Investigation of the performance of classifiers in the extraction of water body areas using Sentinel-2 images

Yıl 2022, , 235 - 245, 15.01.2022

Mehmet Akif Günen

https://doi.org/10.17714/gumusfenbil.992432

Öz

The mapping of water body areas such as rivers, streams, lakes and ponds is very important in terms of monitoring water resources, determining, and managing their change over time. Extracting water body areas is a complicated process that is influenced by a variety of factors. For the problem of identifying water and non-water areas, various multi spectral band satellite imagery and classification-based approaches are used. In this study, non-parametric (Support Vector Machines, k-Nearest Neighborhood and Decision Trees), probabilistic (Hidden Markov Model) and deep learning (Auto-Encoder) based supervised classification, which produce more successful results than index-based methods, were used to investigate the effectiveness of classification algorithms. Since multispectral high spatial resolution satellite images are costly, the water surface areas of Arıklar and Denizli ponds were determined by using only the red, green and blue bands of the Sentinel-2 satellite image for classification. Experimental results were compared using metrics obtained from the confusion matrix such as accuracy, specificity, precision, sensitivity, f-Score, and statistical tools such as mean square error, structural similarity index, peak signal-to-noise ratio, and Kohen's Kappa metric used in image quality determination. In the quantitative and qualitative experimental results obtained, while the deep learning-based auto-encoder was the most successful method statistically, it was determined that the decision trees method worked faster in terms of time comparison.

Anahtar Kelimeler

Image classification, Sentinel-2, Classification, Water body extraction

Sentinel-2 görüntüleri kullanılarak su yüzey alanlarının belirlenmesinde sınıflandırıcıların performanslarının incelenmesi

Öz

Nehirler, akarsular, göller ve göletler gibi su yapılarının haritalanması, su kaynaklarının gözlenmesi, zaman içerisinde değişiminin belirlenmesi ve yönetilmesi açısından oldukça önemlidir. Su yüzey alanlarının tespit edilmesi birçok faktörden etkilenen karmaşık bir süreçtir. Su ve su olmayan alanların belirlenmesi problemi için çeşitli çok kanallı bantlı uydu görüntüleri ve sınıflandırma tabanlı yaklaşımlar kullanılmaktadır. Bu çalışmada, sınıflandırma algoritmalarının etkinliğinin araştırılmasında indeks tabanlı yöntemlerden daha başarı sonuç üreten parametrik olmayan (Destek Vektör Makinalar, k-En Yakın Komşuluk ve Karar Ağaçları), olasılıksal (Saklı Markov Model) ve derin öğrenme (Oto-Kodlayıcı) tabanlı danışmalı sınıflandırma yöntemleri kullanılmıştır. Çok bantlı ve yüksek mekansal çözünürlüklü uydu görüntüleri yüksek maliyetli olduğundan sınıflandırma için Sentinel-2 uydu görüntüsüne ait sadece kırmızı, yeşil ve mavi bantlar kullanılarak Arıklar ve Denizli Göletlerine ait su yüzey alanları belirlenmiştir. Deneysel sonuçlar doğruluk, özgüllük, kesinlik, duyarlılık, f-skor gibi karışıklık matrisinden elde edilen metrikler ve görüntü kalite belirlemede kullanılan ortalama karesel hata, yapısal benzerlik indeksi, pik sinyal-gürültü oranı ve Kohen’in Kappa metriği gibi istatistiksel araçları kullanılarak karşılaştırılmıştır. Elde edilen nicel ve nitel deneysel sonuçlarda derin öğrenme tabanlı oto-kodlayıcı istatistiksel olarak en başarılı yöntem olurken, zamansal karşılaştırma açısından karar ağaçları yönteminin daha hızlı çalıştığı belirlenmiştir.

