Deep Learning for Automatic Extraction of Water Bodies Using Satellite Imagery

Abstract The study introduces an automated approach for extracting water bodies from satellite images using the Faster R-CNN algorithm. was tested on two datasets consisting of body collected Sentinel-2 and Landsat-8 (OLI) images, totaling over 3500 images. results showed that proposed achieved accuracy 98.7% 96.1% datasets, respectively. This is significantly higher than by convolutional neural network (CNN) approach, which 96% 80% These findings highlight effectiveness in accurately mapping imagery. Additionally, dataset performed better Landsat both CNN approaches extraction.