Extraction of Spread Surface Water Body using Supervised and Unsupervised Classification Techniques

Abstract

In this paper different classification techniques are applied to extract spread surface water area in the Nagarjuna sagar reservoir, Andhra Pradesh from Landsat-8 (OLI) image. In addition, the separability of reservoir features are tested to evaluate the thematic correctness of the classified data. This is to evaluate the application of a supervised and unsupervised classification techniques using the ERDAS software to extract the changes of surface water features for the period of 2014 to 2019. Furthermore, the statistical parameters are evaluated for the classification techniques. In supervised and unsupervised classification methods the minimum distance classifier gives better result (overall accuracy is 98.01%) than other classification methods. These obtained results are validated with ground truth data which is provided by Central Water-board Commission(CWC).