Spatial distribution of benthic habitats in Kapota Atoll (Wakatobi National Park, Indonesia) using remote sensing imagery

Abstract. Hamuna B, Pujiyati S, Gaol JL, Hestirianoto T. 2023. Spatial distribution of benthic habitats in Kapota Atoll (Wakatobi National Park, Indonesia) using remote sensing imagery. Biodiversitas 24: 3700-3707. This study aims to classify and map Atoll, Wakatobi Sentinel-2A satellite imagery, that has undergone both atmospheric geometric corrections. imagery was processed pixel-based classification method. used two machine learning algorithms: support vector (SVM) random forest (RF). nine classified habitat classes, namely five homogeneous classes (sand, live coral, dead rubble, dense seagrass) four mixed (mixed rubble sand, sand rare seagrass, medium seagrass a mixture seagrass). The RF algorithm produced maps with higher overall accuracy than the SVM algorithm, which 65.31% 63.51%, respectively. These values have met standards for mapping apply Indonesia. results showed class more dominant other classes. In contrast, dominant. selection appropriate processing found be significant factor producing an accurate map.