Picoli, Michelle
Camara, Gilberto
Sanches, Ieda
Simoes, Rolf
Carvalho, Alexandre
Maciel, Adeline
Coutinho, Alexandre
Esquerdo, Julio
Antunes, Joao
Begotti, Rodrigo
Arvor, Damien
Almeida, Claudio
2018-11-01
<p>This paper presents innovative methods for using satellite image time series to produce land use and land cover classification over large areas in Brazil from 2001 to 2016. We used <a href="https://www.sciencedirect.com/topics/earth-and-planetary-sciences/modis">Moderate Resolution Imaging Spectroradiometer</a> (MODIS) <a href="https://www.sciencedirect.com/topics/computer-science/time-series-data">time series data</a> to classify natural and human-transformed land areas in the state of Mato Grosso, Brazil’s agricultural frontier. Our hypothesis is that building high-dimensional spaces using all values of the time series, coupled with advanced statistical learning methods, is a robust and efficient approach for land cover classification of <a href="https://www.sciencedirect.com/topics/computer-science/large-data-set">large data sets</a>. We used the full depth of satellite image time series to create large dimensional spaces for <a href="https://www.sciencedirect.com/topics/computer-science/statistical-classification">statistical classification</a>. The data consist of <a href="https://www.sciencedirect.com/topics/earth-and-planetary-sciences/modis">MODIS</a> MOD13Q1 time series with 23 samples per year per pixel, and 4 bands (Normalized Difference <a href="https://www.sciencedirect.com/topics/earth-and-planetary-sciences/vegetation-index">Vegetation Index</a> (NDVI), Enhanced Vegetation Index (EVI), <a href="https://www.sciencedirect.com/topics/earth-and-planetary-sciences/near-infrared">near-infrared</a> (nir) and mid-infrared (mir)). By taking a series of labelled time series, we fed a 92-dimensional attribute space into a <a href="https://www.sciencedirect.com/topics/earth-and-planetary-sciences/support-vector-machine">support vector machine</a> model. Using a 5-fold cross validation, we obtained an overall accuracy of 94% for discriminating among nine land cover classes: forest, cerrado, pasture, soybean-fallow, fallow-cotton, soybean-cotton, soybean-corn, soybean-millet, and soybean-sunflower. Producer and user accuracies for all classes were close to or better than 90%. The results highlight important trends in agricultural intensification in Mato Grosso. Double crop systems are now the most common production system in the state, sparing land from agricultural production. Pasture expansion and intensification has been less studied than crop expansion, although it has a stronger impact on deforestation and <a href="https://www.sciencedirect.com/topics/earth-and-planetary-sciences/greenhouse-gas">greenhouse gas</a> (GHG) emissions. Our results point to a significant increase in the stocking rate in Mato Grosso and to the possible abandonment of pasture areas opened in the state’s frontier. The detailed land cover maps contribute to an assessment of the interplay between production and protection in the Brazilian Amazon and Cerrado biomes.</p>
https://doi.org/10.1016/j.isprsjprs.2018.08.007
oai:zenodo.org:3831203
Zenodo
info:eu-repo/semantics/openAccess
Creative Commons Attribution 4.0 International
https://creativecommons.org/licenses/by/4.0/legalcode
ISPRS Journal of Photogrammetry and Remote Sensing, 145, Part B(November 2018), 328-339, (2018-11-01)
Big earth observation data, Land use science, Satellite image time series, Crop expansion, Brazilian Amazonia biome, Brazilian Cerrado biome,Tropical deforestation
Big earth observation time series analysis for monitoring Brazilian agriculture
info:eu-repo/semantics/article