Fast Urban Land Cover Mapping Exploiting Sentinel-1 and Sentinel-2 Data

The rapid change and expansion of human settlements raise the need for precise remote-sensing monitoring tools. While some Land Cover (LC) maps are publicly available, knowledge up-to-date urban extent a specific instance in time is often missing. lack relevant mask, especially developing countries, increases burden on Earth Observation (EO) data users or requires them to rely time-consuming manual classification. This paper explores fast effective exploitation Sentinel-1 (S1) Sentinel-2 (S2) generation LC, which can be frequently updated. method based an Object-Based Image Analysis (OBIA), where one Multi-Spectral (MS) image used define clusters similar pixels through super-pixel segmentation. A short stack (<2 months) Synthetic Aperture Radar (SAR) then employed classify clusters, exploiting unique characteristics radio backscatter from human-made targets. repeated illumination acquisition geometry allows defining robust features amplitude, coherence, polarimetry. Data ascending descending orbits combined overcome distortions decrease sensitivity orientation structures. Finally, unsupervised Machine Learning (ML) model separate signature targets mixed environment. was validated two sites Portugal, with diverse types LC complex topography. Comparative analysis performed state-of-the-art high-resolution solutions, require long sensing periods, indicating significant agreement between methods (averaged accuracy around 90%).