Nesne-Tabanlı Makine Öğrenimi Sınıflandırması ile Sentinel-2 Görüntülerinden Geniş Alanlarda Su Yüzeyi Çıkarımı

Tuğçe Gülseven; Mustafa Türker

doi:10.48123/rsgis.1838375

EN TR

Extracting Water Surfaces in Large Areas from Sentinel 2 Imagery with Object-Based Machine Learning Classification

Öz

Inland water bodies are important natural resources with ecological, economic, and social significance. Their monitoring and mapping using satellite imagery are essential for sustainability. Traditional water indices are widely used for water detection; however, accurate results require condition dependent thresholds. Besides, machine learning techniques have demonstrated high success in detecting water surfaces from remote sensing data. This study presents an object-based machine learning classification approach to extract inland water bodies from optical satellite imagery. Applied to Turkey’s Lakes Region using Sentinel-2 data, image segmentation was performed with the SLIC superpixel algorithm. Training samples were automatically selected using the Global Surface Water (GSW) dataset. Classification was conducted in R Studio using the Random Forest (RF) algorithm. In addition to 10 m and 20 m bands of Sentinel-2, the Normalized Difference Water Index (NDWI) was also used in the classification. Validation results showed an overall accuracy above 98.4% and a Kappa coefficient exceeding 0.957. The findings indicate that the proposed method is promising for accurate mapping of inland water bodies using Sentinel-2 imagery in large areas.

Anahtar Kelimeler

Inland water body extraction, Sentinel-2, Machine learning, SLIC

Nesne-Tabanlı Makine Öğrenimi Sınıflandırması ile Sentinel-2 Görüntülerinden Geniş Alanlarda Su Yüzeyi Çıkarımı

Öz

Karasal su kütleleri, ekolojik, ekonomik ve sosyal açıdan önemli doğal kaynaklardır. Sürdürülebilirlik için bu kütlelerin uydu görüntüleriyle izlenmesi ve haritalanması gereklidir. Geleneksel su indeksi yöntemleri, su yüzeylerinin belirlenmesinde yaygın ve pratik olmakla birlikte, doğru sonuçlar için mekânsal ve görüntüleme koşullarına bağlı değişen eşik değerlerinin belirlenmesini gerektirmektedir. Bununla birlikte, makine öğrenmesi algoritmaları da uydu görüntülerinden su yüzeylerinin tespitinde yüksek başarı göstermektedir. Bu çalışmada, Sentinel-2 uydu görüntülerinden karasal su yüzeylerini çıkarmak için nesne tabanlı makine öğrenmesi sınıflandırma yaklaşımı sunulmuştur. Türkiye’nin Göller Bölgesi’nden seçilen çalışma alanında uygulanan yöntem kapsamında, görüntü segmentasyonu SLIC süperpiksel algoritması ile gerçekleştirilmiştir. Sınıflandırma için gerekli eğitim verisi örnekleri, Global Surface Water (GSW) veri seti yardımıyla otomatik olarak seçilmiştir. Sınıflandırma işlemi R Studio ortamında Rastgele Orman (RO) algoritması kullanılarak yapılmıştır. Sentinel-2’nin 10 m ve 20 m bantlarına ek olarak, Normalize Edilmiş Fark Su Indeksi (Normalized Difference Water Index – NDWI) de sınıflandırmada kullanılmıştır. Doğrulama sonuçları, genel doğruluğun %98,4’ün üzerinde ve Kappa katsayısının 0,957’nin üzerinde olduğunu göstermiştir. Elde edilen bulgular, önerilen yöntemin Sentinel-2 görüntüleri ile karasal su kütlelerinin büyük çalışma alanlarında yüksek doğrulukla haritalanmasında umut vaat ettiğini ortaya koymaktadır.

