Advanced Methods for the Analysis of Multitemporal Sentinel 2 Images

Due to the recent launch of the optical remote sensing satellite Sentinel 2 (S-2) contellation, it is necessary to define advanced methods tailored to the specific properties of the unprecedented data provided by this mission. S-2 is the first optical Earth observation mission including three bands in the “red edge” acquired at high spatial resolution (10-20m), which provide key information on vegetation and agricultural state. Moreover, S-2 acquires dense time series (TS) of images with worldwide coverage at high temporal resolution (about 5 days depending on the latitude), thus determining a new standard for the use of high resolution optical data for multitemporal analysis. The “S2-4Sci Land and Water - Multitemporal Analysis” project (2016-2018), funded by the European Space
Agency (ESA) in the framework of the “Scientific Exploitation of Operational Missions” (SEOM) program, aims at developing unsupervised methods to perform
advanced multitemporal analyses of S-2 images. The project investigates three methodological areas: i) land-cover maps updating, ii) land-cover change
detection, and iii) time-series analysis.