
deep learning
Deep learning
Agriculture
Wireless sensor networks
image processing
Sensors
CNN
Precision agriculture
Image sensors
LED bit sequence
LED communication
Light emitting diodes
sensors
UAV
WSN
LEDNet: Deep Learning-Based Ground Sensor Data Monitoring System
Wireless Sensor Networks (WSN) are generally used for precision agriculture. However, reliability and cost are the key limitations of such approaches. In recent times, the application of Unmanned Aerial Vehicles (UAVs) in the agricultural field has become popular due to scalability, cost efficient and user friendly adaptations with the help of improved navigation algorithms. A Novel and cost effective Light Emitting Diode (LED) based wireless communication of field sensor data to server has been recently explored. This paper proposes a LEDNet framework that utilizes the LED pattern based sensor data encoding in an image with computer vision and deep learning based data extraction/communication of data. The LED pattern image can be captured using any decent resolution cameras that can be mounted on UAVs. The proposed framework generates LED sequences with the help of embedded boards and utilizes image processing and deep learning for the decoding of the sensor data from the LED pattern image. The experiments are carried out with the images taken under various lighting conditions from different heights in the field. Promising performance in terms of accuracy and power consumption is observed for the collection of sensor data using the proposed LEDNet framework for the LED bit sequence extraction from the dataset of images collected under various environmental conditions.
1 Jan.1, 2022
842-850
journalArticle
18
IEEE Transactions on Information Forensics and Security
DOI 10.1109/TIFS.2022.3231121
IEEE Transactions on Information Forensics and Security
ISSN 1556-6021
A. Vangala
A. K. Das
A. Mitra
S. K. Das
Y. Park
Security
security
Blockchains
Internet of Things (IoT)
Costs
blockchain
Smart agriculture
Authentication
authentication and key agreement
Farming
Intelligent precision agriculture
mobile vehicles
Remote monitoring
simulation
Blockchain-Enabled Authenticated Key Agreement Scheme for Mobile Vehicles-Assisted Precision Agricultural IoT Networks
Precision farming has a positive potential in the agricultural industry regarding water conservation, increased productivity, better development of rural areas, and increased income. Blockchain technology is a better alternative for storing and sharing farm data as it is reliable, transparent, immutable, and decentralized. Remote monitoring of an agricultural field requires security systems to ensure that any sensitive information is exchanged only among authenticated entities in the network. To this end, we design an efficient blockchain-enabled authenticated key agreement scheme for mobile vehicles-assisted precision agricultural Internet of Things (IoT) networks called $AgroMobiBlock$ . The limited existing work on authentication in agricultural networks shows passive usage of blockchains with very high costs. $AgroMobiBlock$ proposes a novel idea using the elliptic curve operations on an active hybrid blockchain over mobile farming vehicles with low computation and communication costs. Formal and informal security analysis along with the formal security verification using the Automated Validation of Internet Security Protocols and Applications (AVISPA) software tool have shown the robustness of $AgroMobiBlock$ against man-in-the-middle, impersonation, replay, physical capture, and ephemeral secret leakage attacks among other potential attacks. The blockchain-based simulation on large-scale nodes shows the computational time for an increase in the network and block sizes. Moreover, the real-time testbed experiments have been performed to show the practical usefulness of the proposed scheme.
2023
904-919
journalArticle
31
IEEE Transactions on Image Processing
DOI 10.1109/TIP.2021.3125266
IEEE Transactions on Image Processing
ISSN 1941-0042
W. Xu
G. Wang
Generative adversarial networks
Training
Shape
Task analysis
Generators
Faces
Strain
Generative adversarial network
image-to-image translation
multiple domains
self-regularization
A Domain Gap Aware Generative Adversarial Network for Multi-Domain Image Translation
Recent image-to-image translation models have shown great success in mapping local textures between two domains. Existing approaches rely on a cycle-consistency constraint that supervises the generators to learn an inverse mapping. However, learning the inverse mapping introduces extra trainable parameters and it is unable to learn the inverse mapping for some domains. As a result, they are ineffective in the scenarios where (i) multiple visual image domains are involved; (ii) both structure and texture transformations are required; and (iii) semantic consistency is preserved. To solve these challenges, the paper proposes a unified model to translate images across multiple domains with significant domain gaps. Unlike previous models that constrain the generators with the ubiquitous cycle-consistency constraint to achieve the content similarity, the proposed model employs a perceptual self-regularization constraint. With a single unified generator, the model can maintain consistency over the global shapes as well as the local texture information across multiple domains. Extensive qualitative and quantitative evaluations demonstrate the effectiveness and superior performance over state-of-the-art models. It is more effective in representing shape deformation in challenging mappings with significant dataset variation across multiple domains.
2022
72-84
journalArticle
21
IEEE Sensors Journal
DOI 10.1109/JSEN.2020.3022783
10
IEEE Sensors Journal
ISSN 1558-1748
T. Sun
Y. Liu
Y. Wang
Z. Xiao
Estimation
Cameras
Optimization
Visualization
Simultaneous localization and mapping
Gyroscopes
sensor fusion
simultaneous localization and mapping
Visual-inertial odometry (VIO)
An Improved Monocular Visual-Inertial Navigation System
Simultaneous Localization and Mapping (SLAM) combined with visual and inertial measurements has attained considerable consideration in the Robotics and Computer Vision society. Nevertheless, balancing between real-time needs and precision could be a difficult challenge. Thus, a new tightly-coupled visual-inertial concurrent localization and mapping approach is proposed with precise and real-time motion estimating and map reconstruction capabilities. The nonlinear optimization is based on the concept that the frontend and backend in the visual-inertial SLAM (VISLAM) system can enhance one another. Moreover, a new inertial measurement unit (IMU) initialization approach is employed for rapid calculation of the scale, the gravity orientation, velocity, and gyroscope and accelerometer biases with high precision. Besides, precise motion estimation of the frontend could be provided, which improves the backend optimization due to achieving a more precise initial state for the backend. Also, feedback-based relocalization and continued SLAM frameworks are designed for autonomous robot navigation or SLAM. The accuracy of the presented VISLAM system is investigated via experiments performed on the public EuRoC dataset and actual environments. According to the experiments, the presented VISLAM system is more accurate with lower computational cost compared with existing VISLAM systems.
15 May15, 2021
11728-11739
journalArticle
23
IEEE Transactions on Multimedia
DOI 10.1109/TMM.2020.3001506
IEEE Transactions on Multimedia
ISSN 1941-0077
X. Zuo
S. Wang
J. Zheng
W. Yu
M. Gong
R. Yang
L. Cheng
Biological system modeling
Shape
Three-dimensional displays
Image reconstruction
Solid modeling
human body
non-rigid fusion
RGBD
Surface reconstruction
Tracking
SparseFusion: Dynamic Human Avatar Modeling From Sparse RGBD Images
In this paper, we propose a novel approach to reconstruct 3D human body shapes based on a sparse set of RGBD frames using a single RGBD camera. We specifically focus on the realistic settings where human subjects move freely during the capture. The main challenge is how to robustly fuse these sparse frames into a canonical 3D model, under pose changes and surface occlusions. This is addressed by our new framework consisting of the following steps. First, based on a generative human template, for every two frames having sufficient overlap, an initial pairwise alignment is performed; It is followed by a global non-rigid registration procedure, in which partial results from RGBD frames are collected into a unified 3D shape, under the guidance of correspondences from the pairwise alignment; Finally, the texture map of the reconstructed human model is optimized to deliver a clear and spatially consistent texture. Empirical evaluations on synthetic and real datasets demonstrate both quantitatively and qualitatively the superior performance of our framework in reconstructing complete 3D human models with high fidelity. It is worth noting that our framework is flexible, with potential applications going beyond shape reconstruction. As an example, we showcase its use in reshaping and reposing to a new avatar.
2021
1617-1629
journalArticle
A. Timilsina
A. R. Khamesi
V. Agate
S. Silvestri
Renewable energy sources
Production
reinforcement learning
Green products
Coal
Energy exchange
Energy sharing systems
Power generation
Reinforcement learning
user preference
virtual power plants
A Reinforcement Learning Approach for User Preference-Aware Energy Sharing Systems
Energy Sharing Systems (ESS) are envisioned to be the future of power systems. In these systems, consumers equipped with renewable energy generation capabilities are able to participate in an energy market to sell their energy. This paper proposes an ESS that, differently from previous works, takes into account the consumers' preference, engagement, and bounded rationality. The problem of maximizing the energy exchange while considering such user modeling is formulated and shown to be NP-Hard. To learn the user behavior, two heuristics are proposed: 1) a Reinforcement Learning-based algorithm, which provides a bounded regret and 2) a more computationally efficient heuristic, named BPT- K, with guaranteed termination and correctness. A comprehensive experimental analysis is conducted against state-of-the-art solutions using realistic datasets. Results show that including user modeling and learning provides significant performance improvements compared to state-of-the-art approaches. Specifically, the proposed algorithms result in 25% higher efficiency and 27% more transferred energy. Furthermore, the learning algorithms converge to a value less than 5% of the optimal solution in less than 3 months of learning.
Sept. 2021
1138-1153
5
IEEE Transactions on Green Communications and Networking
DOI 10.1109/TGCN.2021.3077854
3
IEEE Transactions on Green Communications and Networking
ISSN 2473-2400
journalArticle
13
IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
DOI 10.1109/JSTARS.2020.3001980
IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
ISSN 2151-1535
U. Nazir
U. K. Mian
M. U. Sohail
M. Taj
M. Uppal
Computer architecture
Sensors
Satellites
Logic gates
Image sensors
Asia
Brick Kiln
Kilns
ResNet-152
sustainable development goals
you only look once (YOLO)
Kiln-Net: A Gated Neural Network for Detection of Brick Kilns in South Asia
The availability of high-resolution satellite imagery has enabled several new applications such as identification of brick kilns for the elimination of modern-day slavery. This requires automated analysis of approximately 1551997 km2 area within the “Brick-Kiln-Belt” of South Asia. Although modern machine learning techniques have achieved high accuracy for a wide variety of applications, problems involving large-scale analysis using high-resolution satellite imagery requires both accuracy as well as computational efficiency. We propose a coarse-to-fine strategy consisting of an inexpensive classifier and a detector, which work in tandem to achieve high accuracy at low computational cost. More specifically, we propose a two-stage gated neural network architecture called Kiln-Net. At the first stage, imagery is classified using the ResNet-152 model which filters out over 99% of irrelevant data. At the second stage, a YOLOv3-based object detector is applied to find the precise location of each brick kiln in the candidate regions. The dataset, named Asia14, consisting of 14 000 Digital Globe RGB images and 14 categories is also developed to train the proposed kiln-net architecture. Our proposed network architecture is evaluated on approximately 3,300 km2 region (337 723 image patches) from 14 different cities in five different countries of South Asia. It outperforms state-of-the-art methods employed for the recognition of brick kilns and achieved an accuracy of 99.96% and average F1 score of 0.91. To the best of our knowledge, it is also 20 x faster than existing methods.
2020
3251-3262
journalArticle
V. Suryan
P. Tokekar
Prediction algorithms
Robot sensing systems
Sensor phenomena and characterization
Approximation algorithms
Gaussian Process (GP) regression
informative path planning (IPP)
Time measurement
Learning a Spatial Field in Minimum Time With a Team of Robots
In this article, we study an informative path-planning problem where the goal is to minimize the time required to learn a spatially varying entity. We use Gaussian process (GP) regression for learning the underlying field. Our goal is to ensure that the GP posterior variance, which is also the mean square error between the learned and actual fields, is below a predefined value. We study three versions of the problem. In the placement version, the objective is to minimize the number of measurement locations while ensuring that the posterior variance is below a predefined threshold. In the mobile robot version, we seek to minimize the total time required to visit and collect measurements from the measurement locations using a single robot. We also study a multirobot version where the objective is to minimize the time required by the last robot to return to a common starting location called depot. By exploiting the properties of GP regression, we present constant-factor approximation algorithms. In addition to the theoretical results, we also compare the empirical performance using a real-world dataset, with other baseline strategies.
Oct. 2020
1562-1576
36
IEEE Transactions on Robotics
DOI 10.1109/TRO.2020.2994003
5
IEEE Transactions on Robotics
ISSN 1941-0468
journalArticle
71
IEEE Transactions on Instrumentation and Measurement
DOI 10.1109/TIM.2022.3141163
IEEE Transactions on Instrumentation and Measurement
ISSN 1557-9662
C. Shen
Z. Pei
W. Chen
J. Wang
J. Zhang
Z. Chen
Feature extraction
Pattern recognition
Electromyography
Generalizability
gesture recognition
Muscles
pattern recognition (PR)
signal processing
Signal processing algorithms
Speech recognition
surface electromyography (sEMG)
Time-domain analysis
Toward Generalization of sEMG-Based Pattern Recognition: A Novel Feature Extraction for Gesture Recognition
Gesture recognition via surface electromyography (sEMG) has drawn significant attention in the field of human–computer interaction. An important factor limiting the performance of sEMG-based pattern recognition (PR) is the generalization ability which sEMG changes for the identical movements when conducted at various positions or by different persons. Thus, this study aims to explore the generalization of classifier to develop a stable classification model that does not require relearning, even if it is used by other people. We propose a new feature extraction method to diminish the influence of limb position on sEMG-based PR. Specifically, the sEMG features are extracted directly from time domain. This condition is accomplished by using Fourier transform properties, difference, and the sum of squares differences. The best offline cross-validation accuracy (CVA) results are 88.775% training data from the tenth subject and testing data from the fifth subject in the NinaPro dataset. The best online CVA is 99%, and the movement selection time is 47.036 ± 1.028 ms. In comparison with the well-known sEMG feature, the CVA and the generalization of the proposed features improved substantially. These improvements aim to facilitate the practical implementation of myoelectric interfaces.
2022
1-12
journalArticle
M. Gao
X. He
L. Chen
T. Liu
J. Zhang
A. Zhou
Data models
Task analysis
Optimization
Recommender systems
Linear programming
Bipartite networks
Knowledge engineering
link prediction
matrix factorization
network representation learning
recommendation
Social networking (online)
Learning Vertex Representations for Bipartite Networks
Recent years have witnessed a widespread increase of interest in network representation learning (NRL). By far most research efforts have focused on NRL for homogeneous networks like social networks where vertices are of the same type, or heterogeneous networks like knowledge graphs where vertices (and/or edges) are of different types. There has been relatively little research dedicated to NRL for bipartite networks. Arguably, generic network embedding methods like node2vec and LINE can also be applied to learn vertex embeddings for bipartite networks by ignoring the vertex type information. However, these methods are suboptimal in doing so, since real-world bipartite networks concern the relationship between two types of entities, which usually exhibit different properties and patterns from other types of network data. For example, E-Commerce recommender systems need to capture the collaborative filtering patterns between customers and products, and search engines need to consider the matching signals between queries and webpages. This work addresses the research gap of learning vertex representations for bipartite networks. We present a new solution BiNE, short for Bipartite Network Embedding, which accounts for two special properties of bipartite networks: long-tail distribution of vertex degrees and implicit connectivity relations between vertices of the same type. Technically speaking, we make three contributions: (1) We design a biased random walk generator to generate vertex sequences that preserve the long-tail distribution of vertices; (2) We propose a new optimization framework by simultaneously modeling the explicit relations (i.e., observed links) and implicit relations (i.e., unobserved but transitive links); (3) We explore the theoretical foundations of BiNE to shed light on how it works, proving that BiNE can be interpreted as factorizing multiple matrices. We perform extensive experiments on five real datasets covering the tasks of link prediction (classification) and recommendation (ranking), empirically verifying the effectiveness and rationality of BiNE. Our experiment codes are available at: https://github.com/clhchtcjj/BiNE.
1 Jan. 2022
379-393
34
IEEE Transactions on Knowledge and Data Engineering
DOI 10.1109/TKDE.2020.2979980
1
IEEE Transactions on Knowledge and Data Engineering
ISSN 1558-2191
journalArticle
7
IEEE Access
DOI 10.1109/ACCESS.2019.2903422
IEEE Access
ISSN 2169-3536
H. Long
Y. Chung
Z. Liu
S. Bu
Feature extraction
Object detection
Task analysis
Neural networks
object detection
Graphical models
Fuses
aerial images
Automobiles
Convolutional neural networks (CNNs)
feature fusion deep networks (FFDN)
Object Detection in Aerial Images Using Feature Fusion Deep Networks
Object detection acts as an essential part in a wide range of measurement systems in traffic management, urban planning, defense, agriculture, and so on. Convolutional Neural Networks-based researches reach a great improvement on detection tasks in natural scene images enjoying from the strong ability of feature representations. However, because of the high density, the small size of objects, and the intricate background, the current methods achieve relatively low precision in aerial images. The intention of this work is to obtain better detection performance in aerial images by designing a novel deep neural network framework called Feature Fusion Deep Networks (FFDN). The novel architecture combines a designed structural learning layer based on a graphical model. As a result, the network not only provides powerful hierarchical representation but also strengthens the spatial relationship between the high-density objects. We demonstrate the great improvement of the proposed FFDN on the UAV123 data set and another novel challenging data set called UAVDT benchmark. The objects which appear with small size, partial occlusion and out of view, as well as in the dark background can be detected accurately.
2019
30980-30990
journalArticle
13
IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
DOI 10.1109/JSTARS.2020.2972574
IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
ISSN 2151-1535
Z. Xu
L. Cao
S. Zhong
G. Liu
Y. Yang
S. Zhu
X. Luo
L. Di
Remote sensing
Time series analysis
Indexes
Meteorology
Vegetation mapping
MODIS
Market research
AVHRR
trend analysis
vegetation condition index (VCI)
vegetative drought
Trends in Global Vegetative Drought From Long-Term Satellite Remote Sensing Data
In this article, the trends in global vegetative drought were investigated using MODIS- and AVHRR-based NDVI products. A set of selected methods were employed to perform trend analysis including trend test, trend location detection, and trend estimates. Accounting for the effect of the global geographical heterogeneity on trend analysis, the NDVI dataset was aggregated on designated divisions in view of latitude ranges and climate zones. From the results, it was concluded that: AVHRR has longer-term records that provide a critical historical perspective on vegetation activities necessary for global change research, and continuity and correctness is achievable from AVHRR VCI given the systematic offset between the NDVI values derived from the two sensors and the characteristics of the VCI algorithm. From a pixel level global trend analysis map, the proportion of pixels with rising trends is 54.7% in the world, 67.6% and 47.5% in the northern hemisphere and the southern hemisphere, respectively, which means there is an overall rising trends in the global VCI values, especially in the northern hemisphere. The North Temperate and the South Tropical have overall increases in the VCI values while all climate zones have overall increases in the VCI values. The piecewise trends basically adhere to the results of overall trend identification although there are some local variations. There are obvious rising trends during the latest years for all the climate zones. Dominant down trends were identified in A, B, Cw, Ds, and E while the piecewise trends for both Cs and Df are dominantly rising before 2000. An average of about four breakpoints were detected from both the climate zone- and latitude range-aggregated divisions Thus, the mean duration for a piecewise trend is 7-9 years.
2020
815-826
journalArticle
8
IEEE Access
DOI 10.1109/ACCESS.2020.2994079
IEEE Access
ISSN 2169-3536
S. Latif
Z. Zou
Z. Idrees
J. Ahmad
Support vector machines
Machine learning
Neural networks
Internet of Things
support vector machine
Artificial neural network
Computer security
cybersecurity
industrial Internet of Things
Industries
random neural network
A Novel Attack Detection Scheme for the Industrial Internet of Things Using a Lightweight Random Neural Network
The Industrial Internet of Things (IIoT) brings together many sensors, machines, industrial applications, databases, services, and people at work. The IIoT is improving our lives in several ways including smarter cities, agriculture, and e-healthcare, etc. Although the IIoT shares several characteristics with the consumer IoT, different cybersecurity mechanisms are adopted for both networks. Unlike consumer IoT solutions that are used by an individual user for a single purpose, IIoT solutions tend to be integrated into larger operational systems. As a result, IIoT security solutions require additional planning and awareness to ensure the security and privacy of the system. In this paper, different cybersecurity attacks such as denial of service (DoS), malicious operation, malicious control, data type probing, spying, scan, and wrong setup are predicted by applying machine learning techniques. To predict the aforementioned attacks, a novel lightweight random neural network (RaNN)-based prediction model has been proposed in this article. To investigate the performance of the RaNN-based prediction model, several evaluation parameters such as accuracy, precision, recall, and F1 score were calculated and compared with the traditional artificial neural network (ANN), support vector machine (SVM) and decision tree (DT). The evaluation results show that the proposed RaNN model achieves an accuracy of 99.20% for a learning rate of 0.01, with a prediction time of 34.51 milliseconds. Other performance parameters such as the precision, recall, and F1 score were 99.11%, 99.13%, and 99.20%, respectively. The proposed scheme improves the attack detection accuracy by an average of 5.65% compared to that of state-of-the-art machine learning schemes for IoT security.
2020
89337-89350
journalArticle
71
IEEE Transactions on Instrumentation and Measurement
DOI 10.1109/TIM.2022.3204314
IEEE Transactions on Instrumentation and Measurement
ISSN 1557-9662
G. Du
J. Su
L. Zhang
K. Su
X. Wang
S. Teng
P. X. Liu
Convolutional neural networks
Feature extraction
Electroencephalography
electroencephalography (EEG)
Convolution
Entropy
Brain modeling
Deep neural network
emotion recognition
Emotion recognition
graph convolution network (GCN)
SEED
A Multi-Dimensional Graph Convolution Network for EEG Emotion Recognition
Due to the changeable, high-dimensional, nonstationary, and other characteristics of electroencephalography (EEG) signals, the recognition of EEG signals is mostly limited to independent individuals. To deal with these issues, we propose a multidimensional graph convolution network (MD-GCN), which integrates EEG signals’ temporal and spatial characteristics and can classify emotions more accurately. First, we use that the asymmetry of neuron activity in the left and right hemispheres is very important for emotion prediction to initialize the adjacency matrix and perform preliminary edge prediction without considering node features. Then, we perform the feature fusion on the inception network and then input it into the GCN to learn the interrelationship between channels. Finally, we visually analyze the adjacency matrix. To evaluate the performance of the model, we conduct experiments on the SEED dataset and the SEED-IV dataset. The results show that the predefined adjacency matrix method can improve the accuracy of emotion recognition, and the graph convolution has a better performance than the same type of convolution. It also theoretically shows that the emotional state is mainly by the interaction of important brain regions.
2022
1-11
journalArticle
F. A. Dharejo
M. Zawish
Y. Zhou
S. Davy
K. Dev
S. A. Khowaja
Y. Fu
N. M. F. Qureshi
Feature extraction
Deep learning
Task analysis
Discrete wavelet transforms
Internet of Things
Three-dimensional displays
edge computing
Action recognition
Activity recognition
Internet of things (IoT)
recurrent neural network (RNN)
three-dimensional discrete wavelet transform (3D-DWT)
FuzzyAct: A Fuzzy-Based Framework for Temporal Activity Recognition in IoT Applications Using RNN and 3D-DWT
Despite massive research in deep learning, the human activity recognition (HAR) domain still suffers from key challenges in terms of accurate classification and detection. The core idea behind recognizing activities accurately is to assist Internet-of-things (IoT) enabled smart surveillance systems. Thereby, this work is based on the joint use of discrete wavelet transform (DWT) and recurrent neural network (RNN) to classify and detect human activities accurately. Recent approaches on HAR exploit the three-dimensional (3-D) convolutional neural networks (CNNs) to extract spatial information, which adds a computational burden. In our case, features are extracted using 3D-DWT instead of 3-D CNNs, performed in three steps of 1D-DWT to reflect the spatio-temporal features of human action. Given the features, the RNN produces an output label for each video clip taking care of the long-term temporal consistency among close predictions in the output sequence. It is noticed that feature extraction through 3D-DWT essentially recovers the multiple angles of an activity. Many HAR techniques distinguish an activity based on the posture of an image frame rather than learning the transitional relationship between postures in the temporal sequence, resulting in degraded accuracy. To address this problem, in this article, we designed a novel rank-based fuzzy approach that segregates activities precisely by ranking the probabilities of activities based on confidence scores. FuzzyAct achieved an average mean average precision (mAP) of 0.8012 mAP on the ActivityNet dataset, and outperformed the baseline counterparts and other state-of-the-art approaches on benchmark datasets. Finally, we present a mechanism to compress the proposed RNN for edge-enabled IoT applications.