Anahtar Kelimeler

Karasal su kütlelerinin çıkarımı, Sentinel-2, Makine öğrenmesi, SLIC

Kaynakça

Achanta, R., Shaji, A., Smith, K., Lucchi, A., Fua, P., & Süsstrunk, S. (2012). SLIC superpixels compared to state-of-the-art superpixel methods. IEEE Transactions on Pattern Analysis and Machine Intelligence, 34(11), 2274–2282. https://doi.org/10.1109/TPAMI.2012.120
Acharya, T. D., Subedi, A., & Lee, D. H. (2018). Evaluation of water indices for surface water extraction in a Landsat 8 scene of Nepal. Sensors, 18(8), Article 2580. https://doi.org/10.3390/s18082580
Archer, K. J., & Kimes, R. V. (2008). Empirical characterization of random forest variable importance measures. Computational Statistics & Data Analysis, 52(4), 2249–2260. https://doi.org/10.1016/j.csda.2007.08.015
Bie, W., Fei, T., Liu, X., Liu, H., & Wu, G. (2020). Small water bodies mapped from Sentinel-2 MSI (MultiSpectral Imager) imagery with higher accuracy. International Journal of Remote Sensing, 41(20), 7912–7930. https://doi.org/10.1080/01431161.2020.1766150
Blaschke, T. (2010). Object based image analysis for remote sensing. ISPRS Journal of Photogrammetry and Remote Sensing, 65(1), 2–16. https://doi.org/10.1016/j.isprsjprs.2009.06.004
Blaschke, T., Hay, G. J., Kelly, M., Lang, S., Hofmann, P., Addink, E. A., Queiroz Feitosa, R., van der Meer, F., van der Werff, H., van Coillie, F., & Tiede, D. (2014). Geographic object-based image analysis—Towards a new paradigm. ISPRS Journal of Photogrammetry and Remote Sensing, 87, 180–191.
Breiman, L. (2001). Random forests. Machine Learning, 45(1), 5–32. https://doi.org/10.1023/A:1010933404324
Breiman, L. (2002). Manual on setting up, using, and understanding random forests V3.1. University of California, Berkeley, Department of Statistics. https://www.stat.berkeley.edu/~breiman/Using_random_forests_V3.1.pdf
Chagas, M. C., Falcão, A. P., & de Oliveira, R. P. (2025). Using Sentinel imagery for mapping and monitoring small surface water bodies. Remote Sensing, 17(13), Article 2128. https://doi.org/10.3390/rs17132128
Chen, J., Chen, S., Fu, R., Li, D., Jiang, H., Wang, C., Peng, Y., Jia, K., & Hicks, B. J. (2022). Remote sensing big data for water environment monitoring: Current status, challenges, and future prospects. Earth’s Future, 10(1), Article e2021EF002289. https://doi.org/10.1029/2021EF002289

