Google Earth Engine Platformunda SNIC ve Makine Öğrenimi Yöntemlerini Birleştiren Nesne Tabanlı Sınıflandırma (Örnek Olay: Köyceğiz Gölü)

Year 2024, , 125 - 137, 28.03.2024

Pınar Karakuş

https://doi.org/10.48123/rsgis.1411380

Abstract

Köyceğiz Gölü, Akdeniz Bölgesi'nin batı ucunda yer alan kükürt bakımından zengin, ülkemizin en kritik kıyı set göllerinden biridir. Dalyan Boğazı ile Akdeniz’e bağlanan Köyceğiz Gölü, bu özelliği ile de dünyadaki 7 gölden birisidir. Bu çalışmada, Nesne Tabanlı Görüntü Sınıflandırma yöntemi, makine öğrenimi algoritmalarından SRA (Sınıflandırma ve Regresyon Ağaçları), RO (Rasgele Orman) ve DVM (Destek Vektör Makineleri) algoritmaları ile bütünleştirerek Köyceğiz gölünün su değişim analizi gerçekleştirilmiştir. Görüntüyü süper piksellere bölerek nesne düzeyinde ayrıntılı bir analize olanak tanıyan Basit Yinelemesiz Kümeleme (BYK) segmentasyon yöntemi kullanılmıştır. Çalışma alanına ait Sentinel 2 Harmonized görüntüleri 2019, 2020, 2021 ve 2022 yılları için Google Earth Engine (GEE) platformundan elde edilmiş ve tüm hesaplamalar GEE’de yapılmıştır. Dört yılın sınıflandırma doğrulukları incelendiğinde BYK algoritması ile SRA, RO ve DVM makine öğrenme algoritmalarının kombinasyonu ile elde edilen nesne tabanlı sınıflandırma yöntemi kullanılarak göl su alanının bütün yöntemler için sınıflandırma doğruluklarının(ÜD, KD, GD ve Kappa) %92'nin üstünde, F-score’un 0.98’in üzerinde olduğu görülmüştür. SVM algoritmasının SRA ve RO yöntemlerine göre göl su alanının belirlenmesinde daha yüksek değerlendirme metriklerine sahip olduğu belirlenmiştir.

Keywords

GEE, Basit yinelemeli kümeleme, Nesne tabanlı sınıflandırma, Göl yüzey alanı, Sentinel 2, Makine öğrenmesi

Object Based Classification in Google Earth Engine Combining SNIC and Machine Learning Methods (Case Study: Lake Köyceğiz)

Abstract

Köyceğiz Lake is one of our country’s most critical coastal barrier lakes, rich in sulfur, located at the western end of the Mediterranean Region. Köyceğiz Lake, connected to the Mediterranean via the Dalyan Strait, is one of the 7 lakes in the world with this feature. In this study, water change analysis of Köyceğiz Lake was carried out by integrating the Object-Based Image Classification method with CART (Classification and Regression Tree), RF (Random Forest), and SVM (Support Vector Machine) algorithms, which are machine learning algorithms. SNIC (Simple Non-iterative Clustering) segmentation method was used, which allows a detailed analysis at the object level by dividing the image into super pixels. Sentinel 2 Harmonized images of the study area were obtained from the Google Earth Engine (GEE) platform for 2019, 2020, 2021, and 2022,and all calculations were made in GEE. When the classification accuracies of four years were examined, it was seen that the classification accuracies(OA, UA, PA, and Kappa) of the lake water area were above 92%, F-score was above 0.98 for all methods using the object-based classification method obtained by the combination of the SNIC algorithm and CART, RF, and SVM machine learning algorithms. It has been determined that the SVM algorithm has higher evaluation metrics in determining the lake water area than the CART and RF methods.