Anahtar Kelimeler

Görüntü sınıflandırma, Sentinel-2, Sınıflandırma, Su yüzey alanı belirleme

Kaynakça

• Allen, G. H. and Pavelsky, T. M. (2018). Global extent of rivers and streams. Science, 361(6402), 585-588. https://doi.org/10.1126/science.aat0636.
• Aswatha, S. M., Mukherjee, J., Biswas, P. K. and Aikat, S. (2020). Unsupervised classification of land cover using multi-modal data from multi-spectral and hybrid-polarimetric SAR imageries. International Journal of Remote Sensing, 41(14), 5277-5304. https://doi.org/10.1080/01431161.2020.1731771.
• Atasever, U. H., Günen, M. A. and Beşdok, E. (2018). A new unsupervised change detection approach based on PCA based blocking and GMM clustering for detecting flood damage. Fresenius Environmental Bulletin, 27, 1688-1694.
• Aurdal, L., Huseby, R. B., Eikvil, L., Solberg, R., Vikhamar, D. and Solberg, A. (2005). Use of hidden Markov models and phenology for multitemporal satellite image classification: Applications to mountain vegetation classification. International workshop on the analysis of multi-temporal remote sensing images, Biloxi, USA. https://doi.org/10.1109/AMTRSI.2005.1469877.
• Cover, T. and Hart, P. (1967). Nearest neighbor pattern classification. IEEE transactions on information theory, 13(1), 21-27. https://doi.org/10.1109/TIT.1967.1053964.
• Drusch, M., Del Bello, U., Carlier, S., Colin, O., Fernandez, V., Gascon, F. and Martimort, P. (2012). Sentinel-2: ESA's optical high-resolution mission for GMES operational services. Remote Sensing of Environment, 120, 25-36. https://doi.org/10.1016/j.rse.2011.11.026.
• Günen, M. A. (2021). Performance comparison of deep learning and machine learning methods in determining wetland water areas using EuroSAT dataset. Environmental Science Pollution Research, 1-15. https://doi.org/10.1007/s11356-021-17177-z.
• Günen, M. A., Atasever, U. H. and Beşdok, E. (2020). Analyzing the contribution of training algorithms on deep neural networks for hyperspectral image classification. Photogrammetric Engineering Remote Sensing, 86(9), 581-588. https://doi.org/10.14358/PERS.86.9.581.
• Herndon, K., Muench, R., Cherrington, E. and Griffin, R. (2020). An assessment of surface water detection methods for water resource management in the Nigerien Sahel. Sensors, 20(2), 431. https://doi.org/10.3390/s20020431.
• Huang, X., Xie, C., Fang, X. and Zhang, L. (2015). Combining pixel-and object-based machine learning for identification of water-body types from urban high-resolution remote-sensing imagery. IEEE Journal of Selected Topics in Applied Earth Observations Remote Sensing, 8(5), 2097-2110. https://doi.org/10.1109/JSTARS.2015.2420713
• Jiang, H., Feng, M., Zhu, Y., Lu, N., Huang, J. and Xiao, T. (2014). An automated method for extracting rivers and lakes from Landsat imagery. Remote Sensing, 6(6), 5067-5089. https://doi.org/10.3390/rs6065067.
• Jiang, W., Ni, Y., Pang, Z., Li, X., Ju, H., He, G. and Qin, X. (2021). An effective water body extraction method with new water index for sentinel-2 imagery. Water, 13(12), 1647. https://doi.org/10.3390/w13121647.
• Kavzoğlu, T. ve Çölkesen, İ. (2010). Karar ağaçları ile uydu görüntülerinin sınıflandırılması: Kocaeli örneği. Harita Teknolojileri Elektronik Dergisi, 2(1), 36-45.
• Kesikoglu, M. H., Atasever, U. H., Dadaser Celik, F. and Ozkan, C. (2019). Performance of ANN, SVM and MLH techniques for land use/cover change detection at Sultan Marshes wetland, Turkey. Water Science Technology, 80(3), 466-477. https://doi.org/10.2166/wst.2019.290.
• Ko, B. C., Kim, H. H. and Nam, J. Y. (2015). Classification of potential water bodies using Landsat 8 OLI and a combination of two boosted random forest classifiers. Sensors, 15(6), 13763-13777. https://doi.org/10.3390/s150613763.
• Li, Y., Gong, X., Guo, Z., Xu, K., Hu, D. and Zhou, H. (2016). An index and approach for water extraction using Landsat–OLI data. International Journal of Remote Sensing, 37(16), 3611-3635. https://doi.org/10.1080/01431161.2016.1201228.