Chowdhury, M. S. (2024). Comparison of accuracy and reliability of random forest, support vector machine, artificial neural network and maximum likelihood method in land use/cover classification of urban setting. Environmental Challenges, 14, Article 100800. https://doi.org/10.1016/j.envc.2023.100800
Daho, M., Settouti, N., Bechar, M., Boublenza, A., & Chikh, M. A. (2021). A new correlation-based approach for ensemble selection in random forests. International Journal of Intelligent Computing and Cybernetics, 14(2), 251–268. https://doi.org/10.1108/IJICC-10-2020-0147
Elmahdy, S., Ali, T., & Mohamed, M. (2021). Regional mapping of groundwater potential in Ar Rub Al Khali, Arabian Peninsula using the classification and regression trees model. Remote Sensing, 13(12), Article 2300. https://doi.org/10.3390/rs13122300
Feyisa, G. L., Meilby, H., Fensholt, R., & Proud, S. R. (2014). Automated Water Extraction Index: A new technique for surface water mapping using Landsat imagery. Remote Sensing of Environment, 140, 23–35. https://doi.org/10.1016/j.rse.2013.08.029
Ghasemigoudarzi, P., Huang, W., De Silva, O., Yan, Q., & Power, D. (2022). A machine learning method for inland water detection using CYGNSS data. IEEE Geoscience and Remote Sensing Letters, 19, 1–5. https://doi.org/10.1109/LGRS.2020.3020223
Ghosh, A., Fassnacht, F. E., Joshi, P. K., & Koch, B. (2014). A framework for mapping tree species combining hyperspectral and LiDAR data: Role of selected classifiers and sensor across three spatial scales. International Journal of Applied Earth Observation and Geoinformation, 26, 49–63. https://doi.org/10.1016/j.jag.2013.05.017
Guirado, E., Blanco-Sacristán, J., Rodríguez-Caballero, E., Tabik, S., Alcaraz-Segura, D., Martínez-Valderrama, J., & Cabello, J. (2021). Mask R-CNN and OBIA fusion improves the segmentation of scattered vegetation in very high-resolution optical sensors. Sensors, 21(1), Article 320. https://doi.org/10.3390/s21010320
Han, H., Choi, C., Kim, J., Morrison, R. R., Jung, J., & Kim, H. S. (2021). Multiple-depth soil moisture estimates using artificial neural network and long short-term memory models. Water, 13(18), Article 2584. https://doi.org/10.3390/w13182584
Hay, G. J., & Castilla, G. (2006, July 4–5,). Objects-based image analysis: Strengths, weakness, opportunities and threats (SWOT) [Conference presentation]. 1st International Conference on Object-based Image Analysis (OBIA 2006), Salzburg, Austria.
He, C., Wei, J., Song, Y., & Luo, J.-J. (2021). Seasonal prediction of summer precipitation in the middle and lower reaches of the Yangtze River Valley: Comparison of machine learning and climate model predictions. Water, 13(22), Article 3294. https://doi.org/10.3390/w13223294
Jiang, H., Wang, M., Hu, H., & Xu, J. (2021). Evaluating the performance of Sentinel-1A and Sentinel-2 in small waterbody mapping over urban and mountainous regions. Water, 13(7), Article 945. https://doi.org/10.3390/w13070945
Jiang, Z., Wen, Y., Zhang, G., & Wu, X. (2022). Water information extraction based on multi-model RF algorithm and Sentinel-2 image data. Sustainability, 14(7), Article 3797. https://doi.org/10.3390/su14073797
Kale, M. M., & Erişmiş, M. (2024). Eğirdir Gölü alansal değişiminin uzaktan algılama ve coğrafi bilgi sistemleri yardımıyla analizi. International Journal of Geography and Geography Education, 52, 122–140.
Kaya, Ö. A., & Kaplan, G. (2021). Uzaktan algılama yöntemleri ile Burdur Gölü’ndeki alansal değişiminin belirlenmesi. Doğal Afetler ve Çevre Dergisi, 7(1), 1–12. https://doi.org/10.21324/dacd.760805
Kulkarni, V. Y., & Sinha, P. K. (2012, July 18–20). Pruning of random forest classifiers: A survey and future directions [Conference presentation]. International Conference on Data Science & Engineering (ICDSE), Cochin, India.
