Benefits of Combining ALOS/PALSAR-2 and Sentinel-2A Data in the Classification of Land Cover Classes in the Santa Catarina Southern Plateau

The Santa Catarina Southern Plateau is located in Brazil and a region that has gained considerable attention due to the rapid conversion of typical landscape natural grasslands wetlands into agriculture, reforestation, pasture, more recently, wind farms. This study’s main goal was characterize polarimetric attributes experimental quad-polarization acquisition mode Advanced Land Observing Satellite/Phased Array type L-band Synthetic Aperture Radar (ALOS/PALSAR-2) for mapping seven land cover classes. were evaluated alone combined with SENTINEL-2A using supervised classification method based on Support Vector Machine (SVM) algorithm. results showed intensity backscattering reached an overall accuracy 37.48% Kappa index 0.26. Interestingly, addition features increased 71.35% 0.66, respectively. It shows use decomposition relatively efficient discriminating data performed better achieved weighted 85.56% 0.82. increase also significant Z-test. However, ALOS/PALSAR-2 derived slightly improved marginally at 95% confidence level only when all considered. Possible implications performance are accumulated precipitation prior SAR acquisition, which coincides rainy season period. ALOS/PALSAR- 2 shall be near future over different seasonal conditions confirm results. Alternatively, further studies then suggested by focusing additional from such as texture interferometric coherence accuracy. These measures would interesting source monitoring specific classes threatened during periods frequent cloud coverage. Future investigations could address multitemporal approaches employing either single or multifrequency SAR.