Keywords

GEE, Simple non-iterative clustering, Object based classification, Lake surface area, Sentinel 2, Machine learning

References

• Achanta, R., & Süsstrunk, S. (2017). Superpixels and polygons using simple non-iterative clustering. Proceedings of the 30th IEEE Conference on Computer Vision and Pattern Recognition (pp. 4895–4904). IEEE. https://doi.org/10.1109/CVPR.2017.520
• Acharya, T. D., Subedi, A., & Lee, D. H. (2019). Evaluation of machine learning algorithms for surface water extraction in a Landsat 8 Scene of Nepal. Sensors, 19(12), 2769. https://doi.org/10.3390/s19122769
• Aldiansyah, S., & Saputra, R. A. (2023). Comparison of machine learning algorithms for land use and land cover analysis using Google Earth Engine (case study: Wanggu Watershed). International Journal of Remote Sensing and Earth Sciences, 19(2), 197-210.
• Ao, Y., Li, H., Zhu, L., Ali, S., & Yang, Z. (2019). The linear random forest algorithm and its advantages in machine learning assisted logging regression modeling. Journal of Petroleum Science and Engineering, 174, 776-789.
• Avşar, Ö., & Kurtuluş, B. (2017). Köyceğiz Gölü su ve taban sedimanlarının sıcaklık dağılımı. Jeoloji Mühendisliği Dergisi, 41(2), 117-136. https://doi.org/10.24232/jmd.334546
• Bar, S., Parida, B. R., & Pandey, A. C. (2020). Landsat-8 And Sentinel-2 based forest fire burn area mapping using machine learning algorithms on GE cloud platform over Uttarakhand, Western Himalaya. Remote Sensing Applications: Society and Environment, 18, 100324. https://doi.org/10.1016/j.rsase.2020.100324
• Blaschke, T. (2010). Object based image analysis for remote sensing. ISPRS Journal of Photogrammetry and Remote Sensing, 65, 2–16. https://doi.org/10.1016/j.isprsjprs.2009.06.004
• Breiman, L., Friedman, J., Olshen, R. A., & Stone, C. J. (1984). Classification and Regression Trees (1st edition). Chapman and Hall/CRC.
• Breiman, L. (2001). Random forests. Machine Learning, 45(1), 5-32.
• Breiman, L. (2017). Classification and regression trees. Routledge.
• Corcoran, J., Knight, J., Pelletier, K., Rampi, L., & Wang, Y. (2015). The effects of point or polygon based training data on Random Forest classification accuracy of wetlands. Remote Sensing, 7(4), 4002-4025. https://doi.org/10.3390/rs70404002
• Dlamini, M., Adam, E., Chirima, G., & Hamandawana, H. (2021). A remote sensing-based approach to investigate changes in land use and land cover in the lower uMfolozi floodplain system, South Africa. Transactions of the Royal Society of South Africa, 76(1), 13–25. https://doi.org/10.1080/0035919X.2020.1858365
• European Space Agency. (2023, December 19). Introducing Sentinel-2. https://www.esa.int/Applications/ Observing_the_Earth/Copernicus/Sentinel-2/Introducing_Sentinel-2
• Gao, Y., & Mas, J. F. (2008). A Comparison of the performance of pixel-based and object-based classifications over images with various spatial resolutions. Online Journal of Earth Sciences, 2(1), 27-35.
• Gašparović, M., & Singh, S. K. (2022). Urban surface water bodies mapping using the automatic k-means based approach and sentinel-2 imagery. Geocarto International, 38(1), 2148757. https://doi.org/10.1080/10106049.2022.2148757
• Ghamisi, P., & Hoefle, B. (2017). LiDAR data classification using extinction profiles and a composite kernel support vector machine. IEEE Geoscience and Remote Sensing Letters, 14(5), 659-663.
• Google Earth Engine. (2023, December 19). FAQ. https://earthengine.google.com/faq/
• Goller.gen.tr. (2024, January 29). Köyceğiz Gölü. https://www.goller.gen.tr/koycegiz-golu.html
• 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.
