Mapping Land Use and Land Cover Classes in São Paulo State, Southeast of Brazil, Using Landsat-8 OLI Multispectral Data and the Derived Spectral Indices and Fraction Images

This work aims to develop a new method map Land Use and Cover (LULC) classes in the São Paulo State, Brazil, using Landsat-8 Operational Imager (OLI) data. The novelty of proposed consists selecting images based on spectral temporal characteristics LULC classes. First, we defined six be mapped year 2020 as forest, forest plantation, water bodies, urban areas, agriculture, pasture. Second, visually analyzed their variability over year. Then, pre-processed these highlight each class. For classification, Random Forest algorithm available Google Earth Engine (GEE) platform was utilized individually for Afterward, integrated classified maps create final map. results revealed that areas are primarily concentrated eastern region Paulo, predominantly steeper slopes, accounting 19% study area. On other hand, pasture agriculture dominated 73% all Paulo’s landscape, reaching 39% 34%, respectively. overall accuracy classification achieved 89.10%, while producer user accuracies were greater than 84.20% 76.62%, To validate results, compared our findings with MapBiomas Project obtaining an 85.47%. Therefore, demonstrates its potential minimize errors offers advantage facilitating post-classification editing individual