Performance evaluation of machine learning algorithms using optical and microwave data for LULC classification

LULC mapping is essential for any satellite data to visualize the land information. This study aims to focus on the performance evaluation of Machine Learning (ML) Algorithms for LULC mapping of satellite datasets. Optical (Sentinel-2), Microwave (Sentinel-1), and fused datasets have been generated using Ehlers, Brovey and Principal Component fusion. For each dataset, two ML Algorithms i.e. Random Forest (RF) and Support Vector Machine (SVM) have been applied. Results suggested that the optical and fused dataset achieved the more promising results than the microwave dataset as it contains only the backscatter information. Moreover, fusion of micro-wave with optical achieved more realistic LULC classification results. The overall accuracy derived for optical, microwave, and fused data are 92 %, 93.43 %, 37.71 %, 37.14 %, 85.71 % and 89.14 % using RF and SVM classifiers, respectively.