Nov. 2022
4578-4592
30
IEEE Transactions on Fuzzy Systems
DOI 10.1109/TFUZZ.2022.3152106
11
IEEE Transactions on Fuzzy Systems
ISSN 1941-0034
journalArticle
5
IEEE Robotics and Automation Letters
DOI 10.1109/LRA.2020.2969175
2
IEEE Robotics and Automation Letters
ISSN 2377-3766
L. Wu
R. Falque
V. Perez-Puchalt
L. Liu
N. Pietroni
T. Vidal-Calleja
Surface treatment
Probabilistic logic
Kernel
Three-dimensional displays
Image reconstruction
Surface reconstruction
Bayesian fusion
conditionally independent maps
Gaussian process implicit surfaces
Gaussian processes
skeleton extraction
Skeleton-Based Conditionally Independent Gaussian Process Implicit Surfaces for Fusion in Sparse to Dense 3D Reconstruction
3D object reconstructions obtained from 2D or 3D cameras are typically noisy. Probabilistic algorithms are suitable for information fusion and can deal with noise robustly. Consequently, these algorithms can be useful for accurate surface reconstruction. This paper presents an approach to estimate a probabilistic representation of the implicit surface of 3D objects. One of the contributions of the paper is the pipeline for generating an accurate reconstruction, given a set of sparse points that are close to the surface and a dense noisy point cloud. A novel submapping method following the topology of the object is proposed to generate conditional independent Gaussian Process Implicit Surfaces. This allows inference and fusion mechanisms to be performed in parallel followed by information propagation through the submaps. Large datasets can efficiently be processed by the proposed pipeline producing not only a surface but also the uncertainty information of the reconstruction. We evaluate the performance of our algorithm using simulated and real datasets.
April 2020
1532-1539
journalArticle
10
IEEE Access
DOI 10.1109/ACCESS.2022.3216285
IEEE Access
ISSN 2169-3536
Y. Liu
G. Gao
Z. Zhang
Convolutional neural networks
Crops
Feature extraction
Diseases
Neural networks
attention mechanism
Plants
Information filters
Image recognition
Crop disease recognition
light-weight CNN
SqueezeNext
Crop Disease Recognition Based on Modified Light-Weight CNN With Attention Mechanism
The agricultural production is greatly affected by various plant diseases. Classifying the severity of crop diseases is the requirement for formulating disease prevention and control strategies. However, the differences between different severity of the same crop disease are very tiny. It increases the difficulty of correct crop disease recognition. For example, at the early stage of the disease, the lesions on the leaves are not obvious. And it is very difficult to extract the features of the lesions. However, these very small color and texture differences of the lesions are the key patterns to distinguish different kinds of diseases of the same species. In order to achieve better performance in the fine-grained classification of the crop diseases, a modified light-weight convolution neural network was proposed. Multi-scale convolution kernel and coordinate attention mechanism are introduced in SqueezeNext to extract the features of the lesions accurately. The performance of the proposed model was evaluated using the AI challenger 2018 plant disease recognition dataset, and the recognition accuracy can reach 91.94%, which is 3.02% point higher than the original SqueezeNext model. In order to verify the effectiveness of the proposed model, comparative experiments were carried out using ReseNet50, Xception and mobilenetv2. The experimental results showed that the accuracy of the proposed method was slightly better than Xception, while the model size is only 2.83 MB, which is only 3.45% of Xception. The proposed method balances the performance and efficiency very well. Thus, it is suitable for deployment on mobile terminals and other embedded resource-constrained devices, which help to promote the popularization of smart agriculture application.
2022
112066-112075
journalArticle
70
IEEE Transactions on Instrumentation and Measurement
DOI 10.1109/TIM.2021.3089783
IEEE Transactions on Instrumentation and Measurement
ISSN 1557-9662
L. Chen
G. Li
G. Huang
P. Shi
Data models
Smoothing methods
Correlation
Internet of Things
Spatiotemporal phenomena
matrix factorization
Air quality
Data interpolation
Interpolation
missing type-aware method
multi-eXtreme Gradient Boosting (multi-XGBoost)
spatiotemporal correlation
A Missing Type-Aware Adaptive Interpolation Framework for Sensor Data
Data missing problems often occur on the Internet-of-Things domains. This article proposes a missing type-aware interpolation framework (IMA) for data loss problems in city-wide environmental monitoring systems that contain many scattered stations. To interpolate data as accurately as possible, IMA considers three aspects of information, i.e., spatiotemporal, all attributes of one measurement, and all values and accordingly develop three methods to estimate the missing data. First, we develop an improved multiviewer method, which uses the spatiotemporal correlation of data from neighbor stations to estimate random missing values. Second, we propose a new multi-eXtreme Gradient Boosting (multi-XGBoost) method that uses the values of the co-occurring and correlated correct attributes to predict the value of the missing attribute. Third, we take advantage of matrix factorization to estimate the missing parts if the data of the interpolation matrix are not all missing. To avoid the influence of uncorrelated data, IMA calculates Pearson's correlation coefficient between data of each station and uses those data from its top k highest correlation neighbors to form an interpolation matrix. Furthermore, due to the complexity of missing cases, IMA uses confidence levels in each of the three data prediction methods. For example, if the multiviewer method fails, IMA weights all valid results with confidence levels. We conduct our experiments on two real-world datasets from air quality monitoring stations in Beijing. Both datasets contain numerous missing measurements. Experimental results show that IMA outperforms other counterpart methods in interpolating the missing measurements, in terms of accuracy and effectiveness. Compared with the most related method, IMA improves the interpolation accuracy from 0.818 to 0.849 in a small dataset and from 0.214 to 0.759 in a large one.
2021
1-15
journalArticle
60
IEEE Transactions on Geoscience and Remote Sensing
DOI 10.1109/TGRS.2022.3227074
IEEE Transactions on Geoscience and Remote Sensing
ISSN 1558-0644
L. Ding
J. Zhou
Z. -L. Li
J. Ma
C. Shi
S. Sun
Z. Wang
Time series analysis
Climate change
Spatial resolution
Land surface temperature
Meteorology
Clouds
land surface temperature (LST)
Surface reconstruction
All-weather
geostationary satellite
Geostationary satellites
high-temporal resolution
Infrared detectors
thermal infrared (TIR)
Reconstruction of Hourly All-Weather Land Surface Temperature by Integrating Reanalysis Data and Thermal Infrared Data From Geostationary Satellites (RTG)
Thermal infrared (TIR) land surface temperature (LST) products derived from geostationary satellites have a high temporal resolution in a diurnal cycle, but they have many missing values under cloudy-sky conditions. Therefore, it is pressing to obtain all-weather LST (AW LST) with a high temporal resolution by filling the gap of TIR LST. In this study, a method integrating reanalysis data and TIR data from geostationary satellites (RTG) was proposed for reconstructing hourly AW LST. Then, taking the Tibetan Plateau (TP), which is a focus of climate change as a case, RTG was applied to the Chinese Fengyun-4A (FY-4A) TIR LST and China Land Surface Data Assimilation System (CLDAS) data. Validation based on the in-situ LST shows that the accuracy of the AW LST is better than the FY-4A LST and CLDAS LST under clear-sky, cloudy-sky, and all-weather conditions. The mean RMSEs are 3.02 K for clear-sky conditions, 3.94 K for cloudy-sky conditions, and 3.57 K for all-weather conditions. Uncertainty and coarse resolution of the original FY-4A and CLDAS data affect the accuracy of the obtained AW LST. The results of the LST time series comparison also show that the reconstructed AW LST is consistent with in-situ LST. The reconstructed AW LST also has the good image quality and provides reliable spatial patterns. RTG is practical in obtaining high temporal resolution AW LST from the Chinese FY-4A to satisfy related applications. It can also be extended to other geostationary satellites and reanalysis datasets.
2022
1-17
journalArticle
60
IEEE Transactions on Geoscience and Remote Sensing
DOI 10.1109/TGRS.2021.3123117
IEEE Transactions on Geoscience and Remote Sensing
ISSN 1558-0644
Z. Sun
Z. Bu
S. Lu
K. Omasa
Estimation
Wavelength measurement
Hyperspectral imaging
Reflectivity
Goniometers
Hair
Leaf chlorophyll content (LCC)
leaf optical properties
multiangular measurements
plant science
Reflection
spectral indices
A General Algorithm of Leaf Chlorophyll Content Estimation for a Wide Range of Plant Species
Plant leaf chlorophyll content (LCC) plays a key role in the assessment of plant stress and plant functioning. To date, accurate estimation of LCC over a wide range of plant species (trees, bushes, and lianas) under different measurement conditions is still challenging for nondestructive methods. Based on multiangular hyperspectral reflection of 706 leaves (ten plant species), several popular spectral indices were evaluated for a general estimation of LCC. The modified difference ratio index (MDRI) had the strongest linear relationship ( $R^{2}=0.92$ ) to LCC among all the tested spectral indices. The regression algorithm was then used to estimate LCC in other datasets from different regions across the globe. Comparing with the machine learning techniques and PROSPECT model, validation results from 2024 leaves (114 plant species) confirmed that the linear algorithm derived from the MDRI was the most effective for estimating LCC (root-mean-square error (RMSE) $=6.72\,\,\mu \text{g}$ /cm2) across a wide range of plant species under different measurement conditions. The MDRI does not require parameterization for each plant species and has the potential to estimate LCC from a simple handheld laboratory or field instrument at any arbitrary direction. The generality of the approach makes it convenient for botanical and ecological studies under different measurement conditions that need accurate LCC estimates.
2022
1-14
journalArticle
Q. Liu
L. Chen
Y. Yuan
H. Wu
Training
Predictive models
Decoding
Encoding
History
Abstractive summarization
bag-of-words
history reuse
long summaries
Recurrent neural networks
Vocabulary
word order deviation
History Reuse and Bag-of-Words Loss for Long Summary Generation
Recurrent Neural Network (RNN) based abstractive text summarization models have made great progress over the past few years, largely triggered by the encoder-decoder architecture. However, there has been little work improving the generation of relatively long summaries. In this paper, we concentrate on two prominent problems in long summary generation. First, although significant efforts have been made to assist the encoder in handling long sequences, the decoder struggles with long sequences owing to the limited storage capacity of RNN. We propose a simple and effective approach called history reuse, which first mines critical information from the history summary sequence and then transmits the information to the decoder. Second, since encoder-decoder models are typically trained to produce exactly the same summary as the target summary, certain word order deviations between the predicted summary and target summary are excessively punished. Accordingly, we introduce a fully differentiable loss called bag-of-words (BoW) loss, which takes advantage of the feature of BoW discarding word order information in texts, and computes the difference between the two summaries at the BoW space. Experiments on two benchmark datasets, CNN/Daily Mail and Pubmed, demonstrate that our methods significantly improve the baseline.
2021
2551-2560
29
IEEE/ACM Transactions on Audio, Speech, and Language Processing
DOI 10.1109/TASLP.2021.3100281
IEEE/ACM Transactions on Audio, Speech, and Language Processing
ISSN 2329-9304
journalArticle
60
IEEE Transactions on Geoscience and Remote Sensing
DOI 10.1109/TGRS.2022.3199261
IEEE Transactions on Geoscience and Remote Sensing
ISSN 1558-0644
X. Jiang
Y. Zhao
M. Gong
T. Zhan
M. Zhang
Estimation
Hyperspectral imaging
Libraries
Manifolds
Evolutionary computation
Linear mixture model
Mixture models
multiobjective endmember estimation (MoEE)
Pareto optimization
spatial–spectral information
topological structure
vertex-directed local search
A Vertex-Directed Evolutionary Algorithm for Multiobjective Endmember Estimation
Hyperspectral unmixing including endmember extraction and abundance estimation has been investigated successively in recent years due to increasingly hyperspectral processing requirements. As one type of decision after solution paradigm, the multiobjective endmember estimation (MoEE) method is able to obtain a set of Pareto optimal solutions, thus providing a wealth of information to determine the most representative endmembers. In addition, multiobjective optimization methods also have the characteristics of flexible modeling, excellent global convergence, commendable adaptability, and so on. However, the evolutionary algorithms designed for this kind of method generally use little spatial–spectral information of the hyperspectral image. In this article, we delve into the memetic strategy by exploiting the topological structure of hyperspectral data in the high-dimensional space to establish a vertex-directed MoEE method, termed VD-MoEE. According to the frequently used linear mixture model, endmembers of hyperspectral images are generally distributed at the vertices of the hyperspectral data manifold. Therefore, we design a vertex-directed local search operator to guide the search direction of the individuals in evolutionary algorithms. Experimental results on synthetic and real datasets demonstrated that the proposed VD-MOEE is able to achieve appealing performance in terms of solution selection and accuracy in comparison with several classic and state-of-the-art endmember estimation methods.
2022
1-13
journalArticle
10
IEEE Access
DOI 10.1109/ACCESS.2022.3171916
IEEE Access
ISSN 2169-3536
N. Akram
S. Adnan
M. Asif
S. M. A. Imran
M. N. Yasir
R. A. Naqvi
D. Hussain
Feature extraction
Deep learning
Computer architecture
Support vector machines
Image segmentation
Morphology
Computational efficiency
Blood
computer-assisted diagnosis
leukemia diagnosis
WBC count
WBC segmentation
Exploiting the Multiscale Information Fusion Capabilities for Aiding the Leukemia Diagnosis Through White Blood Cells Segmentation
Leukemia is one of the most terminal types of blood cancer, and many people suffer from it every year. White blood cells (WBCs) have a significant association with leukemia diagnosis. Research studies reported that leukemia brings changes in WBC count and morphology. WBC accurate segmentation enables to detect morphology and WBC count which consequently helps in the diagnosis and prognosis of leukemia. Manual WBC assessment methods are tedious, subjective, and less accurate. To overcome these problems, we propose a multi-scale information fusion network (MIF-Net) for WBC segmentation. MIF-Net is a shallow architecture with internal and external spatial information fusion mechanisms. In WBC images, the cytoplasm is with low contrast compared to the background, whereas nuclei shape can be complex with an indistinctive boundary for some cases, therefore accurate segmentation becomes challenging. Spatial features in the initial layers of the network include fine boundary information and MIF-Net splits and propagates this boundary information on multi-scale for external information fusion. Multi-scale information fusion in our network helps in preserving boundary information and contributes to segmentation performance improvement. MIF-Net also uses internal information fusion after intervals for feature empowerment in different stages of the network. We evaluated our network for four publicly available datasets and achieved state-of-the-art segmentation performance. In addition, the proposed architecture exhibits superior computational efficiency by using only 2.67 million trainable parameters.
2022
48747-48760
journalArticle
71
IEEE Transactions on Instrumentation and Measurement
DOI 10.1109/TIM.2022.3189637
IEEE Transactions on Instrumentation and Measurement
ISSN 1557-9662
S. Teng
J. Wu
Y. Chen
H. Fan
X. Cao
Z. Li
Feature extraction
Deep learning
image segmentation
Image segmentation
Generators
Decoding
Image reconstruction
semi-supervised learning
Blood
Generative adversarial network (GAN)
leukocyte
reconstruction enhancement
Semi-Supervised Leukocyte Segmentation Based on Adversarial Learning With Reconstruction Enhancement
The number, relative ratio, and appearance of peripheral blood leukocytes can assist doctors to diagnose diseases such as lymphoma and leukemia. Therefore, segmentation of peripheral blood leukocytes in blood smear images plays a crucial role in the diagnosis of certain diseases. We propose a semisupervised leukocyte segmentation method under the framework of adversarial learning, in which a discriminator is trained to differentiate the segmentation maps coming either from the ground truth or from the segmentation network. Specifically, we first construct a lightweight leukocyte segmentation network by modifying DeepLabV3+ with simplified MobileNetV2. In addition, a reconstruction decoder is developed as a constraint on feature extraction to recover the original leukocyte image from its segmentation result. Then, we design the discriminator in a fully convolutional manner, which as well enables semi-supervised learning by inferring reliable supervisory information for unlabeled images. Quantitative and qualitative experimental results on four image datasets demonstrate the superiority of the proposed method over several state-of-the-art methods, achieving the highest average $F1$ score of 0.9717 and mIoU of 0.9493 with only 20% labeled training samples.
2022
1-11
journalArticle
12
IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
DOI 10.1109/JSTARS.2018.2890387
2
IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
ISSN 2151-1535
B. Yang
Y. Zhao
H. Zhao
B. Li
Y. Huang
Microwave radiometry
Microwave imaging
Standards
Microwave theory and techniques
Satellite broadcasting
Assessment
China
global satellite mapping of precipitation (GSMaP)
precipitation
Rain
version 3
version 4
Assessment of the Two Successive GPM-Based V3 and V4 GSMaP Precipitation Products at Multiple Temporal and Spatial Scales Over China
Since the beginning of the global precipitation measurement (GPM) era, the global satellite mapping of precipitation (GSMaP) products underwent a major upgrade on January 2017, when the newest Version 4 (V4) GSMaP products were formally released. In this study, for the first time ever, the error characteristics of the successive Version 3 (V3) and V4 GSMaP products were evaluated at multiple temporal and spatial scales by comparing them to the China daily Precipitation Analysis Products from March 2014 to February 2017. The GSMaP products include the V3 and V4 standard products (MVK_V3 and MVK_V4), the gauge-adjusted standard products (GAU_V3 and GAU_V4), and the V3 near-real-time product (NRT_V3). Both versions of the gauge-adjusted datasets exhibit improvements over their corresponding unadjusted counterparts. With regard to the three-year daily mean precipitation, both gauge-adjusted products have similar spatial precipitation patterns, and the GAU_V4 provides higher precipitation estimates than the GAU_V3 over China. The MVK_V4 generally outperforms the MVK_V3 over the high-altitude Qinghai-Tibetan plateau, the deserts, and the moist southern regions. Elsewhere, the MVK_V4 has a lower performance than the MVK_V3. Based on the seasonal statistics, the V4 GSMaP products are superior to the V3 GSMaP products over China in the winter and the MVK_V4 provides higher precipitation estimates than the MVK_V3 in most areas of China (except for the Qinghai-Tibetan plateau and the deserts) in spring, summer, and autumn. The daily statistics show that the MVK_V4 significantly corrects for the precipitation bias of the MVK_V3 in the western, arid, and high-altitude regions.
Feb. 2019
577-588
journalArticle
9
IEEE Access
DOI 10.1109/ACCESS.2021.3131630
IEEE Access
ISSN 2169-3536
T. Liu
Y. Chen
H. Shen
R. Zhou
M. Zhang
T. Liu
J. Liu
Feature extraction
Deep learning
Shape
Lesions
Diabetes
Diabetic retinopathy
hard exudates
microaneurysms
Retina
Retinopathy
symmetric convolution neural network
A Novel Diabetic Retinopathy Detection Approach Based on Deep Symmetric Convolutional Neural Network
Diabetic Retinopathy (DR) may lead to blindness in diabetic patients, which is one of the most severe eye diseases. Therefore, using automatical technology to detect DR at the early phase has very vital clinical significance. In order to detect the microaneurysms (MAs) and hard exudates (HEs) of DR, a novel detection method based on deep symmetric convolutional neural network is proposed in this paper. The symmetric convolutional structure is used to improve the effectiveness of feature extraction. The proposed method also can overcome the imbalance of positive and negative samples to avoid overfitting by increasing the width and depth of the network. Furthermore, different network structures (convolution, pooling) are used to achieve different feature filtering in the stage of feature extractions. According to the experimental results, the proposed method is superior to the state-of-the-art approach on the public dataset DIARETDB1 (DB1). The detection accuracy of the objects is 92.0%, 93.2%, 93.6%, when using different filtering structures (convolution, max-pooling, ave-pooling) respectively. The detection of microaneurysms is much improved by using ave-pooling layer for feature filtering, and the max-pooling layer can improve the detection of hard exudates.
2021
160552-160558
journalArticle
22
IEEE Transactions on Intelligent Transportation Systems
DOI 10.1109/TITS.2020.3003902
6
IEEE Transactions on Intelligent Transportation Systems
ISSN 1558-0016
S. Li
B. Li
J. Yu
L. Zhang
A. Zhang
K. Cai
Data models
Computer science
Probabilistic logic
Roads
Internet
Data aggregation
Aggregates
Internet of Vehicles
k-ANN Query
road networks
uncertain Voronoi diagram
Probabilistic Threshold k-ANN Query Method Based on Uncertain Voronoi Diagram in Internet of Vehicles
Effective querying of data in the road networks is an important problem in the Internet of vehicles. Aggregate nearest neighbor queries can return the objects that minimizes an aggregate distance function on road networks considering a set of query points in the Internet of vehicles. And ${k}$ aggregate nearest neighbor query ( ${k}$ - ANN) is a complicate version for the basic one. The existing ${k}$ - ANN queries lack effective model to deal with the uncertain data and the existing query methods cannot be applied to solve the problem of ( ${k}$ - ANN) query on uncertain data directly. Therefore, in this paper, a probabilistic threshold ${k}$ - ANN query method based on uncertain Voronoi diagram is proposed. The method includes three phases: processing phase, pruning phase and refinement phase. The processing phase is to compute the minimum covered circle of the query dataset which is prepared for the pruning phase. In pruning phase, the different pruning algorithms are proposed for the corresponding three aggregate function of aggregate nearest neighbor query. The data points that cannot be the result are pruned and the candidate set is obtained. In refinement phase, the sets composed of ${k}$ data points in candidate set whose probabilities are not less than the user-specified threshold are stored into the result set and returned to the user. Experiments are performed to evaluate the effectiveness and superiority of these algorithms on probabilistic threshold k-ANN query.
June 2021
3592-3602
journalArticle
52
IEEE Transactions on Cybernetics
DOI 10.1109/TCYB.2021.3050487
8
IEEE Transactions on Cybernetics
ISSN 2168-2275
L. Bai
Y. -H. Shao
Z. Wang
W. -J. Chen
N. -Y. Deng
Support vector machines
Optimization
Indexes
Clustering methods
Periodic structures
Manifolds
Clustering
cross-manifold clustering
Elongation
flat-based clustering
manifold clustering
nonconvex programming
Multiple Flat Projections for Cross-Manifold Clustering
Cross-manifold clustering is an extreme challenge learning problem. Since the low-density hypothesis is not satisfied in cross-manifold problems, many traditional clustering methods failed to discover the cross-manifold structures. In this article, we propose multiple flat projections clustering (MFPC) for cross-manifold clustering. In our MFPC, the given samples are projected into multiple localized flats to discover the global structures of implicit manifolds. Thus, the intersected clusters are distinguished in various projection flats. In MFPC, a series of nonconvex matrix optimization problems is solved by a proposed recursive algorithm. Furthermore, a nonlinear version of MFPC is extended via kernel tricks to deal with a more complex cross-manifold learning situation. The synthetic tests show that our MFPC works on the cross-manifold structures well. Moreover, experimental results on the benchmark datasets and object tracking videos show excellent performance of our MFPC compared with some state-of-the-art manifold clustering methods.