• Liao, H.-Y. and Wen, T.-H. (2020). Extracting urban water bodies from high-resolution radar images: Measuring the urban surface morphology to control for radar’s double-bounce effect. International Journal Of Applied Earth Observation Geoinformation, 85, 102003. https://doi.org/10.1016/j.jag.2019.102003.
• Liu, Z., Yao, Z. and Wang, R. (2016). Assessing methods of identifying open water bodies using Landsat 8 OLI imagery. Environmental Earth Sciences, 75(10), 873. https://doi.org/10.1007/s12665-016-5686-2.
• Orhan, O. (2021). Monitoring of land subsidence due to excessive groundwater extraction using small baseline subset technique in Konya, Turkey. Environmental Monitoring Assessment, 193(4), 1-17. https://doi.org/10.1007/s10661-021-08962-x.
• Orhan, O., Oliver-Cabrera, T., Wdowinski, S., Yalvac, S. and Yakar, M. (2021). Land subsidence and its relations with sinkhole activity in Karapınar region, Turkey: a multi-sensor InSAR time series study. Sensors, 21(3), 774. https://doi.org/10.3390/s21030774.
• Osman, A. ve Selçuk, A. (2018). Saklı markov modeli kullanılarak istanbul’daki üniversite öğrencilerinin gsm operatör tercihlerini etkileyen faktörlerin analizi. Çukurova Üniversitesi Mühendislik-Mimarlık Fakültesi Dergisi, 33(4), 203-212. https://doi.org/10.21605/cukurovaummfd.525235.
• Özçalik, H. l., Torun, A. T. ve Bilgilioğlu, S. S. (2020). Landsat uydu görüntüleri kullanılarak Mogan Gölü’nün su yüzeyi ve arazi örtü değişiminin belirlenmesi. Türkiye Uzaktan Algılama Dergisi, 2(2), 77-84.
• Pal, M. and Mather, P. M. (2003). An assessment of the effectiveness of decision tree methods for land cover classification. Remote Sensing of Environment, 86(4), 554-565. https://doi.org/10.1016/S0034-4257(03)00132-9.
• Pan, F., Xi, X. and 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), 1611. https://doi.org/10.3390/rs12101611.
• Ramsar. (2016). An introduction to the convention on wetlands. Ramsar Convention Secretariat, Gland, Switzerland.
• Song, S., Liu, J., Liu, Y., Feng, G., Han, H., Yao, Y. and Du, M. (2020). Intelligent object recognition of urban water bodies based on deep learning for multi-source and multi-temporal high spatial resolution remote sensing imagery. Sensors, 20(2), 397. https://doi.org/10.3390/s20020397.
• Tercan, E. and Atasever, U. H. (2021). Effectiveness of autoencoder for lake area extraction from high-resolution RGB imagery: an experimental study. Environmental Science Pollution Research, 1-13. https://doi.org/10.1007/s11356-021-12893-y.
• Torun, A. T. and Gündüz, H. İ. (2020). Comparison of different classification algorithms for the detection of changes on water bodies; Karakaya Dam Lake. Turkish Journal of Geosciences, 1(1), 27-34.
• Vapnik, V. (2013). The nature of statistical learning theory: Springer Science & Business Media.
• Wang, Z., Liu, J., Li, J. and Zhang, D. D. (2018). Multi-spectral water index (MuWI): a native 10-m multi-spectral water index for accurate water mapping on Sentinel-2. Remote Sensing, 10(10), 1643. https://doi.org/10.3390/rs10101643.
• Weih, R. C. and Riggan, N. D. (2010). Object-based classification vs. pixel-based classification: Comparative importance of multi-resolution imagery. International Archives of the Photogrammetry, Remote Sensing Spatial Information Sciences.
• Yang, X., Li, Y., Wei, Y., Chen, Z. and Xie, P. (2020). Water body extraction from sentinel-3 image with multiscale spatiotemporal super-resolution mapping. Water, 12(9), 2605. https://doi.org/10.3390/w12092605.
• Yang, X., Qin, Q., Grussenmeyer, P. and Koehl, M. (2018). Urban surface water body detection with suppressed built-up noise based on water indices from Sentinel-2 MSI imagery. Remote Sensing of Environment, 219, 259-270. https://doi.org/10.1016/j.rse.2018.09.016.
• Zhang, J., Xing, M., Sun, G.-C., Chen, J., Li, M., Hu, Y. and Bao, Z. (2020). Water body detection in high-resolution SAR images with cascaded fully-convolutional network and variable focal loss. IEEE Transactions on Geoscience Remote Sensing, 59(1), 316-332. https://doi.org/10.1109/TGRS.2020.2999405
• Zhou, Y., Dong, J., Xiao, X., Xiao, T., Yang, Z., Zhao, G. and Qin, Y. (2017). Open surface water mapping algorithms: A comparison of water-related spectral indices and sensors. Water, 9(4), 256. https://doi.org/10.3390/w9040256.