%0 Book Section
%9 OS CH : Chapitres d'ouvrages scientifiques
%A Jarry, R.
%A Chaumont, M.
%A Berti-Equille, Laure
%A Subsol, G.
%T Comparing spatial and spatio-temporal paradigms to estimate the evolution of socio-economical indicators from satellite images
%B IGARSS 2023 - 2023 IEEE International Geoscience and Remote Sensing Symposium : proceedings
%C Piscataway
%D 2023
%L fdi:010090482
%G ENG
%I IEEE
%@ 979-8-3503-2010-7
%K ZANZIBAR ; TANZANIE
%P 5790-5793
%R 10.1109/IGARSS52108.2023.10282306
%U https://www.documentation.ird.fr/hor/fdi:010090482
%> https://www.documentation.ird.fr/intranet/publi/2023-12/010090482.pdf
%W Horizon (IRD)
%X In remote sensing, deep spatio-temporal models, i.e., deep learning models that estimate information based on Satellite Image Time Series obtain successful results in Land Use/Land Cover classification or change detection. Nevertheless, for socioeconomic applications such as poverty estimation, only deep spatial models have been proposed. In this paper, we propose a test-bed to compare spatial and spatio-temporal paradigms to estimate the evolution of Nighttime Light (NTL), a standard proxy for socioeconomic indicators. We applied the test-bed in the area of Zanzibar, Tanzania for 21 years. We observe that (1) both models obtain roughly equivalent performances when predicting the NTL value at a given time, but (2) the spatio-temporal model is significantly more efficient when predicting the NTL evolution.
%B IGARSS. International Geoscience and Remote Sensing Symposium
%8 2023/07/16-21
%$ 126 ; 094