Aug. 2022
7704-7718
journalArticle
10
IEEE Access
DOI 10.1109/ACCESS.2022.3168693
IEEE Access
ISSN 2169-3536
N. S. An
P. N. Lan
D. V. Hang
D. V. Long
T. Q. Trung
N. T. Thuy
D. V. Sang
deep learning
Deep learning
Computer architecture
Image segmentation
Task analysis
Neural networks
Biomedical imaging
colonoscopy
Neoplasms
polyp segmentation
Semantic segmentation
BlazeNeo: Blazing Fast Polyp Segmentation and Neoplasm Detection
In recent years, computer-aided automatic polyp segmentation and neoplasm detection have been an emerging topic in medical image analysis, providing valuable support to colonoscopy procedures. Attentions have been paid to improving the accuracy of polyp detection and segmentation. However, not much focus has been given to latency and throughput for performing these tasks on dedicated devices, which can be crucial for practical applications. This paper introduces a novel deep neural network architecture called BlazeNeo, for the task of polyp segmentation and neoplasm detection with an emphasis on compactness and speed while maintaining high accuracy. The model leverages the highly efficient HarDNet backbone alongside lightweight Receptive Field Blocks and a feature aggregation mechanism for computational efficiency. An auxiliary training strategy is proposed to take full advantage of the training data for the segmentation quality. Our experiments on a challenging dataset show that BlazeNeo achieves improvements in latency and model size while maintaining comparable accuracy against state-of-the-art methods. We obtain over 155 fps while outperforming all compared models in terms of accuracy in INT8 precision when deploying on a dedicated edge device with a conventional configuration.
2022
43669-43684
journalArticle
8
IEEE Access
DOI 10.1109/ACCESS.2020.2981496
IEEE Access
ISSN 2169-3536
H. Li
J. Tang
Generative adversarial networks
Training
Correlation
Convolution
Gallium nitride
Generative adversarial network
Coherence
deeping learning
image generation
Image synthesis
self-attention mechanism
Dairy Goat Image Generation Based on Improved-Self-Attention Generative Adversarial Networks
The lack of long-range dependence in convolutional neural networks causes weaker performance in generative adversarial networks(GANs) with regard to generating image details. The self-attention generative adversarial network(SAGAN) use the self-attention mechanism to calculate the correlation coefficient between feature vectors, which improves the global coherence of the network. In this paper, we put forward an improved-self-attention GANs(Improved-SAGAN) to improve the method for calculating correlation in the SAGAN. We can better measure the correlation between features by normalizing the feature vectors to eliminate as many errors caused by noise as possible. As the network learns the global information by calculating the correlation coefficient between all features, it can make up for the defects of local receptive field in the convolution network. We replace the conventional one-hot label with multi-label to obtain more supervised information for generative adversarial networks. We generate dairy goat images based on auxiliary condition generative adversarial network(ACGAN) incorporating the normalized self-attention mechanism and prove that images generated under multi-label are of higher quality than images generated under one-hot label. The generative results of different networks on the public dataset are compared by the inception score and FID evaluation algorithms, and we propose a new evaluation algorithm called SSIM-Mean to measure the quality of generated dairy goat images to further verify the effectiveness of the improved-self-attention GANs.
2020
62448-62457
journalArticle
8
IEEE Access
DOI 10.1109/ACCESS.2020.3014787
IEEE Access
ISSN 2169-3536
Y. Qiu
J. Cai
X. Qin
J. Zhang
Training
Image segmentation
Task analysis
ensemble learning
Predictive models
Lesions
Measurement
Deep convolutional neural networks
fully connected CRFs
pigmented skin lesion segmentation
Skin
Inferring Skin Lesion Segmentation With Fully Connected CRFs Based on Multiple Deep Convolutional Neural Networks
This article presents a method to infer skin lesion segmentation based on multiple deep convolutional neural network (DCNN) models by employing fully connected conditional random fields (CRFs). This method is on the strength of the synergism between ensemble learning which is responsible for introducing diversity from multiple DCNN models and CRFs inference which is in charge of probabilistic inference based on random fields over dermoscopy images. Contrasting to single DCNN models, the proposed method can gain better segmentation by comprehensively utilizing the advances and performance preferences of multiple different DCNN models. In comparison with simple ensemble schemes, it can effectively and precisely refine the fuzzy lesion boundary by utilizing the information in test images to maximize label agreement between similar pixels. Further, an engineering bonus is the feasibility of parallelization for the heavy operation, predicting on multiple DCNN models. In experiments, we tested the effectiveness and robustness of the proposed method on the mainstream datasets ISIC 2017 and PH2, and the results were competitive with the state-of-art methods. we also confirmed that the proposed method can capture the local information in fuzzy dermoscopy images being able to find more accurate lesion borders with a good boost on Boundary Recall (BR) metric. Moreover, since the hyper-parameters in CRFs are explainable, it is possible to adjust them manually to reach better results case by case, being attractive in practice. This work is of value on integration between the deep learning technologies and probabilistic inference in resolving lesion segmentation, and has great potential to be applied in similar tasks.
2020
144246-144258
journalArticle
9
IEEE Access
DOI 10.1109/ACCESS.2021.3128736
IEEE Access
ISSN 2169-3536
L. -H. Wang
L. -J. Ding
C. -X. Xie
S. -Y. Jiang
I. -C. Kuo
X. -K. Wang
J. Gao
P. -C. Huang
P. A. R. Abu
Convolutional neural networks
Feature extraction
convolutional neural network
Training
Classification algorithms
Databases
ECG classification
Electrocardiogram (ECG)
Electrocardiography
Heart rate variability
OTSU
premature ventricular contraction
Automated Classification Model With OTSU and CNN Method for Premature Ventricular Contraction Detection
Premature ventricular contraction (PVC) is one of the most common arrhythmias which can cause palpitation, cardiac arrest, and other symptoms affecting the work and rest activities of a patient. However, patients hardly decipher their own feelings to determine the severity of the disease thus, requiring a professional medical diagnosis. This study proposes a novel method based on image processing and convolutional neural network (CNN) to extract electrocardiography (ECG) curves from scanned ECG images derived from clinical ECG reports, and segment and classify heartbeats in the absence of a digital ECG data. The ECG curve is extracted using a comprehensive algorithm that combines the OTSU algorithm with erosion and dilation. This algorithm can efficiently and accurately separate the ECG curve from the ECG background grid. The performance of the classification model was evaluated and optimized using hundreds of clinical ECG data collected from Fujian Provincial Hospital. Additionally, thousands of clinical ECG reports were scanned to digital images as the test set to confirm the accuracy of the algorithm for practical application. Results showed that the average sensitivity, specificity, positive predictive value, and accuracy of the proposed model on the MIT-BIH dataset were 95.47%, 97.72%, 98.75%, and 98.25%, respectively. The classification average sensitivity, specificity, positive predictive value, and accuracy based on clinical scanned ECG images can reach to 97.24%, 81.6%, 83.8%, and 89.33%, respectively, and the clinical feasibility is high. Overall, the proposed method can extract ECG curves from scanned ECG images efficiently and accurately. Furthermore, it performs well on heartbeat classification of normal (N) and ventricular premature heartbeat.
2021
156581-156591
journalArticle
8
IEEE Access
DOI 10.1109/ACCESS.2020.2965333
IEEE Access
ISSN 2169-3536
R. Ghazal
A. K. Malik
N. Qadeer
B. Raza
A. R. Shahid
H. Alquhayz
Task analysis
Semantics
Ontologies
ontology
LSTM
Collaboration
Access control
multi agent system
multi-domain distributed environment
secure collaboration
Intelligent Role-Based Access Control Model and Framework Using Semantic Business Roles in Multi-Domain Environments
Today's rapidly developing communication technologies and dynamic collaborative business models made the security of data and resources more crucial than ever especially in multi-domain environments like Cloud and Cyber-Physical Systems (CPS). It enforced the research community to develop enhanced access control techniques and models for resources across multi-domain distributed environments so that the security requirements of all participating organizations can be fulfilled through considering dynamicity of changing environments and versatility of access control policies. The popularity of Role-Based Access Control (RBAC) model is irrefutable because of low administrative overhead and large-scale implementation in business organizations. However, it does not incorporate the dynamically changing policies and lacks semantically meaningful business roles which could have a diverse impact upon access decisions in multi-domain business environments. This paper describes our proposed novel access control framework that uses semantic business roles and intelligent agents through implementation of our Intelligent RBAC (I-RBAC) model. It encompasses occupational entitlements as roles for multiple domains. We use the dataset of original occupational roles provided by Standard Occupational Classification (SOC), USA. The novelty of the paper lies in developing a core I-RBAC ontology using real-world semantic business roles and intelligent agent technologies together for achieving required level of access control in highly dynamic multi-domain environment. The intelligent agents use WordNet and bidirectional LSTM deep neural network for automated population of organizational ontology from unstructured text policies. This dynamically learned organizational ontology is further matched with our core I-RBAC ontology in order to extract unified semantic business roles. The proposed I-RBAC model is mathematically described and the overall I-RBAC framework and its implementation architecture is explained. At the end, the I-RBAC model is validated through the implementation results that show a linear runtime trend of the model in presence of a large number of permission assignments and multiple queries.
2020
12253-12267
journalArticle
60
IEEE Transactions on Geoscience and Remote Sensing
DOI 10.1109/TGRS.2021.3137967
IEEE Transactions on Geoscience and Remote Sensing
ISSN 1558-0644
M. Zhou
X. Fu
J. Huang
F. Zhao
A. Liu
R. Wang
Feature extraction
Computer architecture
Spatial resolution
Task analysis
Convolution
Neural networks
transformer
Transformers
Invertible neural network
pan-sharpening
Effective Pan-Sharpening With Transformer and Invertible Neural Network
In remote sensing imaging systems, pan-sharpening is an important technique to obtain high-resolution multispectral images from a high-resolution panchromatic image and its corresponding low-resolution multispectral image. Due to the powerful learning capability of convolution neural networks (CNNs), CNN-based methods have dominated this field. However, due to the limitation of the convolution operator, long-range spatial features are often not accurately obtained, thus limiting the overall performance. To this end, we propose a novel and effective method by exploiting a customized transformer architecture and information-lossless invertible neural module for long-range dependencies modeling and effective feature fusion in this article. Specifically, the customized transformer formulates the panchromatic (PAN) and multispectral (MS) features as queries and keys to encourage joint feature learning across two modalities, while the designed invertible neural module enables effective feature fusion to generate the expected pan-sharpened results. To the best of our knowledge, this is the first attempt to introduce a transformer and a invertible neural network into the pan-sharpening field. Extensive experiments over different kinds of satellite datasets demonstrate that our method outperforms state-of-the-art algorithms both visually and quantitatively with fewer parameters and flops. Furthermore, the ablation experiments also prove the effectiveness of the proposed customized long-range transformer and effective invertible neural feature fusion module for pan-sharpening.
2022
1-15
journalArticle
6
IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
DOI 10.1109/JSTARS.2013.2258138
3
IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
ISSN 2151-1535
H. Wu
L. Ni
N. Wang
Y. Qian
B. -H. Tang
Z. -L. Li
inverse problems
remote sensing
Hyperspectral imaging
Atmospheric modeling
Land surface
Mathematical model
Atmospheric measurements
Atmospheric humidity profile
atmospheric temperature profile
Humidity
hyperspectral thermal infrared
IASI
Estimation of Atmospheric Profiles From Hyperspectral Infrared IASI Sensor
A physics-based regression algorithm was developed and applied to the Infrared Atmospheric Sounding Interferometer (IASI) observations to estimate atmospheric temperature and humidity profiles. The proposed algorithm utilized three steps to solve the ill-posed problems and to stabilize the solution in a fast speed regression manner: 1) a set of optimal channels was selected to decrease the effect of forward model errors or uncertainties of trace gases; 2) the principal component analysis technique was used to reduce the number of unknowns; 3) a ridge regression procedure was introduced to improve the ill-conditioned problem and to lessen the influence of correlation. To determine the optimal coefficients of the algorithm, a simulated dataset was generated with the spectral emissivities and atmospheric profiles fully covering all the possible situations for clear sky conditions. Then, the accuracy of the algorithm was evaluated against with both simulated and actual IASI data. The root mean squared error (RMSE) of atmospheric temperature profile for the simulated data is about 1.5 K in troposphere and stratosphere and is close to 4 K near the surface with no biases. The RMSE of atmospheric humidity profile for the simulated data is about 0.001-0.003 g/g at low altitude. Although the retrieval accuracy for the actual IASI data is not as good as those for the simulated data, the vertical distribution of atmospheric profiles can be well captured. Those results showed that the proposed algorithm is promising when the profile bias errors could be removed.
June 2013
1485-1494
journalArticle
9
IEEE Access
DOI 10.1109/ACCESS.2021.3058103
IEEE Access
ISSN 2169-3536
S. Ahmadi-Asl
S. Abukhovich
M. G. Asante-Mensah
A. Cichocki
A. H. Phan
T. Tanaka
I. Oseledets
Matrix decomposition
HOSVD
Tensors
Approximation algorithms
Signal processing algorithms
Memory management
Probability distribution
random projection
Randomized algorithm
sampling
tensor decomposition
Tucker decomposition
unfolding
Randomized Algorithms for Computation of Tucker Decomposition and Higher Order SVD (HOSVD)
Big data analysis has become a crucial part of new emerging technologies such as the internet of things, cyber-physical analysis, deep learning, anomaly detection, etc. Among many other techniques, dimensionality reduction plays a key role in such analyses and facilitates feature selection and feature extraction. Randomized algorithms are efficient tools for handling big data tensors. They accelerate decomposing large-scale data tensors by reducing the computational complexity of deterministic algorithms and the communication among different levels of memory hierarchy, which is the main bottleneck in modern computing environments and architectures. In this article, we review recent advances in randomization for computation of Tucker decomposition and Higher Order SVD (HOSVD). We discuss random projection and sampling approaches, single-pass and multi-pass randomized algorithms and how to utilize them in the computation of the Tucker decomposition and the HOSVD. Simulations on synthetic and real datasets are provided to compare the performance of some of best and most promising algorithms.
2021
28684-28706
journalArticle
10
IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
DOI 10.1109/JSTARS.2017.2716376
10
IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
ISSN 2151-1535
Z. Liu
P. Wu
S. Duan
W. Zhan
X. Ma
Y. Wu
Climate change
Land surface temperature
Land surface
Satellites
Genetic algorithms
Clouds
land surface temperature (LST)
Surface reconstruction
FengYun-2F (FY-2F)
genetic algorithm (GA)
Reconstruction algorithms
spatial reconstruction
spectral multimanifold clustering (SMMC)
temporal reconstruction
Spatiotemporal Reconstruction of Land Surface Temperature Derived From FengYun Geostationary Satellite Data
The FengYun-2F (FY-2F) geostationary satellite land surface temperature (LST) and its diurnal variation are important when evaluating climate change, the land-atmosphere energy budget, and the hydrological cycle. However, the presence of clouds generates numerous meaningless pixels that constrain the potential application of the available satellite LST products. These pixels covered by cloud are assigned –2, and otherwise are the LST values, based on the result of a double-channel threshold cloud detection algorithm. This paper proposes a combined temporal and spatial information reconstruction method for the missing FY-2F LST data reconstruction with a good spatial continuity, where cloud detection has already been undertaken. Compared with the methods used in the past, the main characteristics of the proposed method are: 1) the consideration of a free parameter $\delta T$ when modeling the diurnal temperature cycle curve; 2) the introduction of the genetic algorithm for solving the parameters; 3) the adoption of the spectral multimanifold clustering algorithm for clustering the multitemporal geostationary satellite LST data; and 4) the accurate and efficient combined temporal and spatial reconstruction method. The proposed combined temporal and spatial reconstruction method was tested and quantitatively assessed with both simulated and real data experiments, using the FY-2F LST products. The results indicate that the combined reconstruction method is accurate to within about 2 °C, which can significantly improve the practical value of FY-2F LST datasets.
Oct. 2017
4531-4543
journalArticle
7
IEEE Access
DOI 10.1109/ACCESS.2019.2947542
IEEE Access
ISSN 2169-3536
K. H. Abdulkareem
M. A. Mohammed
S. S. Gunasekaran
M. N. Al-Mhiqani
A. A. Mutlag
S. A. Mostafa
N. S. Ali
D. A. Ibrahim
Monitoring
Computational modeling
machine learning
Cloud computing
Security
Internet of Things
Sensors
Internet of Things (IoT)
Edge computing
applications
Fog computing
A Review of Fog Computing and Machine Learning: Concepts, Applications, Challenges, and Open Issues
Systems based on fog computing produce massive amounts of data; accordingly, an increasing number of fog computing apps and services are emerging. In addition, machine learning (ML), which is an essential area, has gained considerable progress in various research domains, including robotics, neuromorphic computing, computer graphics, natural language processing (NLP), decision-making, and speech recognition. Several researches have been proposed that study how to employ ML to settle fog computing problems. In recent years, an increasing trend has been observed in adopting ML to enhance fog computing applications and provide fog services, like efficient resource management, security, mitigating latency and energy consumption, and traffic modeling. Based on our understanding and knowledge, there is no study has yet investigated the role of ML in the fog computing paradigm. Accordingly, the current research shed light on presenting an overview of the ML functions in fog computing area. The ML application for fog computing become strong end-user and high layers services to gain profound analytics and more smart responses for needed tasks. We present a comprehensive review to underline the latest improvements in ML techniques that are associated with three aspects of fog computing: management of resource, accuracy, and security. The role of ML in edge computing is also highlighted. Moreover, other perspectives related to the ML domain, such as types of application support, technique, and dataset are provided. Lastly, research challenges and open issues are discussed.
2019
153123-153140
journalArticle
21
IEEE Sensors Journal
DOI 10.1109/JSEN.2021.3056957
16
IEEE Sensors Journal
ISSN 1558-1748
L. Wang
W. Song
Y. Lan
H. Wang
X. Yue
X. Yin
E. Luo
B. Zhang
Y. Lu
Y. Tang
deep learning
Adaptation models
Standards
Drones
smart agriculture
Image recognition
Droplet detection
Optical variables measurement
Pollution measurement
Size measurement
vision sensing
A Smart Droplet Detection Approach With Vision Sensing Technique for Agricultural Aviation Application
Deep learning has been widely used in various sensor detection fields to realize intelligent detection tasks. However, there are always restrictions on how these functions can be integrated into embedded devices to complete mobile and convenient sensing detection tasks. Therefore, the MobileNet_SSD, A lightweight model after simplification and optimization, is used in this paper to design a portable visual sensor system for the detection of spray droplet deposition in drone applications. The sensing system includes a droplet deposition image loop acquisition device and a supporting host computer interactive platform. It introduces the Sarsa algorithm to establish an adaptive model of light intensity to enhance the robustness and combines Deep Neural Networks and image processing technology to achieve rapid loop detection of droplet deposition parameters on the mobile terminal. Experimental results indicate that the proposed sensor can adapt to light changes in complex environments, and accurately measure the deposition parameters of different droplet density images. Furthermore, it is of great significance to detect the quality of drone sprays, master the rules of droplet deposition, and understand the effects of pesticide spraying.
15 Aug.15, 2021
17508-17516
journalArticle
10
IEEE Access
DOI 10.1109/ACCESS.2022.3231579
IEEE Access
ISSN 2169-3536
M. A. Shafaey
F. Melgani
M. A. . -M. Salem
M. N. Al-Berry
H. M. Ebied
E. -S. A. El-Dahshan
M. F. Tolba
Convolutional neural networks
Feature extraction
Support vector machines
Hyperspectral imaging
machine learning
Convolution
support vector machine
Convolutional neural network
pixel-based classification
feedforward learning
Filter banks
hyperspectral signature
IP networks
Pixel-Wise Classification of Hyperspectral Images With 1D Convolutional SVM Networks
Nowadays, remote sensing image analysis is needed in various important tasks such as city planning, land-use classification, agriculture monitoring, military surveillance, and many other applications. In this context, hyperspectral images can play a useful role, but require specific handling. This paper presents a convolutional neural network based on one-dimensional support vector machine (SVM) convolution operations (1D-CSVM) for the analysis of hyperspectral images. SVM-based CNN (CSVM) was introduced first for the classification of high spatial resolution RGB images. It relies on linear SVMs to create filter banks in the convolution layers. In this work, the network is modified to cope with one-dimensional hyperspectral signatures and perform pixel-based classification. It thus analyzes each pixel spectrum independently from the pixel spatial neighborhood. Experiments were carried out on four benchmark hyperspectral datasets, Salinas-A, Kennedy Space Center (KSC), Indian Pines (IP) and Pavia University (Pavia-U). Compared to state-of-the-art models, the proposed network produces promising results for all tested datasets, with an accuracy up to 99.76%.
2022
133174-133185
journalArticle
15
IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
DOI 10.1109/JSTARS.2021.3132259
IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
ISSN 2151-1535
N. Makkar
L. Yang
S. Prasad
Feature extraction
Image segmentation
Hyperspectral imaging
Task analysis
Adaptation models
Semantics
Adversarial learning
Adversarial machine learning
domain adaptation
hyperspectral image analysis
large-scale mapping
Adversarial Learning Based Discriminative Domain Adaptation for Geospatial Image Analysis
The ability of supervised image analysis methods to provide state-of-the-art performance is limited by availability of high-quality labeled data in large quantities. Domain adaptation approaches propose a solution to this problem by leveraging quality labeled information from auxiliary data sources. In this work, we use adversarial learning for domain adaptation for remote sensing applications. First, we approached the problem of unavailable target domain labels with unsupervised domain adaptation and then extended our method for semisupervised domain adaptation to use a few available labels as well. We are using adversarial learning to extract discriminative target domain features that are aligned with source domain. We test our framework for two very different applications of remote sensing imagery, multiclass classification in hyperspectral images and semantic segmentation in large scale satellite images. For hyperspectral image analysis two datasets were used: the University of Houston shadow data was used for quantifying the efficacy of our approach to varying illumination, and the Botswana data was used to quantify the efficacy of our approach under multitemporal spectral shifts. Multisensor high-resolution images from National Agriculture Imagery Program and SpaceNet-Rio datasets were used as the source and target for the task of building extraction for large scale semantic segmentation based domain adaptation.
2022
150-162
journalArticle
10
IEEE Access
DOI 10.1109/ACCESS.2022.3209186
IEEE Access
ISSN 2169-3536
K. Song
J. Li
R. Qiu
G. Yang
Crops
Cameras
Sensors
Pose estimation
Trajectory
Autonomous systems
Localization
Location awareness
Mobile robots
pose optimization
Robot vision systems
SLAM
VIO
Monocular Visual-Inertial Odometry for Agricultural Environments
The accuracy of autonomous robot localization using a monocular visual-inertial odometry system (VIO) is significantly reduced in an agricultural environment compared to an urban and indoor environment due to the unstructured scenes with unstable features, variation of light conditions, and rugged terrain. To address those challenges, we propose a monocular VIO system with modifications to the existing state-of-the-art monocular VIO system VINS-mono. Three modules of VINS-mono have improved in this work: vision processing front end, pose optimization, failure detection and recovery. In the vision processing front-end module, we proposed a keyframe selection algorithm base on vertical movement smoothness verification to prevent the rapid loss of feature tracks. In the pose optimization module, some feature points are removed using a depth-limited approach to improve the efficiency and accuracy of trajectory tracking. In the failure detection and recovery module, we propose a failure recovery method using the old trajectory poses, which can recover the trajectory tracking process interrupted by the failure and alleviate the orientation drift. Experiments on the Rosario dataset have shown that our system outperforms VINS-mono, and the absolute trajectory error in the agricultural environment can be at least reduced by 69% compared with the VINS-mono, which can effectively improve the localization accuracy of agriculture robots in the agricultural environment.
