COMPARISON OF LANDSAT-9 AND PRISMA SATELLITE DATA FOR LAND USE / LAND COVER CLASSIFICATION

Abstract. Land use and land cover (LU/LC) detection has great significance in management of natural resources protection environment. Hence, monitoring LU/LC with the state-of-the-art approaches gained importance during recent years free access satellite images have become valuable data source. The aim this study is to compare classification abilities Landsat-9 PRISMA while applying Support Vector Machine (SVM) algorithm distinguish different classes. For purpose, area was chosen be heterogeneous character that includes industrial area, roads, residential airport, sea, forest, vegetation barren land. When results were visually examined, it seen airport classes distinguished more accurately than other On hand, qualitative validated quantitative accuracy assessment results. overall (OA) Kappa coefficient values calculated as 89.33 0.88 for image 92.33 0.91 image, respectively. In results, although showed similar performances, a slight improvement observed by using image. findings indicated both proper assess complex region, slightly performance could achieved