• Gxokwe, S., Dube, T., & Mazvimavi, D. (2022). Leveraging Google Earth Engine Platform to characterize and map small seasonal wetlands in the semi-arid environments of South Africa. Science of The Total Environment, 803, 150139. https://doi.org/10.1016/j.scitotenv.2021.150139
• Heydarian, M., Doyle, T. E., & Samavi, R. (2022). MLCM: Multi-Label confusion matrix. IEEE Access, 10, 19083-19095. https://doi.org/10.1109/ACCESS.2022.3151048
• Congalton, R. G. (1991). A review of assessing the accuracy of classifications of remotely sensed data. Remote Sensing of Environment, 37(1), 35-46. https://doi.org/10.1016/0034-4257(91)90048-B
• Jayaswal, V., (2020, September 14). Performance metrics: Confusion matrix, Precision, Recall, and F1 Score. Towards Data Science. https://towardsdatascience.com/performance-metrics-confusion-matrix-precision-recall-and-f1-score-a8fe076a2262
• Jiang, W., Ni, Y., Pang, Z., Li, X., Ju, H., He, G., Lv, J., Yang, K., Fu, J., & 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
• Jiang, L., Zhou, C., & Li, X. (2023). Sub-Pixel Surface Water Mapping for Heterogeneous Areas from Sentinel-2 Images: A Case Study in the Jinshui Basin, China. Water, 15(8), 1446. https://doi.org/10.3390/w15081446
• 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), 3797. https://doi.org/10.3390/su14073797
• Kaplan, G., & Avdan, U. (2017). Object-based water body extraction model using Sentinel-2 satellite imagery. European Journal of Remote Sensing, 50(1), 137-143.
• Kobayashi, N., Tani, H., Wang, X., & Sonobe, R. (2020). Crop classification using spectral indices derived from Sentinel-2A imagery. Journal of Information and Telecommunication, 4(1), 67-90.
• Li, H., Zech, J., Ludwig, C., Fendrich, S., Shapiro, A., Schultz, M., & Zipf, A. (2021). Automatic mapping of national surface water with OpenStreetMap and Sentinel-2 MSI data using deep learning. International Journal of Applied Earth Observation and Geoinformation, 104, 102571. https://doi.org/10.1016/j.jag.2021.102571
• Li, J., Ma, R., Cao, Z., Xue, K., Xiong, J., Hu, M., & Feng, X. (2022). Satellite Detection of Surface Water Extent: A Review of Methodology. Water, 14(7), 1148. https://doi.org/10.3390/w14071148
• Liu, Q., Huang, C., Shi, Z., & Zhang, S. (2020). Probabilistic river water mapping from Landsat-8 using the support vector machine method. Remote Sensing, 12(9), 1374. https://doi.org/10.3390/rs12091374
• Liu, Q., Tian, Y., Zhang, L., & Chen, B. (2022). Urban Surface Water Mapping from VHR Images Based on Superpixel Segmentation and Target Detection. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 15, 5339-5356.
• Loh, W. Y. (2014). Fifty years of classification and regression trees. International Statistical Review, 82(3), 329-348. https://doi.org/10.1111/insr.12016
• Luo, C., Qi, B., Liu, H., Guo, D., Lu, L., Fu, Q., & Shao, Y. (2021). Using time series Sentinel-1 images for object-oriented crop classification in Google Earth Engine. Remote Sensing, 13(4), 561. https://doi.org/10.3390/rs13040561
• Mahdianpari, M., Salehi, B., Mohammadimanesh, F., Homayouni, S., & Gill, E. (2019). The first wetland inventory map of newfoundland at a spatial resolution of 10 m using sentinel-1 and sentinel-2 data on the Google Earth Engine cloud computing platform. Remote Sensing, 11(1), 43. https://doi.org/10.3390/rs11010043
• Mahdianpari, M., Salehi, B., Mohammadimanesh, F., Brisco, B., Homayouni, S., Gill, E., Delancey, E.R., Bourgeau-Chavez, L., (2020). Big Data for a Big Country: The First Generation of Canadian Wetland Inventory Map at a Spatial Resolution of 10-m Using Sentinel-1 and Sentinel-2 Data on the Google Earth Engine Cloud Computing Platform. Canadian Journal of Remote Sensing, 46(1), 15–33. https://doi.org/10.1080/07038992.2019.1711366