2022
103975-103986
journalArticle
4
IEEE Robotics and Automation Letters
DOI 10.1109/LRA.2019.2906548
3
IEEE Robotics and Automation Letters
ISSN 2377-3766
L. Scimeca
J. Hughes
P. Maiolino
F. Iida
Visualization
Three-dimensional displays
and learning for soft robots
control
force and tactile sensing
Modeling
Soft robotics
soft sensors and actuators
Tactile sensors
Tendons
Model-Free Soft-Structure Reconstruction for Proprioception Using Tactile Arrays
Continuum body structures provide unique opportunities for soft robotics, with the infinite degrees of freedom enabling unconstrained and highly adaptive exploration and manipulation. However, the infinite degrees of freedom of continuum bodies makes sensing (both intrinsically and extrinsically) challenging. To address this, in this letter, we propose a model-free method for sensorizing tentacle-like continuum soft-structures using an array of spatially arranged capacitive tactile sensors. By using visual tracking, the relationship between the tactile response and the three-dimensional shape of the continuum soft-structure can be learned. A dataset of 15 000 random soft-body postures was used, with recorded camera-tracked positions logged synchronously to the tactile sensor responses. This was used to train a neural network that can predict posture. We show that it is possible to achieve proprioceptive awareness over all three axis of motion in space, reconstructing the body structure and inferring the soft body head's pose with an average accuracy of ≈1 mm in comparison to the visual tracked counterpart. To demonstrate the capabilities of the system, we perform random exploration of environments limiting the work-space of the sensorized robot. We find the method capable to autonomously reconstruct the reachable morphology of the environment without the need of external sensing units.
July 2019
2479-2484
journalArticle
71
IEEE Transactions on Instrumentation and Measurement
DOI 10.1109/TIM.2022.3156179
IEEE Transactions on Instrumentation and Measurement
ISSN 1557-9662
P. Pal
S. Tripathi
C. Kumar
Soil measurements
Soil moisture
Training
machine learning
precision agriculture
Soil
Artificial neural networks
soil moisture
Costs
Probes
Artificial neural network (ANN)
bidirectional long short term memory network (BLSTM)
capacitive sensor
Single Probe Imitation of Multi-Depth Capacitive Soil Moisture Sensor Using Bidirectional Recurrent Neural Network
This work proposes a single probe imitation of multidepth capacitive soil moisture sensor for low-cost and energy-efficient implementation of IoT-assisted wireless sensor network (IoWSN) farm monitoring infrastructure. A conditioning circuit (CC) is devised to capture the behavior of soil water movement and its impact on soil moisture around the probe at different depths. The captured correlation is used to train the proposed neural network (NN) models to estimate the soil water content (SWC) at different soil depths based on a single measurement taken at the reference depth. To adjust the weight of the neurons, training and test dataset are collected through a measurement campaign. The data are collected during the cropping period of paddy vegetation by deploying 150 sensor nodes at different depths in bare land before sowing. Two NN models—artificial neural network (ANN) and bidirectional long short term memory network (BLSTM)—are proposed and compared based on the accuracy of SWC estimation. To demonstrate the efficacy of the concept, the proposed sensor design is compared with relevant soil moisture sensors reported over the past five years. The root mean square error (RMSE), ${R^{2}}$ and mean absolute percentage error (MAPE)-based analysis validate the significance of the proposed NN models.
2022
1-11
journalArticle
60
IEEE Transactions on Geoscience and Remote Sensing
DOI 10.1109/TGRS.2021.3101016
IEEE Transactions on Geoscience and Remote Sensing
ISSN 1558-0644
N. Romero-Puig
A. Marino
J. M. Lopez-Sanchez
Estimation
Synthetic aperture radar
Agriculture
inversion
Covariance matrices
Vegetation mapping
Scattering
Decorrelation
Coherence
height
polarimetric and interferometric synthetic aperture radar (SAR)
trace coherence (TrCoh)
Application of the Trace Coherence to HH-VV PolInSAR TanDEM-X Data for Vegetation Height Estimation
This article investigates, for the first time, the inclusion of the operator Trace Coherence (TrCoh) in polarimetric and interferometric synthetic aperture radar (SAR) methodologies for the estimation of biophysical parameters of vegetation. A modified inversion algorithm based on the well-known Random Volume over Ground (RVoG) model, which employs the TrCoh, is described and evaluated. In this regard, a different set of coherence extrema is used as input for the retrieval stage. In addition, the proposed methodology improves the inversion algorithm by employing analytical solutions rather than approximations. Validation is carried out exploiting single-pass HH-VV bistatic TanDEM-X data, together with reference data acquired over a paddy rice area in Spain. The added value of the TrCoh and the convenience of the use of analytical solutions are assessed by comparing with the conventional polarimetric SAR interferometry (PolInSAR) algorithm. Results demonstrate that the modified proposed methodology is computationally more effective than current methods on this dataset. For the same scene, the steps required for inversion are computed in 6 min with the conventional method, while it only takes 6 s with the proposed approach. Moreover, vegetation height estimates exhibit a higher accuracy with the proposed method in all fields under evaluation. The root-mean-squared error reached with the modified method improves by 7 cm with respect to the conventional algorithm.
2022
1-10
journalArticle
60
IEEE Transactions on Geoscience and Remote Sensing
DOI 10.1109/TGRS.2021.3134127
IEEE Transactions on Geoscience and Remote Sensing
ISSN 1558-0644
N. Efremova
M. E. A. Seddik
E. Erten
Data models
Feature extraction
Soil measurements
Soil moisture
Training
Agriculture
machine learning (ML)
Predictive models
Satellites
soil moisture (SM)
Sentinel-2
unsupervised domain adaptation
generative adversarial networks (GANs)
Sentinel-1
Soil Moisture Estimation Using Sentinel-1/-2 Imagery Coupled With CycleGAN for Time-Series Gap Filing
Fast soil moisture content (SMC) mapping is necessary to support water resource management and to understand crop growth, quality, and yield. Therefore, earth observation (EO) plays a key role due to its ability of almost real-time monitoring of large areas at a low cost. This study aimed to explore the possibility of taking advantage of freely available Sentinel-1 (S1) and Sentinel-2 (S2) EO data for the simultaneous prediction of SMC with cycle-consistent adversarial network (CycleGAN) for time-series gap filling. The proposed methodology, first, learns latent low-dimensional representation of the satellite images, then learns a simple machine learning (ML) model on top of these representations. To evaluate the methodology, a series of vineyards, located in South Australia ’s Eden valley are chosen. Specifically, we presented an efficient framework for extracting latent features from S1 and S2 imagery. We showed how one could use S1 to S2 feature translation based on CycleGAN using S1 and S2 time series when there are missing images acquired over an area of interest. The resulting data in our study is then used to fill gaps in time-series data. We used the resulting latent representations to predict SMC with various ML tools. In the experiments, CycleGAN and the autoencoders were trained with data randomly chosen around the site of interest, so we could augment the existing dataset. The best performance was demonstrated with random forest (RF) algorithm, whereas linear regression model demonstrated significant overfitting. The experiments demonstrate that the proposed methodology outperforms the compared state-of-the-art methods if there are missing optical and synthetic-aperture radar (SAR) images.
2022
1-11
journalArticle
9
IEEE Access
DOI 10.1109/ACCESS.2021.3110978
IEEE Access
ISSN 2169-3536
T. Ilyas
A. Khan
M. Umraiz
Y. Jeong
H. Kim
Crops
Feature extraction
Deep learning
Diseases
Image segmentation
classification
segmentation
Task analysis
precision agriculture
Three-dimensional displays
disease phenotyping
smart farming
strawberries fruit recognition
Multi-Scale Context Aggregation for Strawberry Fruit Recognition and Disease Phenotyping
Timely harvesting and disease identification of strawberry fruits is a major concern for commercial level cultivators. Failing to harvest the grown strawberries can result in the fruit rotting which makes their damaged tissues more prone to grey mold pathogens. Immediate removal of the overgrown or diseased strawberries is inevitable to curb the mass spreading of the pathogen. In this paper, we propose a deep learning-based framework to identify three different strawberry fruit classes (unripe, partially ripe and ripe), as well as a class of overgrown or diseased strawberries. We equip the proposed convolutional encoder-decoder network with three different modules. One for adaptively controlling receptive filed size of the network to detect objects of multiple sizes. Second for controlling the flow of salient features (information) to the deeper layers of the network and the other for controlling the architecture's computational complexity. These modules combined, outperform the previous state-of-the-art semantic segmentation networks on the task of strawberry fruit phenotyping. We also introduce a dataset collected from different farms to evaluate the performance of the network. Quantitative and qualitative results show that notwithstanding heterogeneity in the data and the effect of the real-field variations, our approach produced remarkable results with a 3% increase in mean intersection over union as compared to the other state-of-the-art networks and was able to recognize diseased fruits with a precision of 92.45%.
2021
124491-124504
journalArticle
5
IEEE Robotics and Automation Letters
DOI 10.1109/LRA.2020.2970654
2
IEEE Robotics and Automation Letters
ISSN 2377-3766
P. Kurtser
O. Ringdahl
N. Rotstein
R. Berenstein
Y. Edan
Cameras
Clustering algorithms
Pipelines
robotics in agriculture and forestry
Yield estimation
Robot sensing systems
agricultural automation
Field robots
RGB-D perception
In-Field Grape Cluster Size Assessment for Vine Yield Estimation Using a Mobile Robot and a Consumer Level RGB-D Camera
Current practice for vine yield estimation is based on RGB cameras and has limited performance. In this letter we present a method for outdoor vine yield estimation using a consumer grade RGB-D camera mounted on a mobile robotic platform. An algorithm for automatic grape cluster size estimation using depth information is evaluated both in controlled outdoor conditions and in commercial vineyard conditions. Ten video scans (3 camera viewpoints with 2 different backgrounds and 2 natural light conditions), acquired from a controlled outdoor experiment and a commercial vineyard setup, are used for analyses. The collected dataset (GRAPES3D) is released to the public. A total of 4542 regions of 49 grape clusters were manually labeled by a human annotator for comparison. Eight variations of the algorithm are assessed, both for manually labeled and auto-detected regions. The effect of viewpoint, presence of an artificial background, and the human annotator are analyzed using statistical tools. Results show 2.8-3.5 cm average error for all acquired data and reveal the potential of using low-cost commercial RGB-D cameras for improved robotic yield estimation.
April 2020
2031-2038
journalArticle
16
IEEE Sensors Journal
DOI 10.1109/JSEN.2016.2574762
15
IEEE Sensors Journal
ISSN 1558-1748
I. Potamitis
I. Rigakis
Insects
precision agriculture
Optical sensors
Light emitting diodes
automatic recording unit
electronic insect traps
Frequency modulation
insects
Optical filters
Optoelectronic sensors
Photodiodes
wingbeat
Large Aperture Optoelectronic Devices to Record and Time-Stamp Insects’ Wingbeats
Recording and analysis of wildlife sounds with regard to monitoring biodiversity are a developing trend in ecology. Automatic audio-based units are commonly used to record field vocalizations of birds, bats, cetaceans, and amphibians. The wingbeat of insects produces audible but feeble tones. Practical automatic recording units for the wingbeat of insects are still pending. In this paper, we present a complete system to record the wingbeat of insects based on the large aperture optical sensors that turn the light fluctuations (caused by the partial occlusion of light from the wings) into sound. Wide apertures are useful when tracking the movement of fast flying insects and the full motion of the beating wing in the case of tethered insects. The system detects a wingbeat event, auto-triggers the recording process, time-stamps the event, and stores the permanent record in situ. When the sensor is inserted in an insectary, it effortlessly produces massive datasets of wingbeat recordings. We discuss the implications for novel studies that are impractical to carry out manually, as they involve large numbers of insects. We also suggest potential applications such as smart insect traps that count, recognize, and alert for the presence of insects of economic and public health importance.
Aug.1, 2016
6053-6061
journalArticle
3
IEEE Robotics and Automation Letters
DOI 10.1109/LRA.2018.2848308
4
IEEE Robotics and Automation Letters
ISSN 2377-3766
A. Zaganidis
L. Sun
T. Duckett
G. Cielniak
Image color analysis
Transforms
Semantics
Partitioning algorithms
Three-dimensional displays
robotics in agriculture and forestry
Localization
SLAM
Gaussian distribution
Iterative closest point algorithm
Integrating Deep Semantic Segmentation Into 3-D Point Cloud Registration
Point cloud registration is the task of aligning 3D scans of the same environment captured from different poses. When semantic information is available for the points, it can be used as a prior in the search for correspondences to improve registration. Semantic-assisted Normal Distributions Transform (SE-NDT) is a new registration algorithm that reduces the complexity of the problem by using the semantic information to partition the point cloud into a set of normal distributions, which are then registered separately. In this letter we extend the NDT registration pipeline by using PointNet, a deep neural network for segmentation and classification of point clouds, to learn and predict per-point semantic labels. We also present the Iterative Closest Point (ICP) equivalent of the algorithm, a special case of Multichannel Generalized ICP. We evaluate the performance of SE-NDT against the state of the art in point cloud registration on the publicly available classification data set Semantic3d.net. We also test the trained classifier and algorithms on dynamic scenes, using a sequence from the public dataset KITTI. The experiments demonstrate the improvement of the registration in terms of robustness, precision and speed, across a range of initial registration errors, thanks to the inclusion of semantic information.
Oct. 2018
2942-2949
journalArticle
10
IEEE Access
DOI 10.1109/ACCESS.2022.3189676
IEEE Access
ISSN 2169-3536
N. Ullah
J. A. Khan
L. A. Alharbi
A. Raza
W. Khan
I. Ahmad
Crops
Feature extraction
deep learning
Insects
convolutional neural networks
Support vector machines
transfer learning
Classification algorithms
Image recognition
fine-tuning
Insects pests
Pest control
An Efficient Approach for Crops Pests Recognition and Classification Based on Novel DeepPestNet Deep Learning Model
Crop pests are to blame for significant economic, social, and environmental losses worldwide. Various pests have different control strategies, and precisely identifying pests has become crucial to pest control and is a significant difficulty in agriculture. Many agricultural professionals are interested in deep learning (DL) models since they have shown significant promise in image recognition. Pest identification approaches in literature have relatively low accuracy in pest recognition and classification due to the complexity of their algorithms and limited data availability. Misclassification of insect pests sometimes leads to using the wrong pesticides, causing harm to agricultural yields and the surrounding environment. It necessitates developing an automated system capable of more accurate pest identification and classification. This paper presents a novel end-to-end DeepPestNet framework for pest recognition and classification. The proposed model has 11 learnable layers, including eight convolutional and three fully connected (FC) layers. We used image rotations techniques to increase the size of the dataset and image augmentations techniques to test the generalizability of the proposed DeepPestNet approach. We used the popular Deng’s crops data set to assess the proposed DeepPestNet framework. We used the proposed method to recognize and classify crop pests into 10-class pests, i.e., Locusta migratoria, Euproctis pseudoconspersa strand, chrysochus Chinensis, empoasca flavescens, Spodoptera exigua, larva of laspeyresia pomonella, parasa lepida, acrida cinerea, larva of S. exigua, and L.pomonella types of insects pests. The proposed method achieved optimal accuracy of 100%. We compared the proposed DeepPestNet approach with traditional pre-trained deep learning (DL) models. To verify the general adaptability of this model, we tested the proposed model on the standard Kaggle dataset “Pest Dataset” to recognize nine types of pests: aphids, armyworm, beetle, bollworm, grasshopper, mites, mosquito, sawfly, and stem borer and achieved an accuracy of 98.92%. The proposed model can provide specialists and farmers with immediate and effective aid in recognizing pests, potentially reducing economic and crop yield losses.
2022
73019-73032
journalArticle
K. Umebayashi
M. Kobayashi
M. López-Benítez
Wireless communication
Sensors
Stochastic processes
Time measurement
cognitive radio
deterministic model
duty cycle
Dynamic spectrum access
Frequency measurement
Long Term Evolution
smart spectrum access
spectrum measurement
Wireless LAN
Efficient Time Domain Deterministic-Stochastic Model of Spectrum Usage
For achieving an efficient spectrum sharing in a context of dynamic spectrum access, understanding the spectrum usage by licensed users [primary users (PUs)], is important for secondary users (SUs). Duty cycle (DC) has been used to express the deterministic and stochastic aspects of spectrum usage. Specifically, a deterministic model for the mean of the duty cycle (M-DC) has been proposed in a previous work. The deterministic aspect of M-DC is affected by social behavior, and common habits of users, which can be confirmed in cellular systems. On the other hand, the observed DC (O-DC) during short time duration has randomness and a stochastic model is more suitable, e.g. distribution of O-DC. In this paper, we extend the conventional approach, in which only either the deterministic or stochastic aspect is considered, to a combined deterministic-stochastic (DS) model, which represents both the deterministic and stochastic aspects at once. For the distribution of the O-DC, the beta distribution has been used as stochastic model, but we employ a mixture of beta distributions. The mixture-beta distribution can achieve higher accuracy but requires more capacity for data storage in spectrum usage measurements since it has a higher number of parameters than the beta distribution. For this issue, we employ regression analysis in DS-model since this approach can reduce the number of parameters while retaining the accuracy. We show the validity of DS-model based on exhaustive spectrum measurements in IEEE 802.11-based wireless local area networks and long-term evolution uplink.
March 2018
1518-1527
17
IEEE Transactions on Wireless Communications
DOI 10.1109/TWC.2017.2779511
3
IEEE Transactions on Wireless Communications
ISSN 1558-2248
journalArticle
60
IEEE Transactions on Geoscience and Remote Sensing
DOI 10.1109/TGRS.2022.3227647
IEEE Transactions on Geoscience and Remote Sensing
ISSN 1558-0644
L. Gao
X. -N. Song
P. Leng
J. -W. Ma
X. -M. Zhu
R. -H. Hu
Y. -F. Wang
Y. -N. Zhang
D. -W. Yin
Soil moisture
Remote sensing
Salinity (geophysical)
Microwave imaging
Soil
soil moisture (SM)
uncertainty
Dielectric constant
Dielectrics
saline soil
salinity
Impact of Soil Salinity on Soil Dielectric Constant and Soil Moisture Retrieval From Active Microwave Remote Sensing
Soil salinity plays a key role in influencing the soil dielectric constant and soil backscatter coefficient. However, soil moisture (SM) retrieval models constructed based on active microwave data hardly consider soil salinity. Thus, obtaining the SM datasets with various salinity on regional and local scales is difficult. This study aimed to employ theoretical model simulation to investigate the errors of SM retrieval due to not considering the impact of soil salinity. Then, three typical saline soil dielectric constant models were validated and compared based on the experimental measurement datasets. Results show that the WYR saline soil dielectric constant model has excellent performance. The soil salinity mainly affects the imaginary part of the dielectric constant and the effect of salinity on the soil dielectric constant is more significant when the SM has larger values. In addition, in retrieving SM with soil salinity more than 10 g/kg, the retrieval result of SM has an absolute error of 0.04 $\text{m}^{3}/\text{m}^{3}$ and a relative error of 5% when not considering the soil salinity impact. In retrieving SM with soil salinity less than 10 g/kg, the retrieved SM error increased by 2%, and the absolute error increased by 0.01 $\text{m}^{3}/\text{m}^{3}$ as soil salinity increased by 3 g/kg. We believe that The study will give a theoretical reference for establishing the SM retrieval model in saline soil areas using microwave data.
2022
1-12
journalArticle
71
IEEE Transactions on Instrumentation and Measurement
DOI 10.1109/TIM.2022.3205920
IEEE Transactions on Instrumentation and Measurement
ISSN 1557-9662
R. Tong
P. Li
L. Gao
X. Lang
A. Miao
X. Shen
Temperature sensors
Sensors
Manifolds
Blades
Ellipsoidal nearest neighbor graph (ENNG)
Fault detection
fisher criterion
icing fault detection of wind turbine blade
semisupervised extreme learning machine (SS-ELM)
Semisupervised learning
the lack of labeled samples
Wind turbines
A Novel Ellipsoidal Semisupervised Extreme Learning Machine Algorithm and Its Application in Wind Turbine Blade Icing Fault Detection
The conventional semisupervised extreme learning machine (SS-ELM) algorithm can provide a solution to the lack of labeled samples in wind turbine blade icing fault detection, but its performance is limited by the irrationality of the spherical nearest neighbor graph (SNNG) calculation strategy. To solve this problem, a novel ellipsoidal semisupervised extreme learning machine (ESS-ELM) algorithm is proposed in this article and applied to wind turbine blade icing fault detection. In this study, we creatively propose a novel ellipsoidal nearest neighbor graph (ENNG) calculation strategy that considers the distribution information of the labeled samples to construct the ESS-ELM algorithm. Different from the conventional SNNG, the ENNG can adaptively assign corresponding calculation weights to each feature in the data space according to the Fisher criterion, which allows it to better match the smoothness assumption of the manifold regularization learning framework. In addition, the two adjustable parameters of the enhancement factor and the degradation factor are ingeniously introduced into the ENNG, which further ensure the applicability and security of the proposed ESS-ELM. The superiority of the ESS-ELM algorithm is verified by extensive benchmark industrial fault datasets and the real-world icing dataset of two wind turbines. It is demonstrated that the proposed ESS-ELM algorithm achieves better performance than the ELM, its existing variants, and some state-of-the-art wind turbine blade icing detection methods.
2022
1-16
journalArticle
9
IEEE Access
DOI 10.1109/ACCESS.2021.3089586
IEEE Access
ISSN 2169-3536
Ö. Aslan
A. A. Yilmaz
Feature extraction
deep learning
Deep learning
Computer architecture
transfer learning
Classification algorithms
Cloud computing
deep neural networks
Malware
malware classification
malware detection
malware variants
Static analysis
A New Malware Classification Framework Based on Deep Learning Algorithms
Recent technological developments in computer systems transfer human life from real to virtual environments. Covid-19 disease has accelerated this process. Cyber criminals' interest has shifted in a real to virtual life as well. This is because it is easier to commit a crime in cyberspace rather than regular life. Malicious software (malware) is unwanted software which is frequently used by cyber criminals to launch cyber-attacks. Malware variants are continuing to evolve by using advanced obfuscation and packing techniques. These concealing techniques make malware detection and classification significantly challenging. Novel methods which are quite different from traditional methods must be used to effectively combat with new malware variants. Traditional artificial intelligence (AI) specifically machine learning (ML) algorithms are no longer effective in detecting all new and complex malware variants. Deep learning (DL) approach which is quite different from traditional ML algorithms can be a promising solution to the problem of detecting all variants of malware. In this study, a novel deep-learning-based architecture is proposed which can classify malware variants based on a hybrid model. The main contribution of the study is to propose a new hybrid architecture which integrates two wide-ranging pre-trained network models in an optimized manner. This architecture consists of four main stages, namely: data acquisition, the design of deep neural network architecture, training of the proposed deep neural network architecture, and evaluation of the trained deep neural network. The proposed method tested on Malimg, Microsoft BIG 2015, and Malevis datasets. The experimental results show that the suggested method can effectively classify malware with high accuracy which outperforms the state of the art methods in the literature. When proposed method tested on Malimg dataset, 97.78% accuracy is obtained which is outperformed most of the ML-based malware detection method.
