Determination Of Coastline Changes at Kozan Dam Lake By Using Artificial Neural Networks Method
Tolga Kaynak Sevim YASEMİN ÇİÇEKLİ Mustafa Hayri Kesikoğlu
AbstractWith the development of technology, remote sensing is commonly used for ecological studies and monitoring wetland and management. Artificial Neural Networks are extremely simplified model of the brain occurring by neurons and layers connecting to neurons so artificial neural networks method is frequently used to classify satellite images. In this study, Landsat5 satellite image with spatial resolution of 30m, acquired on October 29, 2007 and Landsat-8 acquired on November 27, 2017 were used to identified the coastline changes at Kozan Dam Lake. The lake is used as drinking and irrigation water. Therefore, it is very important to examine the coastline changes of the lake. In first step, image to image registration was made to conform image coordinate systems of images to each other. Second step, images were classified by artificial neural networks method. Four classes namely lake, agricultural area, soil, and vegetation area were determined. Third step, image classification accuracies were determined. Finally, the changes in coastline of Dam Lake were calculated by post classification comparison method. Coastline change of Dam Lake was calculated as 0.6 km2 increase and the change image map was created. At the end of the study Kozan Dam Lake coastline changes were monitored by using remote sensing methods.