Denetimli Sınıflandırıcılarla Taşkın Haritalaması: 2021 Gediz Ovası Seli

Year 2023, Volume: 4 Issue: 1, 100 - 113, 28.03.2023

Enis Arslan , Serkan Kartal

https://doi.org/10.48123/rsgis.1220879

Abstract

Taşkın haritalarının oluşturulması, taşkın sebepli risklerin değerlendirilmesinde oldukça faydalıdır. Sel-taşkın haritalaması, eşikleme ile değişiklik tespiti (DT) ve makine öğrenimi tabanlı (MÖ) yöntemler gibi birçok uzaktan algılama tekniği ile gerçekleştirilebilmektedir. Bu çalışmalarda farklı uydu sistemleri tarafından sağlanan optik ve sentetik açıklıklı radar (SAR) görüntüleri yaygın olarak kullanılmaktadır. Bu çalışmada, denetimli MÖ algoritmaları ile Google Earth Engine'de (GEE) Sentinel-1 SAR ve Sentinel-2 MSI uydu verileri kullanılmıştır. Çalışma alanı olarak Türkiye'nin Gediz Ovası seçilmiştir ve bu alan çoğunlukla ekili arazilerle kaplıdır. Bu çalışmada 2021 yılı Şubat ayının ikinci günü meydana gelen taşkın olayı incelenmiş ve çalışma alanı için taşkın haritası oluşturulmuştur. Çalışma için, Support Vector Machines (SVM), Random Forest (RF) ve K-nearest Neighbor (KNN) MÖ algoritmaları seçilmiş ve modeller GEE'de manuel olarak oluşturulan etiketlenmiş verilerle eğitilmiştir. Ayrıca geleneksel yaklaşımla olay öncesi ve sonrası SAR görüntülerine DT uygulanmıştır. RF sınıflandırıcısı, %94 genel sınıflandırma doğruluğu ile Sentinel-2 MSI görüntülerinde en iyi performansı gösterirken, KNN sınıflandırıcı, Sentinel-1 SAR veri kümesi için %93,3 doğruluk değeri vererek SAR görüntülerinin tüm hava koşulları için uygunluğunu göstermektedir.

Keywords

Taşkın haritalaması, GEE, Sınıflandırıcı, Sentinel-1, Sentinel-2

Flood Inundation Mapping with Supervised Classifiers: 2021 Gediz Plain Flood

Abstract

Generation of flood inundation maps is beneficial in flood risk assessment and evaluation. Flood inundation mapping can be achieved by many remote sensing techniques like change detection (CD) with thresholding and machine learning-based (ML) methods. Optical and synthetic aperture radar (SAR) imagery are widely used, provided by different satellite systems. This study used Sentinel-1 SAR and Sentinel-2 MSI satellite data in Google Earth Engine (GEE) with supervised ML algorithms. Gediz Plain, Turkey was selected as the study area, which is an agricultural area covered mostly by croplands. A flood event that occurred on February 2, 2021, was examined and flood inundation map for the study area was composed. Support Vector Machines (SVM), Random Forest (RF) and K-Nearest Neighbor (KNN) ML algorithms were selected and models were trained with manually created labelled data in GEE. Also, CD was applied on after and before event SAR images in a traditional approach. RF classifier performs best in Sentinel-2 MSI imagery with 94% overall classification accuracy where KNN classifier gives 93.3% accuracy value for Sentinel-1 SAR dataset, indicating the robustness of SAR imagery for all-weather conditions.