2021
87936-87951
journalArticle
C. N. Phyo
T. T. Zin
P. Tin
Feature extraction
Monitoring
deep learning
Deep learning
Image recognition
Senior citizens
Consumer electronics
consumer electronics perspective
formation of relative joint image
Human action recognition
skeletal joints
Skeleton
Deep Learning for Recognizing Human Activities Using Motions of Skeletal Joints
With advances in consumer electronics, demands have increased for greater granularity in differentiating and analyzing human daily activities. Moreover, the potential of machine learning, and especially deep learning, has become apparent as research proceeds in applications, such as monitoring the elderly, and surveillance for detection of suspicious people and objects left in public places. Although some techniques have been developed for human action recognition (HAR) using wearable sensors, these devices can place unnecessary mental and physical discomfort on people, especially children and the elderly. Therefore, research has focused on image-based HAR, placing it on the front line of developments in consumer electronics. This paper proposes an intelligent HAR system which can automatically recognize the human daily activities from depth sensors using human skeleton information, combining the techniques of image processing and deep learning. Moreover, due to low computational cost and high accuracy outcomes, an approach using skeleton information has proven very promising, and can be utilized without any restrictions on environments or domain structures. Therefore, this paper discusses the development of an effective skeleton information-based HAR which can be used as an embedded system. The experiments are performed using two famous public datasets of human daily activities. According to the experimental results, the proposed system outperforms other state-of-the-art methods on both datasets.
May 2019
243-252
65
IEEE Transactions on Consumer Electronics
DOI 10.1109/TCE.2019.2908986
2
IEEE Transactions on Consumer Electronics
ISSN 1558-4127
journalArticle
8
IEEE Access
DOI 10.1109/ACCESS.2020.2994746
IEEE Access
ISSN 2169-3536
K. I. Mohammed
J. Jaafar
A. A. Zaidan
O. S. Albahri
B. B. Zaidan
K. H. Abdulkareem
A. N. Jasim
A. H. Shareef
M. J. Baqer
A. S. Albahri
M. A. Alsalem
A. H. Alamoodi
Diseases
Real-time systems
Sensors
Big Data
Decision making
big data
chronic disease
decision-making
HDMVM
intelligent
prioritisation
Telemedicine
A Uniform Intelligent Prioritisation for Solving Diverse and Big Data Generated From Multiple Chronic Diseases Patients Based on Hybrid Decision-Making and Voting Method
Telemedicine is increasingly used in the modern health care system because it provides health care services to patients amidst distant locations. However, the prioritisation process for patients with multiple chronic diseases (MCDs) over telemedicine is becoming increasingly complex due to diverse and big data generated from multiple disease conditions. To solve such a problem, massive datasets must be collected, and high velocity must be acquired, specifically in real-time processing. This process requires decision-making (DM) regarding the emergency degree of each chronic disease for every patient. Multi-criteria decision-making (MCDM) approaches (i.e. direct aggregation, distance measurement and compromise ranking) are the main solutions for dealing with this complex situation. However, each MCDM approach provides a unique rank from those of other methods. By far, the preferred DM approach that can provide an ideal rank better than other approaches has not been established. This study proposes an extension of the technique for reorganising opinion order to interval levels (TROOIL). Such an extension is called Hybrid DM and Voting Method (HDMVM) which is based on different DM approaches (i.e. direct aggregation, distance measurement and compromise ranking). HDMVM is used to prioritise big data of patients with MCDs in real-time through the remote health-monitoring procedure. In this paper, we propose a methodology that is based on three sequential stages. The first stage illustrates how the big data of patients with MCDs can be recognised in the telemedicine environment and identifies the target telemedicine tier in this study. The second stage describes the steps of the proposed HDMVM sequentially. The third stage applies the proposed method by prioritising the case study of big data of patients with MCDs based on the above DM approaches. Moreover, dataset of remote patients with MCDs (n = 500 ) is adopted, which contains three diseases, namely, chronic heart diseases and high and low blood pressures. The prioritisation results vary among direct aggregation, distance measurement and compromise approaches. The proposed HDMVM effectively provides a uniform and final ranking result for big data of patients with MCDs. A statistical method (i.e. mean) is performed to objectively validate the ranking results. Significant differences between the scores of the groups are identified in the objective validation, signifying identical ranking results. The evaluation of the proposed work with the benchmark study indicates that this study has tackled issues relevant to big data and diversity of MCDM approaches in the prioritisation of patients with MCDs.
2020
91521-91530
journalArticle
7
IEEE Access
DOI 10.1109/ACCESS.2019.2937347
IEEE Access
ISSN 2169-3536
F. Ullah
H. Naeem
S. Jabbar
S. Khalid
M. A. Latif
F. Al-turjman
L. Mostarda
Feature extraction
Internet of Things
cyber security
Malware
malware detection
Computer crime
Computer languages
data mining
Plagiarism
software piracy
Cyber Security Threats Detection in Internet of Things Using Deep Learning Approach
The IoT (Internet of Things) connect systems, applications, data storage, and services that may be a new gateway for cyber-attacks as they continuously offer services in the organization. Currently, software piracy and malware attacks are high risks to compromise the security of IoT. These threats may steal important information that causes economic and reputational damages. In this paper, we have proposed a combined deep learning approach to detect the pirated software and malware-infected files across the IoT network. The TensorFlow deep neural network is proposed to identify pirated software using source code plagiarism. The tokenization and weighting feature methods are used to filter the noisy data and further, to zoom the importance of each token in terms of source code plagiarism. Then, the deep learning approach is used to detect source code plagiarism. The dataset is collected from Google Code Jam (GCJ) to investigate software piracy. Apart from this, the deep convolutional neural network is used to detect malicious infections in IoT network through color image visualization. The malware samples are obtained from Maling dataset for experimentation. The experimental results indicate that the classification performance of the proposed solution to measure the cybersecurity threats in IoT are better than the state of the art methods.
2019
124379-124389
journalArticle
7
IEEE Access
DOI 10.1109/ACCESS.2019.2901218
IEEE Access
ISSN 2169-3536
H. Zia
N. R. Harris
G. V. Merrett
M. Rivers
Data models
Biological system modeling
wireless sensor networks
Wireless sensor networks
Computational modeling
Predictive models
machine learning
Soil
Mathematical model
Environmental modeling
M5 decision tree
nitrate loss prediction modeling
water quality management
A Low-Complexity Machine Learning Nitrate Loss Predictive Model–Towards Proactive Farm Management in a Networked Catchment
With the advent of wireless sensor networks, the ability to predict nutrient-rich discharges, using on-node prediction models, offers huge potential for enabling real-time water reuse and management within an agriculturally dominated catchment. Existing discharge models use multiple parameters and large historical data which are difficult to extract and this, coupled with constraints on network nodes (battery life, computing power, and sensor availability), makes it necessary to develop low-dimensional models. This paper investigates a data-driven model for predicting daily total oxidized nitrate fluxes and reduces the number of model parameters used to 5-a reduction of at least 50%. Trained on only a 12-month training dataset derived from the published measured data, results for the model generated using an M5 decision tree, giving an R2 of 0.92 and a relative root-mean-square error of 26%. The 80% of the residuals for test data falls within +/-0.05 Kgůha-1ůday-1 error range, which is minimal, offering an improvement over results obtained by the contemporary research.
2019
26707-26720
journalArticle
13
IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
DOI 10.1109/JSTARS.2020.2971061
IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
ISSN 2151-1535
M. Torre
B. Remeseiro
P. Radeva
F. Martinez
Deep learning
Training
image segmentation
Image segmentation
Image edge detection
Detectors
Clustering algorithms
Radiometry
Agricultural fields
image edge analysis
region extraction
DeepNEM: Deep Network Energy-Minimization for Agricultural Field Segmentation
One of the main characteristics of agricultural fields is that the appearance of different crops and their growth status, in an aerial image, is varied, and has a wide range of radiometric values and high level of variability. The extraction of these fields and their monitoring are activities that require a high level of human intervention. In this article, we propose a novel automatic algorithm, named deep network energy-minimization (DeepNEM), to extract agricultural fields in aerial images. The model-guided process selects the most relevant image clues extracted by a deep network, completes them and finally generates regions that represent the agricultural fields under a minimization scheme. DeepNEM has been tested over a broad range of fields in terms of size, shape, and content. Different measures were used to compare the DeepNEM with other methods, and to prove that it represents an improved approach to achieve a high-quality segmentation of agricultural fields. Furthermore, this article also presents a new public dataset composed of 1200 images with their parcels boundaries annotations.
2020
726-737
journalArticle
10
IEEE Access
DOI 10.1109/ACCESS.2022.3166515
IEEE Access
ISSN 2169-3536
M. A. Tamayo-Monsalve
E. Mercado-Ruiz
J. P. Villa-Pulgarin
M. A. Bravo-Ortíz
H. B. Arteaga-Arteaga
A. Mora-Rubio
J. A. Alzate-Grisales
D. Arias-Garzon
V. Romero-Cano
S. Orozco-Arias
G. Gustavo-Osorio
R. Tabares-Soto
Convolutional neural networks
multispectral images
deep learning
Image color analysis
convolutional neural network
data augmentation
Cameras
transfer learning
Transfer learning
Hyperspectral imaging
Lighting
Machine vision
Coffee maturity classification
Coffee Maturity Classification Using Convolutional Neural Networks and Transfer Learning
This work presents a framework for coffee maturity classification from multispectral image data based on Convolutional Neural Networks (CNNs). The system leverages the use of multispectral image acquisition systems that generate large amounts of data, by taking advantage of the ability of CNNs to extract meaningful patterns from very high-dimensional data. We validated the use of five different popular CNN architectures on the classification of cherry coffee fruits according to their ripening stage. The different models were trained on a training dataset balanced in different ways, which resulted in a top accuracy higher than 98% when applied to the classification of 600 coffee fruits in 5 different stages of ripening. This work has the potential of providing the farmer with a high-quality, optimized, accurate and viable method for classifying coffee fruits. In order to foster future research in this area, the data used in this work, which was acquired with a custom-developed multispectral image acquisition system, have been released.
2022
42971-42982
journalArticle
L. Falaschetti
L. Manoni
R. C. F. Rivera
D. Pau
G. Romanazzi
O. Silvestroni
V. Tomaselli
C. Turchetti
Monitoring
convolutional neural network
Diseases
Real-time systems
Convolution
Detectors
Pipelines
Image coding
tensor decomposition
embedded systems
Esca disease
Image detector
A Low-Cost, Low-Power and Real-Time Image Detector for Grape Leaf Esca Disease Based on a Compressed CNN
Esca is one of the most common grape leaf diseases that seriously affect grape yield, causing a loss of global production in the range of 20%–40%. Therefore, a timely and effective identification of the disease could help to develop an early treatment approach to control its spread while reducing economic losses. For this purpose the use of computer vision and machine learning techniques for recognizing plant diseases have been extensively studied in recent years. The aim of this paper is to propose an image detector based on a high-performance convolutional neural network (CNN) implemented in a low cost, low power platform, to monitor the Esca disease in real-time. To meet the severe constraints typical of an embedded system, a new low-rank CNN architecture (LR-Net) based on CANDECOMP/PARAFAC (CP) tensor decomposition has been developed. The compressed CNN network so obtained has been trained on a specific dataset and implemented in a low-power, low-cost Python programmable machine vision camera for real-time classification. An extensive experimentation has been conducted and the results achieved show the superiority of LR-Net with respect to the state-of-the-art networks both in terms of inference time and memory occupancy.
Sept. 2021
468-481
11
IEEE Journal on Emerging and Selected Topics in Circuits and Systems
DOI 10.1109/JETCAS.2021.3098454
3
IEEE Journal on Emerging and Selected Topics in Circuits and Systems
ISSN 2156-3365
journalArticle
10
IEEE Access
DOI 10.1109/ACCESS.2022.3187203
IEEE Access
ISSN 2169-3536
S. Ahmed
M. B. Hasan
T. Ahmed
M. R. K. Sony
M. H. Kabir
Crops
Feature extraction
Computer architecture
Diseases
data augmentation
transfer learning
Transfer learning
Computational modeling
Viruses (medical)
CLAHE
lightweight architecture
MobileNetV2
Less is More: Lighter and Faster Deep Neural Architecture for Tomato Leaf Disease Classification
To ensure global food security and the overall profit of stakeholders, the importance of correctly detecting and classifying plant diseases is paramount. In this connection, the emergence of deep learning-based image classification has introduced a substantial number of solutions. However, the applicability of these solutions in low-end devices requires fast, accurate, and computationally inexpensive systems. This work proposes a lightweight transfer learning-based approach for detecting diseases from tomato leaves. It utilizes an effective preprocessing method to enhance the leaf images with illumination correction for improved classification. Our system extracts features using a combined model consisting of a pretrained MobileNetV2 architecture and a classifier network for effective prediction. Traditional augmentation approaches are replaced by runtime augmentation to avoid data leakage and address the class imbalance issue. Evaluation on tomato leaf images from the PlantVillage dataset shows that the proposed architecture achieves 99.30% accuracy with a model size of 9.60MB and 4.87M floating-point operations, making it a suitable choice for low-end devices. Our codes and models are available at https://github.com/redwankarimsony/project-tomato.
2022
68868-68884
journalArticle
7
IEEE Access
DOI 10.1109/ACCESS.2019.2923765
IEEE Access
ISSN 2169-3536
W. Bouachir
K. E. Ihou
H. -E. Gueziri
N. Bouguila
N. Bélanger
Feature extraction
computer vision
Computer vision
artificial intelligence
Training
Forestry
Image segmentation
Unmanned aerial vehicles
Proposals
Precision forestry
UAV imagery
Computer Vision System for Automatic Counting of Planting Microsites Using UAV Imagery
Mechanical site preparation by mounding is often used by the forest industry to provide optimal growth conditions for tree seedlings. Prior to planting, an essential step consists in estimating the number of mounds at each planting block, which serves as planting microsites. This task often requires long and costly field surveys, implying several forestry workers to perform manual counting procedure. This paper addresses the problem of automating the counting process using computer vision and UAV imagery. We present a supervised detection-based counting framework for estimating the number of planting microsites on a mechanically prepared block. The system is trained offline to learn feature representations from semi-automatically annotated images. Mound detection and counting are then performed on multispectral UAV images captured at an altitude of 100 m. Our detection framework proceeds by generating region proposals based on local binary patterns (LBP) features extracted from near-infrared (NIR) patches. A convolutional neural network (CNN) is then used for classifying candidate regions by considering multispectral image data. To train and evaluate the proposed method, we constructed a new dataset by capturing aerial images from different planting blocks. The results demonstrate the efficiency and validity of the proposed method under challenging experimental conditions. The methods and results presented in this paper form a promising cornerstone to develop advanced decision support systems for planning planting operations.
2019
82491-82500
journalArticle
8
IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
DOI 10.1109/JSTARS.2015.2424292
5
IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
ISSN 2151-1535
K. Taşdemir
Y. Moazzen
I. Yildirim
Image color analysis
Remote sensing
Quantization (signal)
Spatial resolution
Accuracy
Soil
Topology
Approximate spectral clustering (SC)
cluster ensemble
clustering
geodesic similarity
land-cover identification
An Approximate Spectral Clustering Ensemble for High Spatial Resolution Remote-Sensing Images
Unsupervised clustering of high spatial resolution remote-sensing images plays a significant role in detailed land-cover identification, especially for agricultural and environmental monitoring. A recently promising method is approximate spectral clustering (SC) which enables spectral partitioning for large datasets to extract clusters with distinct characteristics without a parametric model. It also facilitates the use of various information types via advanced similarity criteria. However, it requires an empirical selection of a similarity criterion optimal for the corresponding application. To address this challenge, we propose an approximate SC ensemble (ASCE2) which fuses partitionings obtained by different similarity representations. Contrary to existing spectral ensembles for remote-sensing applications, the proposed ASCE2 employs neural gas quantization instead of random sampling, advanced similarity criteria instead of traditional distance-based Gaussian kernel with different decay parameters, and a two-level ensemble. We evaluate the proposed ASCE2 with three measures (accuracy, adjusted Rand index, and normalized mutual information) using five remote-sensing images, two of which are commonly available. We apply the ASCE2 in two applications for agricultural monitoring: 1) land-cover identification to determine orchard fields using a WorldView-2 image (0.5-m spatial resolution) and 2) finding lands in good agricultural condition using multitemporal RapidEye images (5-m spatial resolution). Experimental results indicate a significant betterment of the resulting partitionings obtained by the proposed ensemble, with respect to the evaluation measures in these applications.
May 2015
1996-2004
journalArticle
14
IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
DOI 10.1109/JSTARS.2020.3040284
IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
ISSN 2151-1535
M. Vallejo Orti
L. Winiwarter
E. Corral-Pazos-de-Provens
J. G. Williams
O. Bubenzer
B. Höfle
Agriculture
Random forests
Vegetation mapping
Soil
Training data
Three-dimensional displays
random forest (RF)
Arid regions
automatic classification
Degradation
gully erosion
iterative learning
land degradation
Namibia
soil erosion mapping
Use of TanDEM-X and Sentinel Products to Derive Gully Activity Maps in Kunene Region (Namibia) Based on Automatic Iterative Random Forest Approach
Gullies are landforms with specific patterns of shape, topography, hydrology, vegetation, and soil characteristics. Remote sensing products (TanDEM-X, Sentinel-1, and Sentinel-2) serve as inputs into an iterative algorithm, initialized using a micro-mapping simulation as training data, to map gullies in the northwestern of Namibia. A Random Forest Classifier examines pixels with similar characteristics in a pool of unlabeled data, and gully objects are detected where high densities of gully pixels are enclosed by an alpha shape. Gully objects are used in subsequent iterations following a mechanism where the algorithm uses the most reliable pixels as gully training samples. The gully class continuously grows until an optimal scenario in terms of accuracy is achieved. Results are benchmarked with manually tagged gullies (initial gully labeled area <; 0.3% of the total study area) in two different watersheds (408 and 302 km2, respectively) yielding total accuracies of >98%, with 60% in the gully class, Cohen Kappa >0.5, Matthews Correlation Coefficient >0.5, and receiver operating characteristic Area Under the Curve >0.89. Hence, our method outlines gullies keeping low false-positive rates while the classification quality has a good balance for the two classes (gully/no gully). Results show the most significant gully descriptors as the high temporal radar signal coherence (22.4%) and the low temporal variability in Normalized Difference Vegetation Index (21.8%). This research builds on previous studies to face the challenge of identifying and outlining gully-affected areas with a shortage of training data using global datasets, which are then transferable to other large (semi-) arid regions.
2021
607-623
journalArticle
24
IEEE Transactions on Multimedia
DOI 10.1109/TMM.2021.3073575
IEEE Transactions on Multimedia
ISSN 1941-0077
P. Dai
Y. Li
H. Zhang
J. Li
X. Cao
data augmentation
Training
Agriculture
Image segmentation
Shape
Training data
Proposals
Location awareness
accurate localization
arbitrary shape
global context
Scene text detection
text part
Accurate Scene Text Detection Via Scale-Aware Data Augmentation and Shape Similarity Constraint
Scene text detection has attracted increasing concerns with the rapid development of deep neural networks in recent years. However, existing scene text detectors may overfit on the public datasets due to the limited training data, or generate inaccurate localization for arbitrary-shape scene texts. This paper presents an arbitrary-shape scene text detection method that can achieve better generalization ability and more accurate localization. We first propose a Scale-Aware Data Augmentation (SADA) technique to increase the diversity of training samples. SADA considers the scale variations and local visual variations of scene texts, which can effectively relieve the dilemma of limited training data. At the same time, SADA can enrich the training minibatch, which contributes to accelerating the training process. Furthermore, a Shape Similarity Constraint (SSC) technique is exploited to model the global shape structure of arbitrary-shape scene texts and backgrounds from the perspective of the loss function. SSC encourages the segmentation of text or non-text in the candidate boxes to be similar to the corresponding ground truth, which is helpful to localize more accurate boundaries for arbitrary-shape scene texts. Extensive experiments have demonstrated the effectiveness of the proposed techniques, and state-of-the-art performances are achieved over public arbitrary-shape scene text benchmarks (e.g., CTW1500, Total-Text and ArT).
2022
1883-1895
journalArticle
10
IEEE Access
DOI 10.1109/ACCESS.2022.3206009
IEEE Access
ISSN 2169-3536
A. A. Khan
M. A. Nauman
R. N. Bashir
R. Jahangir
R. Alroobaea
A. Binmahfoudh
M. Alsafyani
C. Wechtaisong
Agriculture
Irrigation
Salinity (geophysical)
Internet of Things
Long short term memory
saline soil
ensembled LSTM
Evapotranspiration (ET)
evapotranspiration for saline soils (ETs)
FAO-56 Penman-Monteith
Leaching
leaching process
long short-term memory model (LSTM)
Soil measurement
Water conservation
Context Aware Evapotranspiration (ETs) for Saline Soils Reclamation
Accurate Evapotranspiration for saline soils (ETs) is important as well as challenging for the reclamation of saline soils through an effective leaching process. Evapotranspiration (ET) by FAO-56 Penman-Monteith standard method is complex, especially for saline soils. Moreover, existing studies focus on the use of the Internet of Things (IoT) and machine learning-enabled smart and precision irrigation water recommendation systems along with the ET estimation by limited parameters. The ETs for saline soils are also equally important for the reclamation of saline soils, which is ignored by the existing literature. The study proposed IoT and machine leaching-based architecture of context-aware monthly ETs estimations for saline soil reclamation with the effective leaching process. The IoT-enabled crop field contexts in terms of crop field temperature, soil salinity, and irrigation water salinity are used as input features to the Long Short-Term Memory (LSTM) and ensembled LSTM models for monthly ETs predictions. The performance of the proposed solution is observed in terms of the accuracy of the machine learning models along with the comparison against the FAO-56 PM-based standard method. The implementation of the proposed solution reveals that the ensembled LSTM-based approach for ETs is more accurate as compared to the LSTM model with accuracies of 92 and 90% for the training and validation datasets, respectively. The predictions made by the ensembled LSTM are more in line with the FAO-56 PM-based method with a Pearson correlation of 0.916 as compared to LSTM models. The implementation of the proposed solution in real-time environments reveals that the proposed solution is more effective in reducing the soil salinity as compared to the traditional method.
2022
110050-110063
journalArticle
9
IEEE Access
DOI 10.1109/ACCESS.2021.3088075
IEEE Access
ISSN 2169-3536
N. Mamdouh
A. Khattab
Feature extraction
Deep learning
Image color analysis
Insects
Agriculture
Classification algorithms
object detection
Image processing
integrated pest management
YOLO
YOLO-Based Deep Learning Framework for Olive Fruit Fly Detection and Counting
The olive fruit fly can damage up to 100% of the harvested fruit and can cause up to 80% reduction of the value of the resulting olive oil. Therefore, it is important to early detect its presence in the olive orchard to take the appropriate chemical or biological countermeasures as early as possible. Traps filled with attractant pheromones are typically deployed across the orchard to attract and capture the flies. Traditionally, the captured flies were manually counted which is error prone. Recently, the traps are employed with cameras and communication devices to send pictures of the captured flies to experts for analysis which is also error prone and inefficient. Consequently, machine and deep learning have been exploited to develop fully automated and accurate detection that does not include human in the loop. Such a learning problem is challenging due to the small size of the detected object, the differences in the light conditions at which pictures were taken, and the lack of enough data to train the learning model. In this paper, we present a deep learning framework for detecting and counting the number of olive fruit flies that exploits data augmentation to increase the dataset size, includes negative samples in the training to improve the detection accuracy, and normalizes the images to the color of the trap background, i.e., yellow, to unify the illumination conditions. The results of the proposed framework show a precision of 0.84, a recall of 0.97, an F1-score of 0.9 and mean Average Precision (mAP) of 96.68% which significantly outperforms existing pest detection systems.
