Water body extraction and change detection using time series: A case study of Lake Burdur, Turkey. Issue 3 (1st May 2017)

• Record Type: Journal Article
• Authors: Sarp, Gulcan; Ozcelik, Mehmet
• Is Part Of: Journal of Taibah University for science. Volume 11:Issue 3(2017)
• Page Start: 381
• Page End: 391
• Publication Date: 2017-05-01
• Subjects: Support vector machine -- Normalized difference water index -- Modified NDWI -- Automated water extraction index -- Change detection; Science -- Periodicals; Science; Periodicals; 505
• DOI: 10.1016/j.jtusci.2016.04.005
• Languages: English
• ISSNs: 1658-3655

Abstract

Abstract: In this study, spatiotemporal changes in Lake Burdur from 1987 to 2011 were evaluated using multi-temporal Landsat TM and ETM+ images. Support Vector Machine (SVM) classification and spectral water indexing, including the Normalized Difference Water Index (NDWI), Modified NDWI (MNDWI) and Automated Water Extraction Index (AWEI), were used for extraction of surface water from image data. The spectral and spatial performance of each classifier was compared using Pearson's r, the Structural Similarity Index Measure (SSIM) and the Root Mean Square Error (RMSE). The accuracies of the SVM and satellite-derived indexes were tested using the RMSE. Overall, SVM followed by the MNDWI, NDWI and AWEI yielded the best result among all the techniques in terms of their spectral and spatial quality.