Klasifikasi Habitat Bentik Berdasarkan Citra Sentinel-2 di Kepulauan Kei, Maluku Tenggara

Imagery classification has long been used in analyzing remote sensing data. The use of the algorithm model can affect results interpreting benthic habitats shallow water. This study aimed to determine best for mapping habitat cover through Sentinel-2 satellite imagery. Three models were employed: Maximum Likelihood Classification (MLC), Minimum Distance (MDC), and Mahalanobis (MaDC). types extracted using Lyzenga correction, giving three categories: coral, seagrass, sand. showed that application MLC, MDC, MaDC on resulted an accuracy value was not significantly different at 95% confidence interval. However, algorithms used, provides overall (78.35%) than MDC (74.45%) MLC (74.33%). It shows be referred as mapped Kei Islands. this needs continuously studied compared other locations. Keywords: benthic, classification, Islands, sentinel