2021
84252-84262
journalArticle
9
IEEE Access
DOI 10.1109/ACCESS.2021.3096895
IEEE Access
ISSN 2169-3536
A. Khattak
M. U. Asghar
U. Batool
M. Z. Asghar
H. Ullah
M. Al-Rakhami
A. Gumaei
Feature extraction
deep learning
Deep learning
Image color analysis
convolutional neural network
Diseases
Agriculture
Support vector machines
Neural networks
citrus fruit diseases detection
Citrus leaf diseases
Automatic Detection of Citrus Fruit and Leaves Diseases Using Deep Neural Network Model
Citrus fruit diseases are the major cause of extreme citrus fruit yield declines. As a result, designing an automated detection system for citrus plant diseases is important. Deep learning methods have recently obtained promising results in a number of artificial intelligence issues, leading us to apply them to the challenge of recognizing citrus fruit and leaf diseases. In this paper, an integrated approach is used to suggest a convolutional neural networks (CNNs) model. The proposed CNN model is intended to differentiate healthy fruits and leaves from fruits/leaves with common citrus diseases such as black spot, canker, scab, greening, and Melanose. The proposed CNN model extracts complementary discriminative features by integrating multiple layers. The CNN model was checked against many state-of-the-art deep learning models on the Citrus and PlantVillage datasets. According to the experimental results, the CNN Model outperforms the competitors in a variety of measurement metrics. The CNN Model has a test accuracy of 94.55 percent, making it a valuable decision support tool for farmers looking to classify citrus fruit/leaf diseases.
2021
112942-112954
journalArticle
30
IEEE Transactions on Image Processing
DOI 10.1109/TIP.2021.3076272
IEEE Transactions on Image Processing
ISSN 1941-0042
S. Yao
X. Han
H. Zhang
X. Wang
X. Cao
Feature extraction
Training
Agriculture
Task analysis
Visualization
Target tracking
dynamic template-candidate matching
Lucas-Kanade algorithm
object tracking
Object tracking
Siamese network
Learning Deep Lucas-Kanade Siamese Network for Visual Tracking
In most recent years, Siamese trackers have drawn great attention because of their well-balanced accuracy and efficiency. Although these approaches have achieved great success, the discriminative power of the conventional Siamese trackers is still limited by the insufficient template-candidate representation. Most of the existing approaches take non-aligned features to learn a similarity function for template-candidate matching, while the target object's geometrical transformation is seldom explored. To address this problem, we propose a novel Siamese tracking framework, which enables to dynamically transform the template-candidate features to a more discriminative viewpoint for similarity matching. Specifically, we reformulate the template-candidate matching problem of the conventional Siamese tracker from the perspective of Lucas-Kanade (LK) image alignment approach. A Lucas-Kanade network (LKNet) is proposed and incorporated to the Siamese architecture to learn aligned feature representations in data-driven trainable manner, which is able to enhance the model adaptability in challenging scenarios. Within this framework, we propose two Siamese trackers named LK-Siam and LK-SiamRPN to validate the effectiveness. Extensive experiments conducted on the prevalent datasets show that the proposed method is more competitive over a number of state-of-the-art methods.
2021
4814-4827
journalArticle
19
IEEE Geoscience and Remote Sensing Letters
DOI 10.1109/LGRS.2021.3085139
IEEE Geoscience and Remote Sensing Letters
ISSN 1558-0571
M. L. Mekhalfi
C. Nicolò
Y. Bazi
M. M. A. Rahhal
N. A. Alsharif
E. A. Maghayreh
Object detection
Training
Agriculture
Indexes
Computer science
object detection
Detectors
precision farming
Internet
YOLOv5
Aerial imagery
crop circles
detection transformers (DETRs)
efficientDet
Contrasting YOLOv5, Transformer, and EfficientDet Detectors for Crop Circle Detection in Desert
Ongoing discoveries of water reserves have fostered an increasing adoption of crop circles in the desert in several countries. Automatically quantifying and surveying the layout of crop circles in remote areas can be of great use for stakeholders in managing the expansion of the farming land. This letter compares latest deep learning models for crop circle detection and counting, namely Detection Transformers, EfficientDet and YOLOv5 are evaluated. To this end, we build two datasets, via Google Earth Pro, corresponding to two large crop circle hot spots in Egypt and Saudi Arabia. The images were drawn at an altitude of 20 km above the targets. The models are assessed in within-domain and cross-domain scenarios, and yielded plausible detection potential and inference response.
2022
1-5
journalArticle
10
IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
DOI 10.1109/JSTARS.2016.2606514
1
IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
ISSN 2151-1535
A. Ertürk
M. -D. Iordache
A. Plaza
Agriculture
Earth
Hyperspectral imaging
Libraries
hyperspectral imaging
Dictionaries
Change detection
dictionary pruning
multitemporal
sparse unmixing
Sparse Unmixing With Dictionary Pruning for Hyperspectral Change Detection
The localization of changes that occur between the images in a multitemporal series is crucial for many applications, ranging from environmental monitoring to military surveillance. In contrast to traditional change detection methods, unmixing-based change detection has been shown to have the important added benefit of providing subpixel-level information on the nature of the changes, instead of only providing the location of the changes. Recently, sparse unmixing has also been introduced to hyperspectral change detection, resulting in a method that circumvents the drawbacks of regular spectral unmixing approaches. Sparse unmixing-based change detection reveals the changes that occur in a multitemporal series, at subpixel level, and in terms of the library spectra and their sparse abundances, and provides enhanced change detection performance, especially when subpixel-level changes have occurred. However, sparse unmixing is generally an ill-conditioned and time-consuming process, especially as the size of the utilized spectral library increases. In this paper, dictionary pruning is exploited for the first time for hyperspectral change detection using sparse unmixing, in order to alleviate the ill-conditioning of the problem and achieve decreased computation times and enhanced change detection performance. Experimental results on both realistic synthetic and real datasets are used to validate the proposed approach.
Jan. 2017
321-330
journalArticle
21
IEEE Transactions on Multimedia
DOI 10.1109/TMM.2018.2875357
5
IEEE Transactions on Multimedia
ISSN 1941-0077
C. Cui
H. Liu
T. Lian
L. Nie
L. Zhu
Y. Yin
Feature extraction
Agriculture
Task analysis
Visualization
Semantics
Entropy
Image recognition
fully convolutional networks
Image aesthetics assessment
label distribution learning
semantic fusion
Distribution-Oriented Aesthetics Assessment With Semantic-Aware Hybrid Network
Image aesthetics assessment has emerged as a hot topic in recent years due to its potential in numerous high-level vision applications. In this paper, distinguished from existing studies relying on a single label, we propose quantifying image aesthetics by a distribution over multiple quality levels. The distribution-based representation characterizes the disagreement among users' aesthetic preferences regarding the same image, and is also compatible with the traditional task of aesthetic label prediction. Our framework is developed based on fully convolutional networks and enables inputs of varying sizes. In this way, we circumvent the fixed-size constraint of prevalent convolutional neural networks, and avoid the risk of impairing the intrinsic aesthetic appeal of images. Moreover, given the fact that aesthetic perceiving is coupled with semantic understanding, we present a novel semantic-aware hybrid NEtwork (SANE), which harvests the information from object categorization and scene recognition to enhance image aesthetics assessment. Experiments on two benchmark datasets have well verified the effectiveness of our approach in both scenarios of aesthetic distribution prediction and aesthetic label prediction, and highlighted the benefits of input preserving as well as semantic understanding for images.
May 2019
1209-1220
journalArticle
10
IEEE Access
DOI 10.1109/ACCESS.2022.3213319
IEEE Access
ISSN 2169-3536
Z. Lu
Q. Yu
X. Li
X. Li
A. Qiangwang
Deep learning
Predictive models
Embedded systems
link prediction
Social networking (online)
graph attention
graph neural networks
Graph neural networks
Link aggregation
Network embedding
signed network
Symbols
Signed Network Node Embedding via Dual Attention Mechanism
In signed networks, GNNs are used to get node embedding by aggregating node neighbor information. Most of the existing methods aggregate neighbor information from the node level, and the different paths between nodes and neighbors will also affect node embedding. The target node and its neighbors have different link positive,negative signs and link directions, which together constitute different paths.These different paths have different contributions to the target node.Based on the structural balance theory and status theory, this paper divides the different paths between nodes and their neighbors into 20 kinds of motifs, which are using to capture the different effects of paths on target nodes. Comprehensive consideration at the node level and path level, SNEDA (Signed Network Embedding via dual attention Mechanism) is proposed based on the graph attention Network. The model has two attention mechanisms: node-level attention captures different influences between nodes at the node level; path-level attention captures the different influences between motifs at the path level. The final vector representation of nodes is obtained by aggregating neighbor information selectively based on important motifs, and the vector representation is applied to link prediction. Experiments on four real social network data sets show that the network representation obtained by the model can improve the accuracy of link prediction. Experimental results demonstrate the effectiveness of the proposed framework through a signed link prediction task on four real-world signed network datasets.
2022
108641-108650
journalArticle
8
IEEE Access
DOI 10.1109/ACCESS.2020.2982456
IEEE Access
ISSN 2169-3536
Y. Zhang
C. Song
D. Zhang
Feature extraction
Diseases
Object detection
Agriculture
Clustering algorithms
deep residual network
disease diagnosis
disease recognition
Faster RCNN
K-means clustering
Deep Learning-Based Object Detection Improvement for Tomato Disease
To improve the recognition model accuracy of crop disease leaves and locating diseased leaves, this paper proposes an improved Faster RCNN to detect healthy tomato leaves and four diseases: powdery mildew, blight, leaf mold fungus and ToMV. First, we use a depth residual network to replace VGG16 for image feature extraction so we can obtain deeper disease features. Second, the k-means clustering algorithm is used to cluster the bounding boxes. We improve the anchoring according to the clustering results. The improved anchor frame tends toward the real bounding box of the dataset. Finally, we carry out a k-means experiment with three kinds of different feature extraction networks. The experimental results show that the improved method for crop leaf disease detection had 2.71% higher recognition accuracy and a faster detection speed than the original Faster RCNN.
2020
56607-56614
journalArticle
10
IEEE Access
DOI 10.1109/ACCESS.2022.3224594
IEEE Access
ISSN 2169-3536
M. Wang
K. Li
X. Zhu
Y. Zhao
Feature extraction
Image segmentation
Image edge detection
attention mechanism
YOLOv5
adaptive spatial feature fusion
rail surface defect
Rail transportation
Surface morphology
Detection of Surface Defects on Railway Tracks Based on Deep Learning
The detection of rail surface defects is very important in railway transportation. However, the edge defects on both sides of the rail and the multi-scale variation between different types of defects both pose challenges to the detection of rail surface defects. In order to solve the above problems, this paper proposes a novel rail surface defect detection network, YOLOv5s-VF. First, we design a sharpening functional attention mechanism (V-CBAM) that contains two key components: adaptive channel attention (F-CAM) and sharpened spatial attention (SSA). In F-CAM, we use one-dimensional convolution with adaptive convolution kernels for cross-channel connections, which reduces the number of parameters of the attention mechanism without affecting its performance. In SSA, we design a sharpening filter suitable for spatial attention, which is used to enhance the attention to the edge position defects of railway tracks and enhance the detection effect of the network on edge defects. Second, we construct a microscale adaptive spatial feature fusion (M-ASFF), which adds a high-resolution feature extraction layer to enhance the details of the underlying features of tiny defects. At the same time, in order to prevent the loss of detailed information and the excessive increase of the parameters of the model, the low-resolution feature layer is removed. Combined with adaptive spatial feature fusion, it can prevent the semantic conflict caused by the fusion of features at different scales. Finally, given the lack of labeled public rail surface defect datasets, this paper is based on the collection of real rail images and manually labels defects to train an object detection network and open source it. The experimental results show that YOLOv5s-VF outperforms the existing rail surface defect detection methods with a detection accuracy of 93.5% and a detection speed of 114.9 fps.
2022
126451-126465
journalArticle
19
IEEE Geoscience and Remote Sensing Letters
DOI 10.1109/LGRS.2022.3192832
IEEE Geoscience and Remote Sensing Letters
ISSN 1558-0571
R. Chen
L. Guanghui
C. Dai
Feature extraction
Training
Hyperspectral imaging
Convolution
Aggregates
Feature fusion
Geoscience and remote sensing
graph convolutional network (GCN)
hyperspectral image (HSI) classification
Ions
residual learning
Feature Fusion via Deep Residual Graph Convolutional Network for Hyperspectral Image Classification
Recently, graph convolutional network (GCN) has been applied for hyperspectral image (HSI) classification and obtained better performance. The main issue in HSI classification is that the high-resolution HSI contains more complex spectral–spatial structure information. However, the previous GCN-based methods applied in HSI classification only adopted a shallow GCN layer and they cannot extract the deeper discriminative features. In addition, these methods ignored the complementary and correlated information among multiorder neighboring information extracted by multiple GCN layers. In this letter, a novel feature fusion via deep residual GCN is proposed to explore the internal relationship among HSI data. On the one hand, benefiting from residual learning to alleviate the over-smoothing problem, we can construct deep GCN layers to excavate deeper abstract features of HSI. On the other hand, we fuse the outputs of different GCN layers, and thus, the local structural information within multiorder neighborhood nodes can be fully utilized. Extensive experiments on four real HSI datasets, including Indian Pines, Pavia University, Salinas, and Houston University, demonstrate the superiority of the proposed method compared with other state-of-the-art methods in various evaluation criteria.
2022
1-5
journalArticle
7
IEEE Robotics and Automation Letters
DOI 10.1109/LRA.2022.3199026
4
IEEE Robotics and Automation Letters
ISSN 2377-3766
S. de Jong
H. Baja
K. Tamminga
J. Valente
Feature extraction
Object detection
Training
Task analysis
object detection
Three-dimensional displays
Agricultural automation
Annotations
segmentation and categorization
robotics and automation in agriculture and forestry
deep learning methods
Wearable sensors
APPLE MOTS: Detection, Segmentation and Tracking of Homogeneous Objects Using MOTS
Current multi object tracking and segmentation (MOTS) methods made great progress for the simultaneous detection and tracking of heterogeneous objects like cars and pedestrians. Nevertheless, all of these scenes consisted of dissimilar objects, which are easier to track than homogeneous and smaller objects, as those are more similar in appearance. Therefore, this is the first paper that explores the implementation of MOTS algorithms for the simultaneous detection and tracking of homogeneous objects. Towards this end, video data was acquired in an apple orchard using a wearable camera and unmanned aerial vehicles (UAV). The dataset, called APPLE MOTS, contains almost 86000 manually annotated apple masks and is the first public dataset in which apple instances are temporally consistent labelled across frames. Implementation of the MOTS architectures called TrackR-CNN and PointTrack indicates that they could be suitable for the joint detection (MOTSP: 80.4) and tracking (sMOTSA: 38.7, MOTSA: 52.9) of apples. This letter exposes the challenge of tracking homogeneous objects due to their similar shape and colour while detection performance remains state-of-the-art.
Oct. 2022
11418-11425
journalArticle
10
IEEE Access
DOI 10.1109/ACCESS.2022.3185753
IEEE Access
ISSN 2169-3536
N. A. Ubina
S. -C. Cheng
C. -C. Chang
S. -Y. Cai
H. -Y. Lan
H. -Y. Lu
Cameras
Image segmentation
Semantics
Three-dimensional displays
Costs
Measurement
Convolutional neural network
object tracking
Fish
object-based stereo matching
Intelligent Underwater Stereo Camera Design for Fish Metric Estimation Using Reliable Object Matching
Precise fish metric estimation is essential in providing intelligent aquaculture farm decisions. Stereo vision has been widely used for size estimation. Still, many factors affect fish metrics accuracy using a low-cost underwater stereo camera, such as distance, ambient lighting, water velocity, and turbidity. Although such a system is affordable and energy-efficient, they are less accurate in estimating depths than its active counterparts. Since power source is always a problem in offshore aquaculture sites, energy-efficient devices are important. To deal with the accuracy problems of the camera, we propose an effective deep-learning-based object matching to optimize the fish metric estimation. In terms of the challenges of the underwater environment, an analysis of the accuracy of the fish 3D position calculation in the aquaculture cage based on the captured stereo camera images is performed. The analysis assumes a known geometrical configuration of the rectified camera system. The critical factor limiting the 3D fish metric estimation accuracy is the resolution of the computed depth maps of fish. An object-based matching is proposed for underwater fish tracking and depth computing to address this issue using reliable convolutional neural networks (CNNs). For each stereo video frame, an object classification and instance segmentation CNN separates the fish objects from their background. The fish objects are then cropped and matched using sub-pixel disparity computation of the video interpolation CNN. The calculated fish disparities and depth values are used for fish metric estimations. We also tracked each fish and computed the metrics across frames. The median metrics are calculated as the final result to reduce the noises introduced by the different gestures of the fish. Furthermore, underwater stereo video datasets with the actual metrics of sampled fish measured by humans are also constructed to verify the effectiveness of our approach. Our proposed method has less than a 5% error rate for fish length estimation.
2022
74605-74619
journalArticle
8
IEEE Access
DOI 10.1109/ACCESS.2020.3024948
IEEE Access
ISSN 2169-3536
J. Chen
Q. Mao
L. Xue
Feature extraction
convolutional neural network
Training
Machine learning
Task analysis
Visualization
Uncertainty
Sentiment analysis
active learning
texture information
Visual sentiment analysis
Visual Sentiment Analysis With Active Learning
Visual Sentiment Analysis (VSA) has attracted wide attention since more and more people are willing to express their emotion and opinions via visual contents on social media. Meanwhile, extensive datasets drive the rapid development of deep neural networks for this task. However, the annotation of large-scale datasets is very expensive and time consuming. In this paper, we propose a novel active learning framework, which uses few labeled training samples to achieve an effective sentiment analysis model. First, we attach a new branch to the traditional Convolution Neural Network (CNN), which is named ”texture module”. The affective vector will be obtained by computing inner products of feature maps from different convolutional blocks in this branch. We will utilize this vector to distinguish affective images. Second, the query strategy is formed by the classification scores from both the traditional CNN and the texture module. Then, we can use samples obtained by utilizing the query strategy to train our model. Extensive experiments on four public affective datasets show that our approach uses few labeled training samples to achieve promising results for VSA.
2020
185899-185908
journalArticle
10
IEEE Access
DOI 10.1109/ACCESS.2021.3137175
IEEE Access
ISSN 2169-3536
K. Nimmy
S. Sankaran
K. Achuthan
P. Calyam
Security
Internet of Things
Protocols
Logic gates
Cryptography
Authentication
Authentication protocol
geometric secret sharing
Passwords
PRNU
protocol resiliency
Resilience
smart home
Smart homes
Lightweight and Privacy-Preserving Remote User Authentication for Smart Homes
The rapid proliferation of embedded devices has led to the growth of the Internet of Things (IoT) with applications in numerous domains such as home automation, healthcare, education and agriculture. However, many of the connected devices particularly in smart homes are the target of attacks that try to exploit security vulnerabilities such as hard-coded passwords and insecure data transfer. Recent studies show that there is a considerable surge in the number of phishing attacks targeting smart homes during the COVID-19 pandemic. Moreover, many of the existing user authentication protocols in the literature incur additional computational overhead and need to be made more resilient to smart home targeted attacks. In this paper, we propose a novel lightweight and privacy-preserving remote user authentication protocol for securing smart home applications. Our approach is based on Photo Response Non-Uniformity (PRNU) to make our protocol resilient to smart home attacks such as smartphone capture attacks and phishing attacks. In addition, the lightweight nature of our solution is suitable for deployment on heterogeneous and resource constrained IoT devices. Besides, we leverage geometric secret sharing for establishing mutual authentication among the participating entities. We validate the security of the proposed protocol using the AVISPA formal verification tool and prototype it on a Raspberry Pi to analyze the power consumption. Finally, a comparison with existing schemes reveals that our scheme incurs a 20% reduction in communication overhead on smart devices. Furthermore, our proposed scheme is usable as it absolves users from memorizing passwords and carrying smart cards.
2022
176-190
journalArticle
16
IEEE Journal of Selected Topics in Signal Processing
DOI 10.1109/JSTSP.2022.3200911
6
IEEE Journal of Selected Topics in Signal Processing
ISSN 1941-0484
E. Tzinis
Y. Adi
V. K. Ithapu
B. Xu
P. Smaragdis
A. Kumar
Training
Noise measurement
Self-supervised learning
Recording
semi-supervised self-training
speech enhancement
Speech enhancement
zero-shot domain adaptation
RemixIT: Continual Self-Training of Speech Enhancement Models via Bootstrapped Remixing
We present RemixIT, a simple yet effective self-supervised method for training speech enhancement without the need of a single isolated in-domain speech nor a noise waveform. Our approach overcomes limitations of previous methods which make them dependent on clean in-domain target signals and thus, sensitive to any domain mismatch between train and test samples. RemixIT is based on a continuous self-training scheme in which a pre-trained teacher model on out-of-domain data infers estimated pseudo-target signals for in-domain mixtures. Then, by permuting the estimated clean and noise signals and remixing them together, we generate a new set of bootstrapped mixtures and corresponding pseudo-targets which are used to train the student network. Vice-versa, the teacher periodically refines its estimates using the updated parameters of the latest student models. Experimental results on multiple speech enhancement datasets and tasks not only show the superiority of our method over prior approaches but also showcase that RemixIT can be combined with any separation model as well as be applied towards any semi-supervised and unsupervised domain adaptation task. Our analysis, paired with empirical evidence, sheds light on the inside functioning of our self-training scheme wherein the student model keeps obtaining better performance while observing severely degraded pseudo-targets.
Oct. 2022
1329-1341
journalArticle
9
IEEE Access
DOI 10.1109/ACCESS.2021.3120092
IEEE Access
ISSN 2169-3536
S. Yoa
J. Park
H. J. Kim
computer vision
deep learning
Training
Task analysis
machine learning
Optimization
Kernel
Pose estimation
Measurement
Loss measurement
Learning loss
Learning Non-Parametric Surrogate Losses With Correlated Gradients
Training models by minimizing surrogate loss functions with gradient-based algorithms is a standard approach in various vision tasks. This strategy often leads to suboptimal solutions due to the gap between the target evaluation metrics and surrogate loss functions. In this paper, we propose a framework to learn a surrogate loss function that approximates the evaluation metric with correlated gradients. We observe that the correlated gradients significantly benefit the gradient-based algorithms to improve the quality of solutions. We verify the effectiveness of our method in various tasks such as multi-class classification, ordinal regression, and pose estimation with three evaluation metrics and five datasets. Our extensive experiments showed that our method outperforms conventional loss functions and surrogate loss learning methods.
2021
141199-141209
journalArticle
9
IEEE Access
DOI 10.1109/ACCESS.2021.3124050
IEEE Access
ISSN 2169-3536
H. Heo
D. Ko
J. Lee
Y. Hong
H. J. Kim
Convolution
Neural networks
Three-dimensional displays
Solid modeling
Linear programming
Perturbation methods
Action recognition
adversarial attack
safe AI
Search problems
sparse adversarial attack
video classification
Search-and-Attack: Temporally Sparse Adversarial Perturbations on Videos
Modern neural networks are known to be vulnerable to adversarial attacks in various domains. Although most attack methods usually densely change the input values, recent works have shown that deep neural networks (DNNs) are also vulnerable to sparse perturbations. Spatially sparse attacks on images or frames of a video are proven effective but the temporally sparse perturbations on videos have been less explored. In this paper, we present a novel framework to generate a temporally sparse adversarial attack, called Search-and-Attack scheme, on videos. The Search-and-Attack scheme first retrieves the most vulnerable frames and then attacks only those frames. Since identifying the most vulnerable set of frames involves an expensive combinatorial optimization problem, we introduce alternative definitions or surrogate objective functions: Magnitude of the Gradients (MoG) and Frame-wise Robustness Intensity (FRI). Combining them with iterative search schemes, extensive experiments on three public benchmark datasets (UCF, HMDB, and Kinetics) show that the proposed method achieves comparable performance to state-of-the-art dense attack methods.