Lasko, K., Griffin, S. P., Maloney, M. C., Becker, S. J., Griffin, A. W. H., & Lyon, S. L. (2021). Automated training data generation from spectral indexes for mapping surface water extent with Sentinel-2 satellite imagery at 10 m and 20 m resolutions. Remote Sensing, 13(22), Article 4531. https://doi.org/10.3390/rs13224531
Li, L., Yan, Z., Shen, Q., Cheng, G., Gao, L., & Zhang, B. (2019). Water body extraction from very high spatial resolution remote sensing data based on fully convolutional networks. Remote Sensing, 11(10), Article 1162. https://doi.org/10.3390/rs11101162
Li, A., Fan, M., Qin, G., Xu, Y., & Wang, H. (2021). Comparative analysis of machine learning algorithms in automatic identification and extraction of water boundaries. Applied Sciences, 11(21), Article 10062. https://doi.org/10.3390/app112110062
Li, J., Ma, R., Cao, Z., Xue, K., Xiong, J., Hu, M., & Feng, X. (2022a). Satellite detection of surface water extent: A review of methodology. Water, 14(7), Article 1148. https://doi.org/10.3390/w14071148
Li, L., Han, L., Miao, Q., Zhang, Y., & Jing, Y. (2022b). Superpixel-based long-range dependent network for high-resolution remote-sensing image classification. Land, 11(11), Article 2028. https://doi.org/10.3390/land11112028
Li, Z., Shen, H., Weng, Q., Zhang, Y., Dou, P., & Zhang, Y. (2022c). Cloud and cloud shadow detection for optical satellite imagery: Features, algorithms, validation, and prospects. ISPRS Journal of Photogrammetry and Remote Sensing, 188, 89–108. https://doi.org/10.1016/j.isprsjprs.2022.03.020
Liu, H., Jiang, Q., Ma, Y., Yang, Q., Shi, P., Zhang, S., Tan, Y., Xi, J., Zhang, Y., Liu, B., & Gao, X. (2022). Object-based multigrained cascade forest method for wetland classification using Sentinel-2 and Radarsat-2 imagery. Water, 14(1), Article 82. https://doi.org/10.3390/w14010082
Loukika, K. N., Keesara, V. R., & Sridhar, V. (2021). Analysis of land use and land cover using machine learning algorithms on Google Earth Engine for Munneru River Basin, India. Sustainability, 13(24), Article 13758. https://doi.org/10.3390/su132413758
McFeeters, S. K. (1996). The use of the normalized difference water index (NDWI) in the delineation of open water features. International Journal of Remote Sensing, 17, 1425–1432.
Medina-Lopez, E. (2020). Machine learning and the end of atmospheric corrections: A comparison between high-resolution sea surface salinity in coastal areas from top and bottom of atmosphere Sentinel-2 imagery. Remote Sensing, 12(18), Article 2924. https://doi.org/10.3390/rs12182924
Mitchell, T. M. (1997). Machine learning. McGraw-Hill.
Nagaraj, R., & Kumar, L. S. (2022). Multi scale feature extraction network with machine learning algorithms for water body extraction from remote sensing images. International Journal of Remote Sensing, 43(17), 6349–6387. https://doi.org/10.1080/01431161.2022.2136505
Pal, M. (2005). Random forest classifier for remote sensing classification. International Journal of Remote Sensing, 26(1), 217–222. https://doi.org/10.1080/01431160412331269698
Palmer, S. C. J., Kutser, T., & Hunter, P. D. (2014). Remote sensing of inland waters: Challenges, progress and future directions. Remote Sensing of Environment, 157, 1–8. https://doi.org/10.1016/j.rse.2014.09.021
Palomar-Vázquez, J., Pardo-Pascual, J., Almonacid-Caballer, J., & Cabezas-Rabadán, C. (2023). Shoreline Analysis and Extraction Tool (SAET): A new tool for the automatic extraction of satellite-derived shorelines with subpixel accuracy. Remote Sensing, 15(12), Article 3198. https://doi.org/10.3390/rs15123198
Pan, F., Xi, X., & Wang, C. (2020). A comparative study of water indices and image classification algorithms for mapping inland surface water bodies using Landsat imagery. Remote Sensing, 12(10), Article 1611. https://doi.org/10.3390/rs12101611
