Cloud based spatio-temporal analysis of change in sequences of Sentinel images

An important task in remote sensing Earth observation involves the detection of changes which may signal for example environmentally significant events. The Sentinel-1 synthetic aperture radar (SAR) and the Sentinel-2 as well as the Landsat optical/visible-infrared spaceborne platforms, with spatial resolutions of the order of 10-20-30 meters and revisit times of the order of days, provide an attractive source of data for change detection tasks.

Specifically, the SAR imagery provide complete independence from solar illumination and cloud cover. A convenient source of such data is the Google Earth Engine which gives near real time data access and which has an application programming interface for the access and for processing the data. Here we make available open-source automatic change detection software and for optical data also automatic radiometric normalization software for both cloud and local processing.