5777028
doi
10.5281/zenodo.5777028
oai:zenodo.org:5777028
Lorieul Titouan
Inria
Heuret Patrick
Inrae
Joly Alexis
Inria
Bonnet Pierre
Cirad
Can Artificial Intelligence help in the study of vegetative growth dynamics from herbarium collections? An evaluation of the tropical flora of the French Guiana forest
Goëau Hervé
Cirad
info:eu-repo/semantics/openAccess
Creative Commons Attribution 4.0 International
https://creativecommons.org/licenses/by/4.0/legalcode
vegetative phenology
plant growth
herbarium specimens
natural history collection
deep learning
machine learning
neural network
visual analysis
<p>Dataset was used for the article "Can Artificial Intelligence help in the study of vegetative growth dynamics from herbarium collections? An evaluation of the tropical flora of the French Guiana forest".</p>
<p>The related work proposes to study to what extent the use of automated visual analysis techniques, based on deep learning, can help not only to detect relatively rare vegetative structures in herbarium collections but also to automatically classify them by type of growing shoot (continuous or rhythmic).</p>
<p>Abstract of the paper:</p>
<p>A better knowledge of tree vegetative growth patterns and their relationship to environmental variables is crucial in understanding forest growth dynamics and how climate change may affect them. Generally less studied than reproductive structures, the phenology of tree vegetative growth mainly focuses on the analysis of growing shoots, from vegetative buds development to leaf fall. This growth process usually strongly differs between temperate and tropical regions. In temperate regions, this pattern is quite well known. Low winter temperatures impose a stop of the vegetative growth shoots and lead to the typical expression of an annual growth cycle for the vast majority of tree species. In moist tropical regions, on the other hand, the seasonality is much less marked. In addition, these regions contain a much wider variety of tree species. These two aspects lead to a tremendous diversity of phenological patterns that are still poorly known and understood. In particular, not much is known on the periodicity and timing of growth at individual trees, population, or community levels.</p>
<p>The work carried out in this study aims to advance knowledge in this area, focusing more particularly on herbarium scans, as herbarium collections offer the promise of monitoring plant phenology over long time periods. However, such a study requires the ability to detect a sufficiently large number of growing shoots in herbarium collections to draw statistically relevant conclusions, which can be very costly if the work is done manually. Furthermore, herbarium collections traditionally focus on reproductive organs, and herbarium specimens showing growing shoots are pretty rare.</p>
<p>We propose in this paper to study to what extent the use of automated visual analysis techniques, based on deep learning, can help not only to detect these relatively rare vegetative structures in herbarium collections but also to automatically classify them by type of growing shoot (continuous or rhythmic). Our results show the relevance of using herbarium data for vegetative phenology research, as well as the potential of deep learning approaches for growth shoot detection.</p>
Zenodo
2021-12-17
info:eu-repo/semantics/other
5777027
v1.0
award_title=CEnter of the study of Biodiversity in Amazonia; award_number=10-LABX-0025; funder_id=00rbzpz17; funder_name=Agence Nationale de la Recherche;
1639792121.173006
818184091
md5:3c0795b71fe96d072ca3b067d36227d1
https://zenodo.org/records/5777028/files/herbarium-vegetative-phenology.zip
public
10.5281/zenodo.5777027
isVersionOf
doi