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

Abstract

Coastal areas have an essential role in ecological resources and maintaining biodiversity. Seagrass is is a flowering marine angiosperm which has an essential component of coastal ecosystems because of its capability to absorb blue carbon and its involvement in the ecological role of marine biodiversity. This study used GeoEye-1, Sentinel-2 MSI level 1C, and Landsat-8 OLI satellite imagery to identify seagrass using a machine learning method. After pre-processing of GeoEye-1, Sentinel-2 MSI level 1C, and Landsat-8 OLI satellite imagery, SVM classification techniques are applied for seagrass distribution mapping. The field data from Korea Institute of Ocean Science & Technology (KIOST) has been obtained as the training and testing of a classification method. The optical satellite imagery was analyzed according to image classification, through which radiometric correction, sun glint, and water column adjustments were implemented. The scope of the study area to a maximum depth of 10 meters due to the fact that light does not penetrate beyond this level. The support vector machines (SVM) technique was utilized to classify the distribution of seagrasses in the research region. The technique achieved overall accuracy values up to 92% (GeoEye-1), 88% (Sentinel-2 MSI level 1C), and 83% (Landsat-8 OLI), respectively. The results of the overall accuracy values are shown for evaluating classification models.