2021
146938-146947
journalArticle
9
IEEE Access
DOI 10.1109/ACCESS.2021.3113934
IEEE Access
ISSN 2169-3536
S. Yoa
M. Jeon
Y. Oh
H. J. Kim
Deep learning
Training
Task analysis
machine learning
Neural networks
Standards
image classification
Loss measurement
meta-learning
Learning to Balance Local Losses via Meta-Learning
The standard training for deep neural networks relies on a global and fixed loss function. For more effective training, dynamic loss functions have been recently proposed. However, the dynamic global loss function is not flexible to differentially train layers in complex deep neural networks. In this paper, we propose a general framework that learns to adaptively train each layer of deep neural networks via meta-learning. Our framework leverages the local error signals from layers and identifies which layer needs to be trained more at every iteration. Also, the proposed method improves the local loss function with our minibatch-wise dropout and cross-validation loop to alleviate meta-overfitting. The experiments show that our method achieved competitive performance compared to state-of-the-art methods on popular benchmark datasets for image classification: CIFAR-10 and CIFAR-100. Surprisingly, our method enables training deep neural networks without skip-connections using dynamically weighted local loss functions.
2021
130834-130844
journalArticle
10
IEEE Access
DOI 10.1109/ACCESS.2022.3200037
IEEE Access
ISSN 2169-3536
L. Q. Nguyen
V. D. Pham
Y. Li
H. Wang
L. M. Dang
H. -K. Song
H. Moon
Convolutional neural networks
Feature extraction
Deep learning
Predictive models
Visualization
Solid modeling
Face recognition
Face alignment
graph convolutional network
heatmap
high resolution net
Facial Landmark Detection With Learnable Connectivity Graph Convolutional Network
The conventional heatmap regression with deep networks has become one of the mainstream approaches for landmark detection. Despite their success, these methods do not exploit the overall landmarks structure. We present a new landmark detection which is capable to capture the overall structure of landmarks by modeling these landmarks as a graph structure. Our method combines a deep heatmap regression network with Graph Convolutional Network (GCN) into an end-to-end differentiable model. The proposed method can utilize both visual information and overall landmarks structure to localize landmarks from an image. The ad hoc spatial relationships between landmarks are learned naturally with GCN network. Experiments on multiple datasets show the robustness of the proposed method.
2022
94354-94362
journalArticle
21
IEEE Sensors Journal
DOI 10.1109/JSEN.2021.3077272
17
IEEE Sensors Journal
ISSN 1558-1748
Z. Jiang
Y. Guo
K. Jiang
M. Hu
Z. Zhu
Feature extraction
Prediction algorithms
Visualization
Clustering algorithms
Robot kinematics
Data mining
Technological innovation
GhostNet
loss function
Plant cultivation
SE attention
yolov3
Optimization of Intelligent Plant Cultivation Robot System in Object Detection
Intelligent plant cultivation robot is an emerging device in the field of intelligent plant cultivation. The device can solve many problems that cannot be solved by Non-intelligent plant cultivation device in the past. Moreover, compared with other devices, intelligent plant cultivation robot is more convenient, low-cost and efficient. And in the process of intelligent robot plant breeding work, visual recognition is one of the most important step. In this paper, on the steps of using visual identification module in the traditional yolov3 visual identification algorithm is improved, in does not affect yolov3 visual identification algorithm under the condition of its running speed. In fact, due to its relatively low recognition accuracy, the high rate of error rate and empty selected situation, we have carried on corresponding optimizations and innovations such as,Attention mechanisim namely SE(squeeze and excitation) module, which can help the network to focus on more inportant fearture and enhancing the whole performance(higher accuracy, lower error rate) of the network. In addition, we changed the original backbone Darknet53 to GhostNet, which greatly reduced the parameters(also FLOPs) during the network inference and improved the precision to a certain extent. The loss function is optimized,namely the traditional IOU is changed into CIOU, which reduces the empty selection rate and improves recognition accuracy (2%). Experiments show that our method is better(better precision, recall, F1 and less inference time) than the original method both on the VOC dataset and our self-made plant dataset.
1 Sept.1, 2021
19279-19288
journalArticle
7
IEEE Access
DOI 10.1109/ACCESS.2019.2909522
IEEE Access
ISSN 2169-3536
L. Liu
R. Wang
C. Xie
P. Yang
F. Wang
S. Sudirman
W. Liu
Feature extraction
Deep learning
Computer architecture
convolutional neural network
Insects
Training
Task analysis
Proposals
Channel-spatial attention
multi-class pest detection
position-sensitive score map
region proposal network
PestNet: An End-to-End Deep Learning Approach for Large-Scale Multi-Class Pest Detection and Classification
Multi-class pest detection is one of the crucial components in pest management involving localization in addition to classification which is much more difficult than generic object detection because of the apparent differences among pest species. This paper proposes a region-based end-to-end approach named PestNet for large-scale multi-class pest detection and classification based on deep learning. PestNet consists of three major parts. First, a novel module channel-spatial attention (CSA) is proposed to be fused into the convolutional neural network (CNN) backbone for feature extraction and enhancement. The second one is called region proposal network (RPN) that is adopted for providing region proposals as potential pest positions based on extracted feature maps from images. Position-sensitive score map (PSSM), the third component, is used to replace fully connected (FC) layers for pest classification and bounding box regression. Furthermore, we apply contextual regions of interest (RoIs) as contextual information of pest features to improve detection accuracy. We evaluate PestNet on our newly collected large-scale pests' image dataset, Multi-class Pests Dataset 2018 (MPD2018) captured by our designed task-specific image acquisition equipment, covering more than 80k images with over 580k pests labeled by agricultural experts and categorized in 16 classes. The experimental results show that the proposed PestNet performs well on multi-class pest detection with 75.46% mean average precision (mAP), which outperforms the state-of-the-art methods.
2019
45301-45312
journalArticle
21
IEEE Sensors Journal
DOI 10.1109/JSEN.2020.3046575
6
IEEE Sensors Journal
ISSN 1558-1748
A. Abdella
I. Uysal
Monitoring
Temperature sensors
Wireless sensor networks
Time series analysis
Temperature distribution
Sensors
time-series analysis
Cold-chain
correlation and time-distance
sensory time-series data
Transportation
wireless sensors
Sense2Vec: Representation and Visualization of Multivariate Sensory Time Series Data
Processing multivariate sensory time-series with variable lengths is a challenging problem across different application domains due to the naturally complex, high-dimensional, and often non-stationary nature of the data. An excellent example can be found in the temperature-controlled transportation of goods where sensors could be placed in different locations along the supply chain and data could be coming from different shipments with different numbers of observations across time. In this paper, we propose a new approach (Sense2Vec) for processing variable-length sensory time-series data leveraging various similarity metrics between different time-series temperature profiles. The proposed algorithm is shown to be independent of the distance similarity measure (like dynamic time warping or Pearson's correlation coefficient) and provides better visualization and summarization of the multivariate raw time-series through representations that are robust to noise and outliers. Specifically, a moving clipping mechanism is used to create uniform sets of disjoint sensory recordings across multiple groups to calculate normalized similarity distances followed by a weighted fusion and concatenation to create a representative vector for each sensor group. The proposed algorithm is tested on a novel food transportation dataset which consists of temperature recordings from wireless sensor networks implemented on different shipments of perishable commodities across the United States. Graphical results show that the algorithm facilitates discovering similarities and discrepancies across the transportation process to find proper representations while reducing the time-series dimensionality for back-end applications.
15 March15, 2021
7972-7988
journalArticle
33
IEEE Transactions on Robotics
DOI 10.1109/TRO.2016.2597321
1
IEEE Transactions on Robotics
ISSN 1941-0468
C. Forster
L. Carlone
F. Dellaert
D. Scaramuzza
Estimation
Computer vision
Smoothing methods
Computational modeling
Optimization
Real-time systems
Manifolds
sensor fusion
Jacobian matrices
visual--inertial odometry (VIO)
On-Manifold Preintegration for Real-Time Visual--Inertial Odometry
Current approaches for visual-inertial odometry (VIO) are able to attain highly accurate state estimation via nonlinear optimization. However, real-time optimization quickly becomes infeasible as the trajectory grows over time; this problem is further emphasized by the fact that inertial measurements come at high rate, hence, leading to the fast growth of the number of variables in the optimization. In this paper, we address this issue by preintegrating inertial measurements between selected keyframes into single relative motion constraints. Our first contribution is a preintegration theory that properly addresses the manifold structure of the rotation group. We formally discuss the generative measurement model as well as the nature of the rotation noise and derive the expression for the maximum a posteriori state estimator. Our theoretical development enables the computation of all necessary Jacobians for the optimization and a posteriori bias correction in analytic form. The second contribution is to show that the preintegrated inertial measurement unit model can be seamlessly integrated into a visual-inertial pipeline under the unifying framework of factor graphs. This enables the application of incremental-smoothing algorithms and the use of a structureless model for visual measurements, which avoids optimizing over the 3-D points, further accelerating the computation. We perform an extensive evaluation of our monocular VIO pipeline on real and simulated datasets. The results confirm that our modeling effort leads to an accurate state estimation in real time, outperforming state-of-the-art approaches.
Feb. 2017
1-21
journalArticle
9
IEEE Access
DOI 10.1109/ACCESS.2021.3104537
IEEE Access
ISSN 2169-3536
E. Lasso
N. Motisi
J. Avelino
J. C. Corrales
Data models
Agriculture
Predictive models
Analytical models
Forecasting
Systematics
Knowledge based systems
smart farming
Crop pest forecasting
data-based model
knowledge-based model
FramePests: A Comprehensive Framework for Crop Pests Modeling and Forecasting
Crop pests are among the greatest threats to food security, generating broad economic, social, and environmental impacts. These pests interact with their hosts and the environment through complex pathways, and it is increasingly common to find professionals from different areas gathering into projects that attempt to deal with this complexity. We propose a framework called FramePests guiding steps and activities for crop pest modeling and forecasting. From theoretical references about carrying out mappings and systematic reviews of the literature, the framework proposes a series of steps leading to a state of science as a knowledge base for modeling tasks. Then, two modeling solutions, based on data and knowledge are used. Finally, the model outputs and performances are compared. The application of the proposed framework was demonstrated for coffee leaf rust modeling, for which we obtained a data-based model built using a gradient boosting algorithm (XGBoost) with a mean absolute error of 7.19% and a knowledge-based model represented by a hierarchical multi-criteria decision structure with an accuracy of 56.03%. A complementary study for our case study allowed us to explore how elements of a data-based model can improve a knowledge-based model, improving its accuracy by 7.07%. and showed that knowledge-based modeling can be an alternative to data-based modeling when the available dataset has approximately 60 instances. Data-based models tend to have better performance, but their replicability is conditioned by the diversity in the dataset used. Knowledge-based models may be simpler but allow expert supervision, and these models are not usually tied to specific sites.
2021
115579-115598
journalArticle
9
IEEE Access
DOI 10.1109/ACCESS.2021.3105903
IEEE Access
ISSN 2169-3536
G. O. Tetteh
A. Gocht
S. Erasmi
M. Schwieder
C. Conrad
remote sensing
Agriculture
Artificial satellites
Earth
image segmentation
Image segmentation
Remote sensing
Spatial resolution
Agricultural field delineation
band indices
essential agricultural variables
feature combination
Force
intersection over union
segmentation optimization
Evaluation of Sentinel-1 and Sentinel-2 Feature Sets for Delineating Agricultural Fields in Heterogeneous Landscapes
The Group on Earth Observations Global Agricultural Monitoring Initiative (GEOGLAM) considers agricultural fields as one of the essential variables that can be derived from satellite data. We evaluated the accuracy at which agricultural fields can be delineated from Sentinel-1 (S1) and Sentinel-2 (S2) images in different agricultural landscapes throughout the growing season. We used supervised segmentation based on the multiresolution segmentation (MRS) algorithm to first identify the optimal feature set from S1 and S2 images for field delineation. Based on this optimal feature set, we analyzed the segmentation accuracy of the fields delineated with increasing data availability between March and October of 2018. From the S1 feature sets, the combination of the two polarizations and two radar indices attained the best segmentation results. For S2, the best results were achieved using a combination of all bands (coastal aerosol, water vapor, and cirrus bands were excluded) and six spectral indices. Combining the radar and spectral indices further improved the results. Compared to the single-period dataset in March, using the dataset covering the whole season led to a significant increase in the segmentation accuracy. For very small fields (< 0.5 ha), the segmentation accuracy obtained was 27.02%, for small fields (0.5 – 1.5 ha), the accuracy was 57.65%, for medium fields (1.5 ha – 15 ha), the accuracy was 75.71%, and for large fields (>15 ha), the accuracy stood at 68.31%. As a use case, the segmentation result was used to aggregate and improve a pixel-based crop type map in Lower Saxony, Germany.
2021
116702-116719
journalArticle
8
IEEE Robotics and Automation Letters
DOI 10.1109/LRA.2023.3234744
2
IEEE Robotics and Automation Letters
ISSN 2377-3766
F. Ou
Y. Li
Z. Miao
Feature extraction
Robots
Task analysis
Three-dimensional displays
Laser radar
Location awareness
Attention score map
orchard robots
place recognition
Point cloud compression
spatial binary pattern (SBP)
Place Recognition of Large-Scale Unstructured Orchards With Attention Score Maps
The availability of autonomous orchard robots could alleviate the conflict caused by rising labor costs and labor shortages. The essential technical requirements are autonomous localization and mapping which rely on place recognition to explore data associations. This letter presents a novel LiDAR-based place recognition algorithm for unstructured and large-scale orchards. Concretely, we propose a discriminative global representation, spatial binary pattern (SBP), that encodes three-dimensional (3D) spatial distributed scan into an eight-bit binary pattern. In addition, an efficient two-stage hierarchical re-identification process is proposed. The attention score map is introduced for task-relevant features and preliminary candidates retrieval. The overlap re-identification is used to align a pair of descriptors to confirm the final loop closure index. Experiments on orchard and public datasets have been conducted to evaluate the performance of the proposed method, our method achieves a higher recall rate and localization accuracy. Moreover, experiments on the long-term outdoor dataset KITTI further demonstrate the generality.
Feb. 2023
958-965
journalArticle
1
IEEE Internet of Things Journal
DOI 10.1109/JIOT.2014.2346513
5
IEEE Internet of Things Journal
ISSN 2327-4662
D. Banerjee
B. Dong
M. Taghizadeh
S. Biswas
Wireless sensor networks
Wireless communication
privacy
Protocols
Internet of Things (IoT)
Resource management
Privacy
Computer security
Channel access
distributed slot allocation
Network security
Time division multiple access
trust domain
Ubiquitous computing
Privacy-Preserving Channel Access for Internet of Things
This paper presents a new way of providing privacy for Internet of Things (IoT) in a multi-trust-domain environment. The key idea is to develop a privacy-aware slotted channel access mechanism using which IoT nodes from multiple operators or trust domains can share wireless channel without mutually exposing their identities, thus alleviating threats from cross-trust-domain traffic analysis geared toward node-profiling, link layer topology estimation, node-tracking, and flow-tracking. The proposed scheme uses a novel zero-exposure slot allocation scheme in which packet transmission timing is the only information that is used for scheduling, collision detection, and collision resolution purposes. In addition to the proposed access scheme, this paper reports the design of a custom hardware unit for implementing the proposed protocol in a test-bed of sensors, emulating IoT networks. Presented results include functional validation and performance of the proposed channel access while preventing complete cross-trust-domain identity exposure.
Oct. 2014
430-445
journalArticle
10
IEEE Access
DOI 10.1109/ACCESS.2022.3159678
IEEE Access
ISSN 2169-3536
H. Amin
A. Darwish
A. E. Hassanien
M. Soliman
Convolutional neural networks
Feature extraction
deep learning
Deep learning
Diseases
Agriculture
Visualization
Tensors
feature fusion
plant disease
Colutional neural networks
deep features
End-to-End Deep Learning Model for Corn Leaf Disease Classification
Plant diseases compose a great threat to global food security. However, the rapid identification of plant diseases remains challenging and time-consuming. It requires experts to accurately identify if the plant is healthy or not and identify the type of infection. Deep learning techniques have recently been used to identify and diagnose diseased plants from digital images to help automate plant disease diagnosis and help non-experts identify diseased plants. While many deep learning applications have been used to identify diseased plants and aims to increase the detection rate, the limitation of the large parameter size in the models persist. In this paper, an end-to-end deep learning model is developed to identify healthy and unhealthy corn plant leaves while taking into consideration the number of parameters of the model. The proposed model utilizes two pre-trained convolutional neural networks (CNNs), EfficientNetB0, and DenseNet121, to extract deep features from the corn plant images.The deep features extracted from each CNN are then fused using the concatenation technique to produce a more complex feature set from which the model can learn better about the dataset. In this paper, data augmentation techniques were used to add variations to the images in the dataset used to train the model, increasing the variety and number of the images and enabling the model to learn more complex cases of the data. The obtained result of this work is compared with other pre-trained CNN models, namely ResNet152 and InceptionV3, which have a larger number of parameters than the proposed model and require more processing power. The proposed model is able to achieve a classification accuracy of 98.56% which shows the superiority of the proposed model over ResNet152 and InceptionV3 that achieved a classification accuracy of 98.37% and 96.26% respectively.
2022
31103-31115
journalArticle
8
IEEE Access
DOI 10.1109/ACCESS.2020.3014355
IEEE Access
ISSN 2169-3536
J. Zhou
R. Cao
J. Kang
K. Guo
Y. Xu
Data models
deep learning
Diseases
Machine learning
Labeling
Biomedical imaging
Semisupervised learning
active learning
biomedical engineering
High-quality data
Manuals
An Efficient High-Quality Medical Lesion Image Data Labeling Method Based on Active Learning
The rapid development of artificial intelligence has allowed deep learning technology to change our lives and has brought considerable convenience, but deep learning cannot succeed without a sufficient quantity and quality of data. In medical systems, due to the special nature of medical data resources, labeling and screening require professional input from doctors at considerable cost. However, if these data cannot be used effectively, then resources are wasted. To solve this problem, this paper proposes an effective high-quality medical lesion image data labeling method based on active learning, which labels the most representative and high-quality medical image data with artificial assistance. First, we generated subregions for all unlabeled images and predicted their classifications. Second, multifactor calculations were performed on all images. Finally, the values of multiple factors were used to sort all images, and the top-ranked images were selected and labeled with artificial assistance. The above steps were repeated until a suitable number of datasets had been labeled. The experimental results showed that a model trained on the labeled high-quality dataset could achieve the same quality as the model trained on all the data and save a considerable amount of time on manual labeling, which demonstrates the effectiveness of the method. The method ensures that the labeled data are valuable, high quality and rich in information to reduce the labeling workload and avoid wasting data resources.
2020
144331-144342
journalArticle
9
IEEE Access
DOI 10.1109/ACCESS.2020.3047839
IEEE Access
ISSN 2169-3536
Z. Jiang
X. Zhao
J. Zhou
Production
Companies
Investment
Technological innovation
Audit supervision
Finance
Government
Government subsidies
Research and development
shareholding supervision
tax & fee returns
Does the Supervision Mechanism Promote the Incentive Effects of Government Innovation Support on the R&D Input of Agricultural Enterprises?
The stimulating issues of government innovation support to the market players' R&D vitality has always been the focus of innovation. This article analyzes the impact of government innovation support's two policies, namely, government subsidies and tax & fee returns, on the R&D input of agricultural enterprises from the perspective of government intervention. Moreover, this article is primarily focusing on the institutional investors, leading shareholders, and social audit institutions in the corporate governance to play a role in the improvement of shareholding and audit supervision mechanism. This article conducts unbalanced panel data regression tests based on the relevant data of government innovation support of A-share agricultural enterprises listed in Shanghai and Shenzhen from 2009 to 2019. The conclusions are as follows: Firstly, government subsidies have a significant crowding-out effect on R&D investment of agricultural enterprises, while tax & fee returns have a significant stimulating effect. Secondly, when the shareholding ratio of institutional investors and leading shareholders increases, the shareholding supervision mechanism strengthens the effect of government innovation support on enterprise R&D input. Finally, with the improvement of social audit institutions' auditing opinions, the enhancement of auditing supervision mechanisms has weakened the effect of government innovation support on enterprise innovation investment. These research findings can provide some academic supports and policy references for formulating appropriate government innovation support and giving full play to the role of shareholding supervision and audit supervision in corporate governance.
2021
3339-3359
journalArticle
21
IEEE Sensors Journal
DOI 10.1109/JSEN.2020.3027587
3
IEEE Sensors Journal
ISSN 1558-1748
P. Das
S. Paul
S. S. Bhattacharya
P. Nath
Standards
Soil
Tools
spectroscopy
Optical sensors
Optical imaging
DVD
DVD grating
sensor
Smartphone
soil pH
Smartphone-Based Spectrometric Analyzer for Accurate Estimation of pH Value in Soil
This article demonstrates a cost-effective, compact, and handheld smartphone-based sensing tool for accurate estimation of pH values of agricultural farmlands. We develop a spectrometric tool with a resolution ability of 0.22 nm/pixel by utilizing 3D printing technology, regular optical components, a Digital Versatile Disc (DVD) as a grating element, and the rear camera of the phone. The sensor responses for standard pH samples within the pH range 4 to 10 are observed to be linear yet yield a sensitivity of 0.129 per pH unit. The resolution of the proposed sensor for the considered samples is observed to be 0.09 pH units. The results obtained from the designed tool while measuring the pH values of six field-collected soil samples are found to be accurate. The designed sensor's performance has been evaluated by comparing the experimental data with the commercial-grade pH sensing tool. With the advantages of being a low-weight and data-sharing ability, we envision that the proposed sensing scheme could emerge as a promising alternative platform for in-field estimation of pH values of soil and water resources of our environment.
1 Feb.1, 2021
2839-2845
journalArticle
7
IEEE Internet of Things Journal
DOI 10.1109/JIOT.2020.2982520
5
IEEE Internet of Things Journal
ISSN 2327-4662
C. X. Mavromoustakis
M. Mukherjee
G. Mastorakis
H. Song
M. Gorlatova
M. Aazam
Edge computing
Smart homes
Machine-to-machine communication
Smart cities
Smart devices
Special issues and sections
Guest Editorial Special Issue on Emerging Trends and Challenges in Fog Computing for IoT
With the emergence of the Internet of Things (IoT), billions of heterogeneous physical objects are connected through a network for collecting and sharing information, which can improve various aspects of daily lives, including smart living and transportation, and smart ambient environment, including smart city, smart home, smart agriculture, smart water, waste management, etc. The main objective of the IoT devices is to provide seamless services to the users without their intervention. The all-connected paradigm (i.e., connecting people, things, processes, and data in the network) is based on near Internet ubiquity and includes three types of communication: 1) machine-to-machine; 2) person-to-machine; and 3) person-to-person, and consists as the base for reliable services provision to the end devices at the edge. Fog paradigm implements effectively and efficiently the all-data requests to be shared in a reliable manner as fog implementations complement the cloud computing paradigm by extending computing and caching capabilities to the edges of the network, and it facilitates smart localization decisions and rapid responses. The wide range of IoT services calls for a disruptive, highly efficient, scalable, and flexible communication network able to cope with the increasing demands and the number of connected devices, as well as the diverse and stringent application requirements.
