SHORELINE EXTRACTION USING TIME SERIES OF SENTINEL-2 SATELLITE IMAGES BY GOOGLE EARTH ENGINE PLATFORM

Abstract. In recent decades, global warming and sea level rise, population growth, intensification of human activities, have directly affected the coasts as such, their monitoring for accretion retreat are among issues that considered by coastal countries. This study, compares two supervised classification algorithms classifying Sentinel-2 satellite imagery shoreline extraction. Median monthly images from 2020/01 to 2021/12 taken classified Random Forest (RF) Support Vector Machine (SVM) algorithms. By validating maps, it is found RF algorithm has better accuracy such averaging all overall (OA) values 97.18% kappa coefficient (KC) 0.97, mean maps SVM 85.15% 0.79, respectively, obtained. After extracting shorelines, Digital Shoreline Analysis System (DSAS) used calculate displacement rate. calculating Linear Regression Rate (LRR) factor, in 91% transects (166 transects) we see land. 54% them, average rate 5.42 meters per year only 9% (16 towards sea.