Pekel, J.-F., Cottam, A., Gorelick, N., & Belward, A. S. (2016). High-resolution mapping of global surface water and its long-term changes. Nature, 540(7633), 418–422. https://doi.org/10.1038/nature20584
Peker, E. A. (2019). Spatio-temporal changes of lake water extents in Lakes Region (Turkey) using remote sensing [Master’s thesis, Middle East Technical University]. YÖK Ulusal Tez Merkezi. https://tez.yok.gov.tr/UlusalTezMerkezi
Petrushevsky, N., Manzoni, M., & Monti-Guarnieri, A. (2022). Fast urban land cover mapping exploiting Sentinel-1 and Sentinel-2 data. Remote Sensing, 14(1), Article 36. https://doi.org/10.3390/rs14010036
Ruppen, D., Runnalls, J., Tshimanga, R., Wehrli, B., & Odermatt, D. (2023). Optical remote sensing of large-scale water pollution in Angola and DR Congo caused by the Catoca mine tailings spill. International Journal of Applied Earth Observation and Geoinformation, 118, Article 103237. https://doi.org/10.1016/j.jag.2023.103237
Schmitt, M. (2020). Potential of large-scale inland water body mapping from Sentinel-1/2 data on the example of Bavaria’s lakes and rivers. PFG – Journal of Photogrammetry, Remote Sensing and Geoinformation Science, 88, 271–289. https://doi.org/10.1007/s41064-020-00111-2
Solano, F., Di Fazio, S., & Modica, G. (2019). A methodology based on GEOBIA and WorldView-3 imagery to derive vegetation indices at tree crown detail in olive orchards. International Journal of Applied Earth Observation and Geoinformation, 83, Article 101912. https://doi.org/10.1016/j.jag.2019.101912
Şerifoğlu Yılmaz, Ç. (2025). Assessment of burned area and fire severity using Sentinel-2 imagery: Case studies from Türkiye’s summer 2025 wildfires. Turkish Journal of Remote Sensing and GIS, 6(2), 300–314. https://doi.org/10.48123/rsgis.1751391
Tian, S., Guo, H., Xu, W., Zu, X., Wang, B., Zeng, Q., Mai, Y., & Huang, J. J. (2022). Remote sensing retrieval of inland water quality parameters using Sentinel-2 and multiple machine learning algorithms. Environmental Science and Pollution Research, 30(7), 1–14. https://doi.org/10.1007/s11356-022-23431-9
Tonbul, H., & Kavzoğlu, T. (2018). Nesne tabanlı görüntü analizinde görüntü bölütleme yaklaşımları ve bölütleme kalitesinin analizi. Harita Dergisi, 160, 12-23.
Wang, M., Liu, X., Gao, Y., Ma, X., & Soomro, N. Q. (2017). Superpixel segmentation: A benchmark. Signal Processing: Image Communication, 56, 28–39.
Whyte, A., Ferentinos, K. P., & Petropoulos, G. P. (2018). A new synergistic approach for monitoring wetlands using Sentinels-1 and 2 data with object-based machine learning algorithms. Environmental Modelling & Software, 104, 40–54. https://doi.org/10.1016/j.envsoft.2018.01.023
Xie, H., Luo, X., Xu, X., Pan, H., & Tong, X. (2016). Automated sub-pixel surface water mapping from heterogeneous urban environments using Landsat 8 OLI imagery. Remote Sensing, 8(7), Article 584. https://doi.org/10.3390/rs8070584
Xu, H. (2006). Modification of Normalised Difference Water Index (NDWI) to enhance open water features in remotely sensed imagery. International Journal of Remote Sensing, 27(14), 3025–3033. https://doi.org/10.1080/01431160600589179
Yang, X., Zhao, S., Qin, X., Zhao, N., & Liang, L. (2017). Mapping of urban surface water bodies from Sentinel-2 MSI imagery at 10 m resolution via NDWI-based image sharpening. Remote Sensing, 9(6), Article 596. https://doi.org/10.3390/rs9060596
Ye, Z., Guo, Q., Zhang, J., Zhang, H., & Deng, H. (2022). Extraction of urban impervious surface based on the visible images of UAV and OBIA-RF algorithm. Transactions of the Chinese Society of Agricultural Engineering, 38(4), 225–234. https://doi.org/10.11975/j.issn.1002-6819.2022.04.026
Zhu, Y., Zhou, J., Qiu, H., Li, J., & Zhang, Q. (2021). Operation rule derivation of hydropower reservoirs by support vector machine based on grey relational analysis. Water, 13(18), Article 2518. https://doi.org/10.3390/w13182518

