A General Land Cover Classification Framework for Sentinel-1 SAR Data

Nowadays, radar time series are increasingly used for land cover mapping and monitoring, thanks also to the large datasets of Synthetic Aperture Radar (SAR) over the Earth's surface, provided by Sentinel-1 mission. During the last years, a wide variety of SAR applications have benefited from the use of the large stacks of Sentinel-1 products, and processing and methods of analysis have increased more and more in the field of remote sensing. The aim of this work is to describe the processing chain realized for the global land cover mapping by using a time series stacking of Sentinel-1 for 2019. Random Forest (RF) and Support Vector Machine (SVM) have been applied for the continental Amazonian region, and their performace have been compared by means of a qualitative assessment.