Sentinel-2 görüntüleri kullanılarak Burdur Gölü'nde kuraklık izleme

Yıl 2024, , 882 - 891, 15.07.2024

Ümit Haluk Atasever , Hussein Hadi Abbas

https://doi.org/10.28948/ngumuh.1411803

Öz

Bu çalışma, Burdur Gölü'nde kuraklık izlemesi için Sentinel-2 uydu verileri ve K-means kümeleme kullanılarak otomatik bir iş akışı sunmaktadır. 2019'dan 2023'e kadar beş Sentinel-2 görüntüsü, spektral su indekslerini üretmek için işlenmiştir. Su indekslerinin eşiklenmesiyle bir su maskesi oluşturulmuş, böylece su kütlelerinin ayırt edilmesi sağlanmıştır. K-means kümeleme, zaman içinde göl alanındaki değişiklikleri ölçümlenmiştir. Sonuçlar, Ağustos 2019'dan Ağustos 2023'e kadar su genişliğinde azalan bir eğilim ortaya koymaktadır. Ağustos 2019'da su genişliği yaklaşık %18.53 (138.9456 Km2) iken, Ağustos 2023'e kadar yaklaşık %16.64'e (124.7500 Km2) düşmüş, başlangıç ve bitiş yılları arasında yaklaşık %10.3'lük bir su genişliği azalmasına işaret etmektedir. Bu yaklaşım, serbestçe erişilebilir uydu verileri ve makine öğrenmesi algoritmalarının operasyonel kuraklık izlemeye entegrasyonu için değerli bir çerçeve sunmaktadır.

Anahtar Kelimeler

Kuraklık İzleme, Su Maskesi, Sentinel-2 Görüntüleme, K-Means Kümeleme, Burdur Gölü Türkiye

Drought monitoring in Burdur Lake using Sentinel-2 images

Öz

This study presents an automated workflow for drought monitoring in Burdur Lake, Turkey, utilizing Sentinel-2 satellite data and K-means clustering. Five Sentinel-2 images from 2019 to 2023 were processed to derive spectral water indices. A water mask was generated by thresholding the indices, allowing for the distinction of water bodies. K-means clustering quantified changes in the lake area over time. The results reveal a decreasing trend in water extent from August 2019 to August 2023. In August 2019, the water extent was approximately 18.53% (138.9456 Km2), which declined to around 16.64% (124.7500 Km2) by August 2023, signifying an approximately 10.3% reduction in water extent between the start and end years. This approach demonstrates a valuable framework for the integration of freely available satellite data and machine learning algorithms in operational drought monitoring.

Anahtar Kelimeler

Drought Monitoring, Water Mask, Sentinel-2 Imagery, K-Means Clustering, Burdur Lake Türkiye