Keywords

Flood mapping, GEE, Classifier, Sentinel-1, Sentinel-2

References

• Afify, H. A. (2011). Evaluation of change detection techniques for monitoring land-cover changes: A case study in new Burg El-Arab area. Alexandria Engineering Journal, 50(2), 187-195.
• Amani, M., Brisco, B., Afshar, M., Mirmazloumi, S. M., Mahdavi, S., Mirzadeh, S. M. J., & Granger, J. (2019). A generalized supervised classification scheme to produce provincial wetland inventory maps: An application of Google Earth Engine for big geo data processing. Big Earth Data, 3(4), 378-394.
• Arslan, D., Çiçek, K., Döndüren, Ö., & Ernoul, L. (2021). Threat ranking to improve conservation planning: an example from the Gediz Delta, Turkey. Land, 10(12), 1381. doi: 10.3390/land10121381.
• Baghi, A., & Karami, A. (2017). SAR image segmentation using region growing and spectral cluster. In 3rd International Conference on Pattern Recognition and Image Analysis (IPRIA), 2017. Proceedings. (pp. 229-232). IEEE.
• Benoudjit, A., & Guida, R. (2019). A novel fully automated mapping of the flood extent on SAR images using a supervised classifier. Remote Sensing, 11(7), 779. doi: 10.3390/rs11070779.
• Breiman, L. (2001). Random forests. Machine Learning, 45(1), 5-32.
• Brown, K. M., Hambidge, C. H., & Brownett, J. M. (2016). Progress in operational flood mapping using satellite synthetic aperture radar (SAR) and airborne light detection and ranging (LiDAR) data. Progress in Physical Geography, 40(2), 196-214.
• Cao, H., Zhang, H., Wang, C., & Zhang, B. (2019). Operational flood detection using Sentinel-1 SAR data over large areas. Water, 11(4), 786. doi: 10.3390/w11040786.
• Carincotte, C., Derrode, S., & Bourennane, S. (2006). Unsupervised change detection on SAR images using fuzzy hidden Markov chains. IEEE Transactions on Geoscience and Remote Sensing, 44(2), 432-441.
• Chang, Y. L., Anagaw, A., Chang, L., Wang, Y. C., Hsiao, C. Y., & Lee, W. H. (2019). Ship detection based on YOLOv2 for SAR imagery. Remote Sensing, 11(7), 786. doi: 10.3390/rs11070786.
• Chen, Y., Li, J., & Chen, A. (2021). Does high risk mean high loss: Evidence from flood disaster in southern China. Science of The Total Environment, 785, 147127. doi: 10.1016/j.scitotenv.2021.147127.
• Cian, F., Marconcini, M., Ceccato, P., & Giupponi, C. (2018). Flood depth estimation by means of high-resolution SAR images and lidar data. Natural Hazards and Earth System Sciences, 18(11), 3063-3084.
• Clement, M. A., Kilsby, C. G., & Moore, P. (2018). Multi‐temporal synthetic aperture radar flood mapping using change detection. Journal of Flood Risk Management, 11(2), 152-168.
• Cohen, J. (1960). A coefficient of agreement for nominal scales. Educational and Psychological Measurement, 20(1), 37-46.
• Čotar, K., Oštir, K., & Kokalj, Ž. (2016). Radar satellite imagery and automatic detection of water bodies. Geodetski glasnik, 50(47), 5-15.
• ÇOB. (2007). Gediz Deltası Sulak Alan Yönetim Planı. Ankara: T.C. Çevre ve Orman Bakanlığı, Doğa Koruma ve Milli Parklar, Sulak Alanlar Şube Müdürlüğü.
• Damtea, W., Kim, D., & Im, S. (2020). Spatiotemporal analysis of land cover changes in the chemoga basin, Ethiopia, using Landsat and google earth images. Sustainability, 12(9), 3607. doi: 10.3390/su12093607.
• Duda, R. O., Hart, P. E., & Stork, D. G. (1973). Pattern classification and scene analysis. New York, NY: Wiley.
• Goffi, A., Stroppiana, D., Brivio, P. A., Bordogna, G., & Boschetti, M. (2020). Towards an automated approach to map flooded areas from Sentinel-2 MSI data and soft integration of water spectral features. International Journal of Applied Earth Observation and Geoinformation, 84, 101951. doi:10.1016/j.jag.2019.101951.
