Automatic land cover classification with SAR imagery and Machine learning using Google Earth Engine

Land cover is the most critical information required for land management and planning because human interference on can be easily detected through it. However, mapping utilizing optical remote sensing not easy due to acute shortage of cloud-free images. Google Earth Engine (GEE) an efficient effective tool huge analysis by providing access large volumes imagery available within a few days after acquisition in one consolidated system. This article demonstrates use Sentinel-1 datasets create map Pusad, Maharashtra using GEE platform. provides Synthetic Aperture Radar (SAR) that have temporally dense high spatial resolution, which renowned its cloud penetration characteristics round-the-year observations irrespective weather. VV VH polarization sentinel-1 time series data were automatically classified support vector machine (SVM) Random Forest (RF) learning algorithms. Overall accuracies (OA), ranging from 82.3% 90%, obtained depending methodology used. RF algorithm with dataset stands better comparison SVM achieving OA 90% Kappa coefficient 0.86. The highest user accuracy was water class both classifiers.