Kaynakça

• Y. O. Ouma and R. Tateishi, A water index for rapid mapping of shoreline changes of five East African Rift Valley lakes: an empirical analysis using Landsat TM and ETM+ data, Int J Remote Sens, vol. 27, no. 15, pp. 3153–3181, Aug. 2006, doi: 10.1080/01431160500309934.
• C. Giardino, M. Bresciani, P. Villa, and A. Martinelli, Application of Remote Sensing in Water Resource Management: The Case Study of Lake Trasimeno, Italy, Water Resources Management, vol. 24, no. 14, pp. 3885–3899, 2010, doi: 10.1007/s11269-010-9639-3.
• J. E. Pardo-Pascual, J. Almonacid-Caballer, L. A. Ruiz, and J. Palomar-Vázquez, Automatic extraction of shorelines from Landsat TM and ETM+ multi-temporal images with subpixel precision, Remote Sens Environ, vol. 123, pp. 1–11, Aug. 2012, doi: 10.1016/J.RSE.2012.02.024.
• J. H. Ryu, J. S. Won, and K. D. Min, Waterline extraction from Landsat TM data in a tidal flat: A case study in Gomso Bay, Korea, Remote Sens Environ, vol. 83, no. 3, pp. 442–456, Dec. 2002, doi: 10.1016/S0034-4257(02)00059-7.
• G. Sarp and M. Ozcelik, Water body extraction and change detection using time series: A case study of Lake Burdur, Turkey, Journal of Taibah University for Science, vol. 11, no. 3, pp. 381–391, 2017, doi: 10.1016/j.jtusci.2016.04.005.
• S. K. McFEETERS, The use of the Normalized Difference Water Index (NDWI) in the delineation of open water features, Int J Remote Sens, vol. 17, no. 7, pp. 1425–1432, May 1996, doi: 10.1080/01431169608948714.
• H. Xu, Modification of normalised difference water index (NDWI) to enhance open water features in remotely sensed imagery, Int J Remote Sens, vol. 27, no. 14, pp. 3025–3033, Jul. 2006, doi: 10.1080/01431160600589179.
• K. Rokni, A. Ahmad, A. Selamat, and S. Hazini, Water feature extraction and change detection using multitemporal landsat imagery, Remote Sens (Basel), vol. 6, no. 5, pp. 4173–4189, 2014, doi: 10.3390/rs6054173.
• H. Gao, C. Birkett, and D. P. Lettenmaier, Global monitoring of large reservoir storage from satellite remote sensing, Water Resour Res, vol. 48, no. 9, 2012, doi: 10.1029/2012WR012063.
• W. Sun, B. Du, and S. Xiong, Quantifying sub-pixel surface water coverage in urban environments using low-albedo fraction from Landsat Imagery, Remote Sens (Basel), vol. 9, no. 5, May 2017, doi: 10.3390/rs9050428.
• E. Firatli, A. Dervisoglu, N. Yagmur, N. Musaoglu, and A. Tanik, Spatio-temporal assessment of natural lakes in Turkey, Earth Sci Inform, vol. 15, no. 2, pp. 951–964, Jun. 2022, doi: 10.1007/s12145-022-00778-8.
• R. R. Colditz, C. Troche Souza, B. Vazquez, A. J. Wickel, and R. Ressl, Analysis of optimal thresholds for identification of open water using MODIS-derived spectral indices for two coastal wetland systems in Mexico, International Journal of Applied Earth Observation and Geoinformation, vol. 70, pp. 13–24, Aug. 2018, doi: 10.1016/j.jag.2018.03.008.
• G. L. Feyisa, H. Meilby, R. Fensholt, and S. R. Proud, Automated Water Extraction Index: A new technique for surface water mapping using Landsat imagery, Remote Sens Environ, vol. 140, pp. 23–35, Jan. 2014, doi: 10.1016/j.rse.2013.08.029.
• W. Li et al., A comparison of land surface water mapping using the normalized difference water index from TM, ETM+ and ALI, Remote Sens (Basel), vol. 5, no. 11, pp. 5530–5549, 2013, doi: 10.3390/rs5115530.
• Y. Han et al., Water distribution based on SAR and optical data to improve hazard mapping, Environ Res, vol. 235, Oct. 2023, doi: 10.1016/j.envres.2023.116694.
• Y. Du, Y. Zhang, F. Ling, Q. Wang, W. Li, and X. Li, Water bodies’ mapping from Sentinel-2 imagery with Modified Normalized Difference Water Index at 10-m spatial resolution produced by sharpening the swir band, Remote Sens (Basel), vol. 8, no. 4, 2016, doi: 10.3390/rs8040354.
• A. A. Davrawalska, Drought Monitoring with Sentinel-2 Case study: Western Cape Province, 2015-2020 training KIT-HYDR03, Nov. 2021. [Online]. Available: https://rus-copernicus.eu/portal/the-rus-library/learn-
• U. H. Atasever, A novel unsupervised change detection approach based on reconstruction independent component analysis and ABC-Kmeans clustering for environmental monitoring, Environ Monit Assess, vol. 191, no. 7, Jul. 2019, doi: 10.1007/s10661-019-7591-0.