Sentinel-1 Image Classification Using Machine Learning Algorithms Based on the Support Vector Machine and Random Forest

Abstract

Due to concerns of recent earth climate changes such as an increase of earth surface temperature and monitoring its effect on the earth's surface, environmental monitoring is a necessity. Environmental change monitoring in earth sciences needs land use land cover change (LULCC) modeling to investigate the impact of climate change phenomena such as droughts and floods on earth surface land cover. As land cover has a direct effect on Land Surface Temperature (LST), the Land cover mapping is an essential part of climate change modeling. In this paper, for land use land cover mapping (LULCM), image classification of Sentinel-1A Synthetic Aperture Radar (SAR) Ground Range Detected (GRD) data using two machine learning algorithms including Support Vector Machine (SVM) and Random Forest (RF) are implemented in R programming language and compared in terms of overall accuracy for image classification. With seven different scenarios defined in this research, RF and SVM classification methods show their best performance with overall accuracies of 75.30 and 75.35 percent, respectively.