Ayrıntılar

Birincil Dil

Türkçe

Konular

Fotogrametri ve Uzaktan Algılama

Bölüm

Araştırma Makalesi

Yazarlar

Tuğçe Gülseven ^*
0009-0001-1193-8884
Türkiye

Mustafa Türker
0000-0001-5604-0472
Türkiye

Yayımlanma Tarihi

24 Eylül 2026

Gönderilme Tarihi

8 Aralık 2025

Kabul Tarihi

15 Nisan 2026

Yayımlandığı Sayı

Yıl 2026 Cilt: 7 Sayı: 2

DOI

https://doi.org/10.48123/rsgis.1838375

IZ

https://izlik.org/JA79CN29XH

APA

Gülseven, T., & Türker, M. (2026). Nesne-Tabanlı Makine Öğrenimi Sınıflandırması ile Sentinel-2 Görüntülerinden Geniş Alanlarda Su Yüzeyi Çıkarımı. Türk Uzaktan Algılama ve CBS Dergisi, 7(2), 247-268. https://doi.org/10.48123/rsgis.1838375

AMA

1.Gülseven T, Türker M. Nesne-Tabanlı Makine Öğrenimi Sınıflandırması ile Sentinel-2 Görüntülerinden Geniş Alanlarda Su Yüzeyi Çıkarımı. Turk J Remote Sens GIS. 2026;7(2):247-268. doi:10.48123/rsgis.1838375

Chicago

Gülseven, Tuğçe, ve Mustafa Türker. 2026. “Nesne-Tabanlı Makine Öğrenimi Sınıflandırması ile Sentinel-2 Görüntülerinden Geniş Alanlarda Su Yüzeyi Çıkarımı”. Türk Uzaktan Algılama ve CBS Dergisi 7 (2): 247-68. https://doi.org/10.48123/rsgis.1838375.

EndNote

Gülseven T, Türker M (01 Eylül 2026) Nesne-Tabanlı Makine Öğrenimi Sınıflandırması ile Sentinel-2 Görüntülerinden Geniş Alanlarda Su Yüzeyi Çıkarımı. Türk Uzaktan Algılama ve CBS Dergisi 7 2 247–268.

IEEE

[1]T. Gülseven ve M. Türker, “Nesne-Tabanlı Makine Öğrenimi Sınıflandırması ile Sentinel-2 Görüntülerinden Geniş Alanlarda Su Yüzeyi Çıkarımı”, Turk J Remote Sens GIS, c. 7, sy 2, ss. 247–268, Eyl. 2026, doi: 10.48123/rsgis.1838375.

ISNAD

Gülseven, Tuğçe - Türker, Mustafa. “Nesne-Tabanlı Makine Öğrenimi Sınıflandırması ile Sentinel-2 Görüntülerinden Geniş Alanlarda Su Yüzeyi Çıkarımı”. Türk Uzaktan Algılama ve CBS Dergisi 7/2 (01 Eylül 2026): 247-268. https://doi.org/10.48123/rsgis.1838375.

JAMA

1.Gülseven T, Türker M. Nesne-Tabanlı Makine Öğrenimi Sınıflandırması ile Sentinel-2 Görüntülerinden Geniş Alanlarda Su Yüzeyi Çıkarımı. Turk J Remote Sens GIS. 2026;7:247–268.

MLA

Gülseven, Tuğçe, ve Mustafa Türker. “Nesne-Tabanlı Makine Öğrenimi Sınıflandırması ile Sentinel-2 Görüntülerinden Geniş Alanlarda Su Yüzeyi Çıkarımı”. Türk Uzaktan Algılama ve CBS Dergisi, c. 7, sy 2, Eylül 2026, ss. 247-68, doi:10.48123/rsgis.1838375.

Vancouver

1.Tuğçe Gülseven, Mustafa Türker. Nesne-Tabanlı Makine Öğrenimi Sınıflandırması ile Sentinel-2 Görüntülerinden Geniş Alanlarda Su Yüzeyi Çıkarımı. Turk J Remote Sens GIS. 01 Eylül 2026;7(2):247-68. doi:10.48123/rsgis.1838375

Turkish Journal of Remote Sensing and GIS (Türk Uzaktan Algılama ve CBS Dergisi), Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License ile lisanlanmıştır.

Extracting Water Surfaces in Large Areas from Sentinel 2 Imagery with Object-Based Machine Learning Classification

Öz

Anahtar Kelimeler

Nesne-Tabanlı Makine Öğrenimi Sınıflandırması ile Sentinel-2 Görüntülerinden Geniş Alanlarda Su Yüzeyi Çıkarımı

Öz

Anahtar Kelimeler

Kaynakça

Ayrıntılar

Birincil Dil

Konular

Bölüm

Yazarlar

Yayımlanma Tarihi

Gönderilme Tarihi

Kabul Tarihi

Yayımlandığı Sayı

DOI

IZ

Kaynak Göster