Performances Evaluation of Water Body Extraction Techniques Using Landsat ETM+ Data: Case- Study of Lake Nubia, Sudan

Abstract

Lake Nubia (LN) is the Sudanese portion of Aswan High Dam Lake (AHDL). This paper aims to detect the better technique for extraction of the water surface of LN. Eight techniques are tested using Landsat ETM+ image and their performances in extracting the surface water area are evaluated. The eight techniques include Automated Water Extraction Index [AWEI], Normalized Difference Moisture Index [NDMI], Normalized Difference Water Index [NDWI], Modified Normalized Difference Water Index [MNDWI], Normalized Difference Vegetation Index [NDVI], Water Ratio Index [WRI], Supervised and Unsupervised image classification techniques. The results indicate the effectiveness and superiority of the unsupervised technique, as it gave the highest overall accuracy (about 97.23%) and the lowest absolute error. It is recommended to apply this technique to efficiently monitor changes in the surface water areas of the lakes using Landsat ETM+ data.