Water body extraction and change detection using time series: A case study of Lake Burdur, Turkey
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...
Main Authors: | , |
---|---|
Format: | Article |
Language: | English |
Published: |
Taylor & Francis Group
2017-05-01
|
Series: | Journal of Taibah University for Science |
Subjects: | |
Online Access: | http://www.sciencedirect.com/science/article/pii/S1658365516300206 |
id |
doaj-46ff67d504354575b9ae4b8e694a6a34 |
---|---|
record_format |
Article |
spelling |
doaj-46ff67d504354575b9ae4b8e694a6a342020-11-25T00:08:43ZengTaylor & Francis GroupJournal of Taibah University for Science1658-36552017-05-0111338139110.1016/j.jtusci.2016.04.005Water body extraction and change detection using time series: A case study of Lake Burdur, TurkeyGulcan Sarp0Mehmet Ozcelik1Department of Geography, Suleyman Demirel University, 32260 Isparta, TurkeyDepartment of Geological Engineering, Suleyman Demirel University, 32260 Isparta, TurkeyIn 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. Spatiotemporal changes of the lake based on the applied method reveal an intense decreasing trend in surface area between 1987 and 2011, especially from 1987 to 2000, when the lake lost approximately one fifth of its surface area compared to that in 1987. The results show the effectiveness of SVM and MNDWI-based surface water change detection, particularly in identifying changes between specified time intervals.http://www.sciencedirect.com/science/article/pii/S1658365516300206Support vector machineNormalized difference water indexModified NDWIAutomated water extraction indexChange detection |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Gulcan Sarp Mehmet Ozcelik |
spellingShingle |
Gulcan Sarp Mehmet Ozcelik Water body extraction and change detection using time series: A case study of Lake Burdur, Turkey Journal of Taibah University for Science Support vector machine Normalized difference water index Modified NDWI Automated water extraction index Change detection |
author_facet |
Gulcan Sarp Mehmet Ozcelik |
author_sort |
Gulcan Sarp |
title |
Water body extraction and change detection using time series: A case study of Lake Burdur, Turkey |
title_short |
Water body extraction and change detection using time series: A case study of Lake Burdur, Turkey |
title_full |
Water body extraction and change detection using time series: A case study of Lake Burdur, Turkey |
title_fullStr |
Water body extraction and change detection using time series: A case study of Lake Burdur, Turkey |
title_full_unstemmed |
Water body extraction and change detection using time series: A case study of Lake Burdur, Turkey |
title_sort |
water body extraction and change detection using time series: a case study of lake burdur, turkey |
publisher |
Taylor & Francis Group |
series |
Journal of Taibah University for Science |
issn |
1658-3655 |
publishDate |
2017-05-01 |
description |
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.
Spatiotemporal changes of the lake based on the applied method reveal an intense decreasing trend in surface area between 1987 and 2011, especially from 1987 to 2000, when the lake lost approximately one fifth of its surface area compared to that in 1987. The results show the effectiveness of SVM and MNDWI-based surface water change detection, particularly in identifying changes between specified time intervals. |
topic |
Support vector machine Normalized difference water index Modified NDWI Automated water extraction index Change detection |
url |
http://www.sciencedirect.com/science/article/pii/S1658365516300206 |
work_keys_str_mv |
AT gulcansarp waterbodyextractionandchangedetectionusingtimeseriesacasestudyoflakeburdurturkey AT mehmetozcelik waterbodyextractionandchangedetectionusingtimeseriesacasestudyoflakeburdurturkey |
_version_ |
1725414824655978496 |