May 2020
4155-4159
journalArticle
13
IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
DOI 10.1109/JSTARS.2020.3044424
IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
ISSN 2151-1535
Soil moisture
Agriculture
Vegetation mapping
Nitrogen
Special issues and sections
Foreword to the Special Issue on Digital Innovations in Agriculture Research and Applications
The articles in this special section focus on the use of digital technology in agricultural research and applications. Sustainability of global agricultural and food systems is one of the prominent factors for peaceful future of the world in next few decades. Although agriculture is the main part of the global food supply chain, it is under rising pressure of global climate change, environmental deterioration, and falling per-capita arable land. Efficiency and sustainability management at all levels of agricultural planning and production appear as the most promising balancing factor for the short and medium terms. For this reason, timely and accurate information about the current conditions and future predictions in agriculture and the related resources become more important than ever. We are living in an age that the annual production number of transistors in microprocessors is more than the number of wheat grains produced in the same year. This is an indication of increasing data processing capability and decreasing cost. On the other hand, the number of Internet connected devices is estimated to be more than 20 billion now and is increasing rapidly, and Intent-of-Things (IoT) devices have the highest share in this rising trend. While it may be not able to solve long-term global food sustainability issue, the rapid increase in data collection and processing capabilities for agricultural monitoring and prediction may remediate the issue at least in short and middle terms.
2020
6519-6523
journalArticle
15
IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
DOI 10.1109/JSTARS.2022.3168485
IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
ISSN 2151-1535
A. Mahmood
L. Farhadi
Estimation
Soil moisture
Land surface temperature
Land surface
Hydraulic systems
Mathematical models
soil moisture (SM)
Effective soil hydraulic properties
evapotranspiration
Heating systems
Hydrus-1-D
recharge
variational data assimilation (VDA)
A Variational Framework for Coupled Estimation of Evapotranspiration and Recharge Fluxes by Assimilating Land Surface Soil Moisture and Temperature
The evapotranspiration and recharge are the key fluxes that link the land's water and energy cycles. These fluxes have major impacts on agriculture, water supply system, water resources planning, climate, etc. Accurate mapping of these fluxes is limited due to lack of in-situ observation sites and errors in estimation from numerical models. The dynamics of land surface state observations, specifically land surface soil moisture (SM) and temperature (LST), have implicit information on the partitioning of evapotranspiration and recharge fluxes, which provides an opportunity for global mapping of these fluxes across a range of spatial and temporal scales. In this study, a variational data assimilation (VDA) framework is developed for coupled estimation of evapotranspiration and recharge fluxes by assimilating LST and SM observations into a coupled water and energy balance model. We modified LIDA framework (Abdolghafoorian and Farhadi, 2019) to calculate the effective soil hydraulic parameters required for estimating the recharge flux in addition to evaporative flux parameters. Two numerical experiments are conducted using synthetic dataset generated by Hydrus 1-D model to test the accuracy and feasibility of the proposed estimation framework. Second-order information is used to estimate the uncertainty of the estimated parameters and fluxes and guide toward a well-posed optimization problem. Results demonstrate the success of the VDA framework in estimating evaporative and recharge fluxes from implicit information contained in SM and LST data and feasibility test results show promise in extending the framework to large scale using remotely sensed observations.
2022
3246-3257
journalArticle
13
IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
DOI 10.1109/JSTARS.2020.2984608
IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
ISSN 2151-1535
L. Liang
T. Huang
L. Di
D. Geng
J. Yan
S. Wang
L. Wang
L. Li
B. Chen
J. Kang
Data models
Vegetation
Remote sensing
Indexes
Vegetation mapping
leaf area index (LAI)
Sensitivity
Bandwidth
PROSAIL model
vegetation index
Influence of Different Bandwidths on LAI Estimation Using Vegetation Indices
Leaf area index (LAI) is a valuable indicator used in vegetation growth monitoring. To optimize the index selection according to the type of remote sensing data and to improve the inversion accuracy of LAI, this article analyzes the influence of different bandwidths on the accuracy of the inversion model based on vegetation indices. First, the simulation dataset is generated by the PROSAIL model, and on this basis, 15 vegetation indices with high correlation coefficients with LAI. Then, by analyzing the sensitivity of these 15 indices to the variations in bandwidth, and to the coefficient of determination (R2) of the LAI inversion model with the variations of bandwidth, the influence of different bandwidths on the accuracy of LAI estimation by each index is determined. The results show that bandwidth is one of the most important factors in determining the accuracy of LAI inversion, and the influence on different vegetation indices can be divided into the following three categories. First, narrowband vegetation index, the accuracy of inversion models built by vegetation indices decreases with the increase of bandwidth, including SR[800,680], OSAVI, MTVI2, SR[752,690], RDVI, NDCI, and NVI. Second, middleband vegetation index, the accuracy first increases and then decreases with the increase of bandwidth, including SR[700,670], Carte5, and SR[675,700]. Third, broadband vegetation index, the accuracy increases with the increase of bandwidth, including SPVI, Carte2, OSAVI2, MTVI1, and NDVI705. The study provides a scientific basis for vegetation index optimization in the process of LAI inversion.
2020
1494-1502
journalArticle
60
IEEE Transactions on Geoscience and Remote Sensing
DOI 10.1109/TGRS.2022.3203294
IEEE Transactions on Geoscience and Remote Sensing
ISSN 1558-0644
T. Gelvez-Barrera
H. Arguello
A. Foi
Image color analysis
Hyperspectral imaging
Spatial resolution
Indexes
Histograms
Colored noise
Human-robot interaction
Hyperspectral image-multispectral image (HSI-MSI) fusion
low-rank regularizations
nonlocal patch-based denoiser
plug-and-play with alternating direction method of multipliers (PnP-ADMM)
Joint Nonlocal, Spectral, and Similarity Low-Rank Priors for Hyperspectral–Multispectral Image Fusion
The fusion of a low-spatial-and-high-spectral resolution hyperspectral image (HSI) with a high-spatial-and-low-spectral resolution multispectral image (MSI) allows synthesizing a high-resolution image (HRI), supporting remote sensing applications, such as disaster management, material identification, and precision agriculture. Unlike existing variational methods using low-rank regularizations separately, we present an HSI-MSI fusion method promoting various low-rank regularizations jointly. Our method refines the HRI spatial and spectral correlations from the individual HSI and MSI data through the proper plug-and-play (PnP) of a nonlocal patch-based denoiser in the alternating direction method of multipliers (ADMM). Notably, we consider the nonlocal self-similarity, the spectral low-rank, and introduce a rank-one similarity prior. Furthermore, we demonstrate via an extensive empirical study that the rank-one similarity prior is an inherent characteristic of the HRI. Simulations over standard benchmark datasets show the effectiveness of the proposed HSI-MSI fusion outperforming state-of-the-art methods, particularly in recovering low-contrast areas.
2022
1-12
journalArticle
8
IEEE Access
DOI 10.1109/ACCESS.2020.2989138
IEEE Access
ISSN 2169-3536
H. Li
P. Tang
Monitoring
Remote sensing
Task analysis
Satellites
Databases
data integration
distributed system
Metadata
Multi-source data synergies
quantitative remote sensing
task parallelism
Dps-MuSyQ: A Distributed Parallel Processing System for Multi-Source Data Synergized Quantitative Remote Sensing Products Producing
With the development of earth observation technologies and the construction of earth observation systems, an increasing amount of remote sensing data are being obtained. These provide the datasets required for research on remote sensing monitoring across large areas. To compensate for the shortcomings of global and large-area temporal monitoring data, synergized computing using multi-source remote sensing data can improve the accuracy and temporal resolution of remote sensing monitoring. However, remote sensing data are drawn from multiple sources and multiple scales, and have a complex structure and large volume; in addition, the nested system architecture of multi-source synergized remote sensing products makes the design of large-scale multi-source synergized remote sensing monitoring systems difficult. In this paper, we describe the design and implementation of a distributed parallel processing system for multi-source data synergized quantitative remote sensing based on a distributed cluster platform. The system integrates the algorithms normalizing more than 30 kinds of data sources and producing 40 quantitative remote sensing products. The system also connects a number of centers for satellite data, serves for several applications, and implements dynamic expansion integration for highly efficient quantitative remote sensing products. The system has produced approximately 50 TB of quantitative remote sensing products, and the application of these data to agriculture, forestry, the environment, and water conservation has resulted in very positive effects.
2020
79510-79520
journalArticle
60
IEEE Transactions on Geoscience and Remote Sensing
DOI 10.1109/TGRS.2022.3207551
IEEE Transactions on Geoscience and Remote Sensing
ISSN 1558-0644
R. Hang
P. Yang
F. Zhou
Q. Liu
Convolutional neural networks
Feature extraction
Image segmentation
Remote sensing
Convolution
Kernel
Decoding
semantic segmentation
high-resolution remote sensing imagery
multiscale objects
position-sensitive modules
scale guidance modules
Multiscale Progressive Segmentation Network for High-Resolution Remote Sensing Imagery
Semantic segmentation of high-resolution remote sensing imageries (HRSIs) is a critical task for a wide range of applications, such as precision agriculture and urban planning. Although convolutional neural networks (CNNs) have made great progress in accomplishing this task recently, there still exist some challenges to address, one of which is simultaneously segmenting objects with large-scale variations in a HRSI. Targeting at this challenge, previous CNNs often adopt multiple convolution kernels in one layer or skip-layer connections between different layers to extract multiscale representations. However, due to the limited learning capacity of each CNN, it tends to make tradeoffs in segmenting different-scale objects. This would lead to unsatisfactory segmentation results for some objects, especially the small or the large ones. In this article, we propose a multiscale progressive segmentation network to address this issue. Instead of forcing one network to deal with all scales of objects, our network attempts to cascade three subnetworks for gradually segmenting objects into small scale, large scale, and other scale. In order to make the subnetwork focus on the specific scale objects, a scale guidance module is designed. It takes advantage of segmentation results from the preceding subnetwork to guide the feature learning of the succeeding one. Additionally, to acquire the final segmentation results, we propose a position-sensitive module for adaptively combining the outputs of the three subnetworks. This module is capable of assigning combination weights of different subnetworks according to their importance. Experiments on two benchmark datasets named Vaihingen and Potsdam indicate that our proposed network can achieve considerable improvements in comparison with several state-of-the-art segmentation models.
2022
1-12
journalArticle
8
IEEE Access
DOI 10.1109/ACCESS.2020.3006424
IEEE Access
ISSN 2169-3536
M. A. Khan
F. Algarni
Monitoring
Diseases
Predictive models
Internet of Things
Medical diagnostic imaging
ANFIS
Biomedical monitoring
Heart
heart disease
Internet of Medical Things
LCSA
MSSO
A Healthcare Monitoring System for the Diagnosis of Heart Disease in the IoMT Cloud Environment Using MSSO-ANFIS
The IoT has applications in many areas such as manufacturing, healthcare, and agriculture, to name a few. Recently, wearable devices have become popular with wide applications in the health monitoring system which has stimulated the growth of the Internet of Medical Things (IoMT). The IoMT has an important role to play in reducing the mortality rate by the early detection of disease. The prediction of heart disease is a key issue in the analysis of clinical dataset. The aim of the proposed investigation is to identify the key characteristics of heart disease prediction using machine learning techniques. Many studies have focused on heart disease diagnosis, but the accuracy of the findings is low. Therefore, to improve prediction accuracy, an IoMT framework for the diagnosis of heart disease using modified salp swarm optimization (MSSO) and an adaptive neuro-fuzzy inference system (ANFIS) is proposed. The proposed MSSO-ANFIS improves the search capability using the Levy flight algorithm. The regular learning process in ANFIS is dependent on gradient-based learning and has a tendency to become trapped in local minima. The learning parameters are optimized utilizing MSSO to provide better results for ANFIS. The following information is taken from medical records to predict the risk of heart disease: blood pressure (BP), age, sex, chest pain, cholesterol, blood sugar, etc. The heart condition is identified by classifying the received sensor data using MSSO-ANFIS. A simulation and analysis is conducted to show that MSSA-ANFIS works well in relation to disease prediction. The results of the simulation demonstrate that the MSSO-ANFIS prediction model achieves better accuracy than the other approaches. The proposed MSSO-ANFIS prediction model obtains an accuracy of 99.45 with a precision of 96.54, which is higher than the other approaches.
2020
122259-122269
journalArticle
9
IEEE Internet of Things Journal
DOI 10.1109/JIOT.2021.3103053
6
IEEE Internet of Things Journal
ISSN 2327-4662
R. Mahmud
A. N. Toosi
Cloud computing
Internet of Things
Sensors
Resource management
Containers
edge computing
Edge computing
Container
Docker
Economic indicators
fog computing
microservice
Raspberry Pi (RPi)
Con-Pi: A Distributed Container-Based Edge and Fog Computing Framework
Edge and Fog computing paradigms overcome the limitations of cloud-centric execution for different latency-sensitive Internet of Things (IoT) applications by offering computing resources closer to the data sources. Small single-board computers (SBCs) like Raspberry Pis (RPis) are widely used as computing nodes in both paradigms. These devices are usually equipped with moderate speed processors and provide support for peripheral interfacing and networking, making them well suited to deal with IoT-driven operations, such as data sensing, analysis, and actuation. However, these small Edge devices are constrained in facilitating multitenancy and resource sharing. The management of computing and peripheral resources through centralized entities further degrades their performance and service quality significantly. To address these issues, a fully distributed framework, named Con-Pi, is proposed in this work to manage resources at the Edge or Fog environments. Con-Pi exploits the concept of containerization and harnesses Docker containers to run IoT applications as microservices. The software system of the proposed framework also provides a scope to integrate different IoT applications, resource and energy management policies for Edge and Fog computing. Its performance is compared with the state-of-the-art frameworks through real-world experiments. The experimental results show that Con-Pi outperforms others in enhancing response time and managing energy usage and computing resources through its distributed offloading model. Further, we have developed an automated pest bird deterrent system using Con-Pi to demonstrate its suitability in developing practical solutions for various IoT-enabled use cases, including smart agriculture.
15 March15, 2022
4125-4138
journalArticle
10
IEEE Access
DOI 10.1109/ACCESS.2022.3204760
IEEE Access
ISSN 2169-3536
H. Yang
S. Li
L. Tu
R. Ma
Y. Chen
Data models
Feature extraction
Machine learning
Time series analysis
machine learning
Tuning
Anomaly detection
Safety
Feature combination
LOKI algorithm
outlier detection mechanism
parameter tuning method
tea traceability
Unsupervised Outlier Detection Mechanism for Tea Traceability Data
The presence of outliers in tea traceability data can mislead customers and have a significant impact on the reputation and profits of tea companies. To solve this problem, an unsupervised outlier detection mechanism for tea traceability data is proposed. Firstly, tea traceability data is uploaded to the MySQL database, and then the data is preprocessed to aggregate features based on relevance, which makes it easier to identify abnormal features. Secondly, the LOKI algorithm based on Local Outlier Factor (LOF), Isolation Forest (IForest), and K-Nearest Neighbors (KNN) algorithms is used to achieve unsupervised outlier detection of tea traceability data. In addition, a Density-Based Spatial Clustering of Applications with Noise (DBSCAN-based) tuning method for unsupervised outlier detection algorithms is also provided. Finally, the types of anomalies among the identified outliers are identified to investigate the causes of the anomalies in order to develop remedial procedures to eliminate the anomalies, and the analysis results are fed back to the tea companies. Experiments on real datasets show that the DBSCAN-based tuning method can effectively help the unsupervised outlier detection algorithm optimize the parameters, and that the LOF-KNN-IForest (LOKI) algorithm can effectively identify the outliers in tea traceability data. This proves that the unsupervised outlier detection mechanism for tea traceability data can effectively guarantee the quality of tea traceability data.
2022
94818-94831
journalArticle
10
IEEE Access
DOI 10.1109/ACCESS.2022.3182493
IEEE Access
ISSN 2169-3536
V. Rathi
P. Goyal
Correlation
Information filters
Imaging
Interpolation
Binary trees
Demosaicking
interpolation
K-band
multispectral filter array
Multispectral imaging
multispectral imaging system
Generic Multispectral Demosaicking Based on Directional Interpolation
The low-cost snapshot multispectral spectral imaging systems with multispectral filter array (MSFA) require generic MSFA demosaicking methods to generate the multispectral image (MSI) with a variable number of spectral bands depending on the applications. Most of the existing MSFA demosaicking methods are either non-generic or perform inadequately. This paper presents a new generic MSFA demosaicking method based on the directional weighted interpolation. Our proposed method calculates the four directional estimates around the location of the unknown pixel and combines them in a weighted manner using the local edge magnitude in the corresponding directions to estimate the missing pixel values. Experimental results confirm that the proposed demosaicking method provides improvement, compared to the state-of-the-art generic demosaicking methods in terms of both subjective and objective evaluations on the two benchmark MSI datasets.
2022
64715-64728
journalArticle
19
IEEE Geoscience and Remote Sensing Letters
DOI 10.1109/LGRS.2022.3171536
IEEE Geoscience and Remote Sensing Letters
ISSN 1558-0571
R. Chen
G. Li
C. Dai
Convolutional neural networks
Feature extraction
Principal component analysis
Hyperspectral imaging
Convolution
Data mining
Degradation
hyperspectral image (HSI) classification
residual learning
Graph convolutional network (GCN)
graph representation
DRGCN: Dual Residual Graph Convolutional Network for Hyperspectral Image Classification
Recently, graph convolutional network (GCN) has drawn increasing attention in hyperspectral image (HSI) classification, as it can process arbitrary non-Euclidean data. However, dynamic GCN that refines the graph heavily relies on the graph embedding in the previous layer, which will result in performance degradation when the embedding contains noise. In this letter, we propose a novel dual residual graph convolutional network (DRGCN) for HSI classification that integrates two adjacency matrices of dual GCN. In detail, one GCN applies a soft adjacency matrix to extract spatial features, whereas the other utilizes the dynamic adjacency matrix to extract global context-aware features. Subsequently, the features extracted by dual GCN are fused to make full use of the complementary and correlated information among two graph representations. Moreover, we introduce residual learning to optimize graph convolutional layers during the training process, to alleviate the over-smoothing problem. The advantage of dual GCN is that it can extract robust and discriminative features from HSIs. Extensive experiments on four HSI datasets, including Indian Pines, Pavia University, Salinas, and Houston University, demonstrate the effectiveness and superiority of our proposed DRGCN, even with small-sized training data.
2022
1-5
journalArticle
9
IEEE Access
DOI 10.1109/ACCESS.2021.3096194
IEEE Access
ISSN 2169-3536
Y. Zhu
Y. Yang
Y. Li
J. Qiang
Y. Yuan
R. Zhang
Data models
Training
Correlation
Linear programming
Manifolds
dual autoencoder
Independent component analysis
manifold regularization
Multi-label classification
representation learning
RICA
Representation Learning With Dual Autoencoder for Multi-Label Classification
Multi-label classification aims to deal with the problem that an object may be associated with one or more labels, which is a more difficult task due to the complex nature of multi-label data. The crucial problem of multi-label classification is the more robust and higher-level feature representation learning, which can reduce non-helpful feature attributes from the input space prior to training. In recent years, deep learning methods based on autoencoders have achieved excellent performance in multi-label classification for the advantages of powerful representations learning ability and fast convergence speed. However, most existing autoencoder-based methods only rely on the single autoencoder model, which pose challenges for multi-label feature representations learning and fail to measure similarities between data spaces. To address this problem, in this paper, we propose a novel representation learning method with dual autoencoder for multi-label classification. Compared to the existing autoencoder-based methods, our proposed method can capture different characteristics and more abstract features from data by the serially connection of two different types of autoencoders. More specifically, firstly, the algorithm of Reconstruction Independent Component Analysis (RICA) in sparse autoencoder is trained on patches on all training and test dataset for robust global feature representations learning. Secondly, with the output of RICA, stacked autoencoder with manifold regularization (SAMR) is introduced to ameliorate the quality of multi-label features learning. Comprehensive experiments on several real-world data sets demonstrate the effectiveness of our proposed approach compared with several competing state-of-the-art methods.
2021
98939-98947
journalArticle
T. Buddhika
S. L. Pallickara
S. Pallickara
Monitoring
Cloud computing
Sensors
Distributed databases
Logic gates
edge computing
Internet-of-Things
Data sketches
Data transfer
stream processing systems
Throughput
Pebbles: Leveraging Sketches for Processing Voluminous, High Velocity Data Streams
Voluminous, time-series data streams originating in continuous sensing environments pose data ingestion and processing challenges. We present a holistic methodology centered around data sketching to address both challenges. We introduce an order-preserving sketching algorithm that we have designed for space-efficient representation of multi-feature streams with native support for stream processing related operations. Observational streams are preprocessed at the edges of the network generating sketched streams to reduce data transfer costs and energy consumption. Ingested sketched streams are then processed using sketch-aware extensions to existing stream processing APIs delivering improved performance. Our benchmarks with real-world datasets show up to a ~8× reduction in data volumes transferred and a ~27× improvement in throughput.
1 Aug. 2021
2005-2020
32
IEEE Transactions on Parallel and Distributed Systems
DOI 10.1109/TPDS.2021.3055265
8
IEEE Transactions on Parallel and Distributed Systems
ISSN 1558-2183
journalArticle
T. Debnath
M. Song
Genomics
Runtime
Heuristic algorithms
Clustering algorithms
bacteria
Circular clustering
CpG island
Dynamic programming
framed clustering
Microorganisms
mitochondria
Reproducibility of results
round genome
Fast Optimal Circular Clustering and Applications on Round Genomes
Round genomes are found in bacteria, plant chloroplasts, and mitochondria. Genetic or epigenetic marks can present biologically interesting clusters along a circular genome. The circular data clustering problem groups $N$N points on a circle into $K$K clusters to minimize the within-cluster sum of squared distances. Repeatedly applying the $K$K-means algorithm takes quadratic time, impractical for large circular datasets. To overcome this issue, we developed a reproducible fast optimal circular clustering (FOCC) algorithm of worst-case $\mathcal {O}(KN \log ^2 N)$O(KNlog2N) time. The core is a fast optimal framed clustering algorithm, which we designed by integrating two divide-and-conquer and one bracket dynamic programming strategies. The algorithm is optimal based on a property of monotonic increasing cluster borders over frames on linearized data. On clustering 50,000 circular data points, FOCC outruns brute-force or heuristic circular clustering by three orders of magnitude in time. We produced clusters of CpG sites and genes along three round genomes, exhibiting higher quality than heuristic clustering. More broadly, the presented subquadratic-time algorithms offer the fastest known solution to not only framed and circular clustering, but also angular, periodical, and looped clustering. We implemented these algorithms in the R package ‘OptCirClust’ (https://CRAN.R-project.org/package=OptCirClust).
1 Nov.-Dec. 2021
2061-2071
18
IEEE/ACM Transactions on Computational Biology and Bioinformatics
DOI 10.1109/TCBB.2021.3077573
6
IEEE/ACM Transactions on Computational Biology and Bioinformatics
ISSN 1557-9964
analisis
datasets
generated_datasets
open_data
others
usa_images
CD&S
COCO
ImageNet
IP102
plantvillage
sugar_beets
usan_satelites
corine
earthstat
landsat
modis
OTHERS
sentinel
worldview
use_economics_and_statistics
IEEE Xplore
1_screening
2_manual_tag
falta_datos
genera_datos
habla_datos
trazabilidad
usa_datos
included
merge
1_screening
2_manual_tag
falta_datos
genera_datos
habla_datos
trazabilidad
usa_datos
soa
WoS
1_screening
2_manual_tag
falta_datos
genera_datos
habla_datos
trazabilidad
usa_datos
zenodo_repositories