The determination of coastline changes using artificial neural networks in Yamula Dam Lake, Turkey

Abstract

Yamula Dam Lake is an important area constructed for the purpose of producing hydroelectric energy and irrigation. In this study, the coastline boundary changes occurred in a part of Yamula Dam Lake in Kayseri province were examined using three multispectral Landsat 8 LDCM satellite images of March, August and November 2016. Firstly, image-to-image registration process was performed to conform the image coordinate systems of images to each other. The radiometric calibration process wasn't done, since there was not any process related to the reflectance and radiance values when determining the coastline boundary change. Then, each satellite image was classified into two information classes, namely water and other fields by using artificial neural network method. The change images were created for March-August and August-November pairs by using the obtained classification images. The changes in coastline boundary were determined by the post classification comparison method. Consequently, bi-directional changes from water to land and from land to water were detected in Yamula Dam Lake.