Publications des agents du Cirad


How do deep convolutional SDM trained on satellite images unravel vegetation ecology?

Deneu B., Joly A., Bonnet P., Servajean M., Munoz F.. 2021. In : Del Bimbo Alberto (ed.), Cucchiara Rita (ed.), Sclaroff Stan (ed.), Farinella Giovanni Maria (ed.), Mei Tao (ed.), Bertini Marco (ed.), Escalante Hugo Jair (ed.), Vezzani Roberto (ed.). Pattern recognition. ICPR International Workshops and Challenges. Virtual event, January 10¿15, 2021, Proceedings, Part VI. Cham : Springer, p. 148-158. (Lecture Notes in Computer Science, 12666). International Conference on Pattern Recognition (ICPR 2021). 25, 2021-01-10/2021-01-15, Milan (Italie).

DOI: arXiv:2004.04192

DOI: 10.1007/978-3-030-68780-9_15

Species distribution models (SDM) assess and predict how species spatial distributions depend on the environment, due to species ecological preferences. These models are used in many different scenarios such as conservation plans or monitoring of invasive species. The choice of a model and of environmental data have strong impact on the model's ability to capture important ecological information. Specifically, state-of-the-art models generally rely on local, punctual environmental information, and do not take into account environmental variation in surrounding landscape. Here we use a convolutional neural network model to analyze and predict species distributions depending on high resolution data including remote sensing images, land cover and altitude. We show that the model unravel the functional response of vegetation to both local and large-scale environmental variation. To demonstrate the ecological significance of the results, we propose an original statistical analysis of t-SNE nonlinear dimension reduction. We illustrate and test the traits-species- environment relationships learned by the model and expressed in t-SNE dimensions.

Documents associés

Communication de congrès

Agents Cirad, auteurs de cette publication :