Big Data from Space for Precision Agriculture Applications

This paper presents an approach for precision agriculture large scale applications based on the analysis of big data consisting in Satellite Image Time Series (SITS) acquired by ESA Sentinel-2 (S2) satellite constellation. The approach has been developed in the framework of the ESA SEOM - Scientific Exploitation of Operational Missions - S2-4Sci Land and Water project [1]. To focus only on agricultural areas, images are first filtered based on a land cover (LC) map that is generated by updating available old maps by means of recent images. Then S2 SITS are used to analyse agricultural areas. Two macro challenges are therefore considered: (i) automatic update of LC maps and generation of agricultural areas mask; and (ii) unsupervised multi-temporal (MT) fine characterization of land plots.