Comparison of Satellite Imagery for Identifying Seagrass Distribution Using a Machine Learning Algorithm on the Eastern Coast of South Korea

Seagrass is an essential component of coastal ecosystems because its capability to absorb blue carbon, and involvement in sustaining marine biodiversity. In this study, support vector machine (SVM) technologies with corrected satellite imagery data, were applied identify the distribution seagrasses. Observations seagrasses from obtained using GeoEye-1, Sentinel-2 MSI level 1C, Landsat-8 OLI imagery. The Google Earth has been at a very high resolution, was be used within both training testing classification method. optical must processed for image classification, throughout which radiometric correction, sunglint, water column adjustments applied. We restricted scope study area maximum depth 10 m due fact that light does not penetrate beyond level. When classifying present research region, recently developed SVM technique achieved overall accuracy values up 92% (GeoEye-1), 88% (Sentinel-2 1C), 83% (Landsat-8 OLI), respectively. results are also evaluate models.