Marie Curie Fellowship
Project duration: 
Oct 2019 to Oct 2021

Development of advanced algorithms for estimating essential vegetation variables at high spatial and temporal resolution from Sentinel-2 data. Sentinel-2 products and essential vegetation variables, in particular, must make a decisive contribution to land management, agriculture and forestry applications to support decision-making and implementation of sustainability policies at the regional, national and regional levels. , European and global.


The aim of MOVES project is to develop advanced machine learning algorithms for the retrieval of essential vegetation variables from high spatio-temporal resolution satellite data. Leaf area index, fraction of absorbed photosynthetically active radiation, fraction of green vegetation cover, water content and chlorophyll content are key biophysical variables for monitoring the status and functioning of vegetation. High spatiotemporal resolution estimates of these biophysical variables are needed in many terrestrial applications including crop and forest management. The trade-off in traditional remote sensing sensors between temporal and spatial resolutions hinders the generation of such products. The launch of Sentinel-2 satellites, with 13 spectral bands with a spatial resolution of 10-20-60 m and 5-day temporal frequency, opens a new paradigm in satellite vegetation monitoring. MOVES will underpin new avenues for the development of high spatiotemporal frequency vegetation monitoring systems.