• Gorelick, N., Hancher, M., Dixon, M., Ilyushchenko, S., Thau, D., & Moore, R. (2017). Google Earth Engine: Planetary-scale geospatial analysis for everyone. Remote sensing of Environment, 202, 18-27.
• Hardisky, M.A., Klemas, V., & Smart, R. (1983). The influence of soil salinity, growth form, and leaf moisture on-the spectral radiance of Spartina alterniflora Canopies. Photogrammetric Engineering and Remote Sensing, 49(1), 77-83.
• Hsu, C.-W., Chang, C.-C., & Lin, C.-J. (2016). A practical guide to support vector classification. Retrieved from https://www.csie.ntu.edu.tw/~cjlin/papers/guide/guide.pdf.
• Klemas, V. (2013). Remote sensing of emergent and submerged wetlands: An overview. International Journal of Remote Sensing, 34(18), 6286-6320.
• Kurita, T., Otsu, N., & Abdelmalek, N. (1992). Maximum likelihood thresholding based on population mixture models. Pattern Recognition, 25(10), 1231-1240.
• Martinis, S., Kuenzer, C., Wendleder, A., Huth, J., Twele, A., Roth, A., & Dech, S. (2015). Comparing four operational SAR-based water and flood detection approaches. International Journal of Remote Sensing, 36(13), 3519-3543.
• 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(7), 1425-1432.
• MGM, (2023). Resmi İstatistikler, İllere Ait Mevsim Normalleri (1991-2020). Retrieved from https://mgm.gov.tr/ veridegerlendirme/il-ve-ilceler-istatistik.aspx?k=H&m=MANISA.
• Ozkan, S. P., & Tarhan, C. (2016). Detection of flood hazard in urban areas using GIS: Izmir case. Procedia Technology, 22, 373-381.
• Pradhan, B., Hagemann, U., Tehrany, M. S., & Prechtel, N. (2014). An easy to use ArcMap based texture analysis program for extraction of flooded areas from TerraSAR-X satellite image. Computers & Geosciences, 63, 34-43.
• Pramanick, N., Acharyya, R., Mukherjee, S., Mukherjee, S., Pal, I., Mitra, D. & Mukhopadhyay, A. (2022). SAR based flood risk analysis: A case study Kerala flood 2018. Advances in Space Research, 69(4), 1915-1929.
• Rouse, J. W., Haas, R. H., Schell, J. A., & Deering, D. W. (1974). Monitoring vegetation systems in the Great Plains with ERTS. In Third Earth Resources Technology Satellite-1 Symposium, 1974. Proceedings. (pp. 309-317). NASA.
• Schumann, G., Di Baldassarre, G., Alsdorf, D., & Bates, P. D. (2010). Near real‐time flood wave approximation on large rivers from space: Application to the River Po, Italy. Water Resources Research, 46(5), W05601. doi: 0.1029/2008WR007672.
• Solbø, S., & Solheim, I. (2005, September). Towards operational flood mapping with satellite SAR. In Envisat & ERS Symposium, 2004. Proceedings. (pp. 1-8).
• Taati, A., Sarmadian, F., Mousavi, A., Pour, C. T. H., & Shahir, A. H. E. (2015). Land use classification using support vector machine and maximum likelihood algorithms by Landsat 5 TM images. Walailak Journal of Science and Technology (WJST), 12(8), 681-687.
• Taheri Dehkordi, A., Valadan Zoej, M. J., Ghasemi, H., Ghaderpour, E., & Hassan, Q. K. (2022). A new clustering method to generate training samples for supervised monitoring of long-term water surface dynamics using Landsat data through Google Earth Engine. Sustainability, 14(13), 8046. doi: 10.3390/su14138046.
• Thanh Noi, P., & Kappas, M. (2017). Comparison of random forest, k-nearest neighbor, and support vector machine classifiers for land cover classification using Sentinel-2 imagery. Sensors, 18(1), 18. doi: 10.3390/s18010018.
• Topouzelis, K. N. (2008). Oil spill detection by SAR images: dark formation detection, feature extraction and classification algorithms. Sensors, 8(10), 6642-6659.
• 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.