Coastal Zone Detection in Istanbul using Landsat 8 OLI Image
ISBN 978-85-88783-11-9
Authors
1Bektas Balcik, F.; 2Balik Sanli, F.; 3Goksel, C.; 4Ustuner, M.
1ISTANBUL TECHNICAL UNIVERSITY Email: bektasfi@itu.edu.tr
2YILDIZ TECHNICAL UNIVERSITY Email: fbalik@yildiz.edu.tr
3ISTANBUL TECHNICAL UNIVERSITY Email: goksel@itu.edu.tr
4YILDIZ TECHNICAL UNIVERSITY Email: mustuner@itu.edu.tr
Abstract
Coastal zone, and its environmental management require the information about coastlines determination and monitoring. This study examines different pixel based classification methods with remote sensing indices as Normalized Difference Vegetation Index (NDVI) and Normalized Difference Water Index (NDWI) for coastline determination in Istanbul, Turkey. Istanbul has approximately 45% of industrial activity of Turkey and as a result of this the region including migration from all areas of Turkey. For the past 60 years, Istanbul has been experiencing an accelerated urban expansion. Three different test regions were selected for the study. Two test sites were selected from Black sea part and the last one selected from Marmara Sea side of the megacity. Supervised classification and support vector machine classification methods were applied using 2013-dated Landsat 8 OLI image. For the accuracy assessment confusion matrix was used to calculate overall accuracy, Kappa statistic, user and producer accuracies. High-resolution satellite image was used for accuracy assessment purpose. In order to compare the classification results McNemar's test was applied.