• Ministry of Environment, Urbanisation and Climate Change. (2019, October 12). Köyceğiz-Dalyan Özel Çevre Koruma Bölgesi. Retrieved October 12, 2019, from https://ockb.csb.gov.tr/koycegiz-dalyan-ozel-cevre-koruma-bolgesi-i-2753
• Ouchra B, H., Belangour, A., & Erraissi, A. (2023). Comparison of Machine Learning Methods for Satellite Image Classification: A Case Study of Casablanca Using Landsat Imagery and Google Earth Engine. Journal of Environmental & Earth Sciences, 5(2), 118-134.
• Pal, M. (2005). Random forest classifier for remote sensing classification. International Journal of Remote Sensing, 26(1), 217-222.
• Pan, H., Chen, H., Hong, Z., Liu, X., Wang, R., Zhou, R., ... & Ma, Z. (2023). A Novel Boundary Enhancement Network for Surface Water Mapping Based on Sentinel-2 MSI Data. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 16, 9207-9222. https://doi.org/10.1109/JSTARS.2023.3308046
• Phan, T. N., Kuch, V., & Lehnert, L. W. (2020). Land cover classification using Google Earth Engine and random forest classifier—The role of image composition. Remote Sensing, 12(15), 2411. https://doi.org/10.3390/rs12152411
• Sarp, G., & Ozcelik, M. (2017). Water body extraction and change detection using time series: A case study of Lake Burdur, Turkey. Journal of Taibah University for Science, 11(3), 381-391. https://doi.org/10.1016/j.jtusci.2016.04.005
• 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(3-4), 271-289. https://doi.org/10.1007/s41064-020-00111-2
• Selim, S., Çoşlu, M., Sönmez, N., & Karakuş, N. (2016). Köyceğiz Gölü ve Dalyan Kanallarında Kıyı Kenar Çizgisinin UA ve CBS Teknikleri ile Belirlenmesi, Alanda Karşılaşılan Sorunlar. Süleyman Demirel Üniversitesi Fen Bilimleri Enstitüsü Dergisi, 20(2), 254-260. https://doi.org/10.19113/sdufbed.78402
• Simioni, J. P., Guasselli, L. A., de Oliveira, G. G., Ruiz, L. F., & de Oliveira, G. (2020). A comparison of data mining techniques and multi-sensor analysis for inland marshes delineation. Wetlands Ecology and Management, 28(4), 577-594.
• Slagter, B., Tsendbazar, N. E., Vollrath, A., & Reiche, J. (2020). Mapping wetland characteristics using temporally dense Sentinel-1 and Sentinel-2 data: A case study in the St. Lucia wetlands, South Africa. International Journal of Applied Earth Observation and Geoinformation, 86, 102009. https://doi.org/10.1016/j.jag.2019.102009
• 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, 101912. https://doi.org/10.1016/j.jag.2019.101912
• Tassi, A., & Vizzari, M. (2020). Object-Oriented LULC Classification in Google Earth Engine Combining SNIC, GLCM, and Machine Learning Algorithms. Remote Sensing, 12(22), 3776. https://doi.org/10.3390/rs12223776
• Tassi, A., Gigante, D., Modica, G., Di Martino, L., & Vizzari, M. (2021). Pixel-vs. Object-Based Landsat 8 Data Classification in Google Earth Engine Using Random Forest: The Case Study of Maiella National Park. Remote Sensing, 13(12), 2299. https://doi.org/10.3390/rs13122299
• T.C. Köyceğiz Kaymakamlığı. (2023, October 12). Köyceğiz Gölü. http://www.koycegiz.gov.tr/koycegiz-golu
• Türedi, M. (2006). Köyceğiz Gölü (Limnolojik Etüt) [Yüksek lisans tezi, Marmara Üniversitesi]. YÖK Ulusal Tez Merkezi. https://tez.yok.gov.tr/UlusalTezMerkezi
• Vapnik, V. (1995). The nature of statistical learning theory. Springer.
• Wang, M., Liu, X., Gao, Y., Ma, X., & Soomro, N. Q. (2017). Superpixel segmentation: A benchmark. Signal Processing: Image Communication, 56, 28–39. https://doi.org/10.1016/j.image.2017.04.007
• Wang, G., Meng, D., Chen, R., Yang, G., Wang, L., Jin, H., ... & Feng, H. (2024). Automatic Rice Early-Season Mapping Based on Simple Non-Iterative Clustering and Multi-Source Remote Sensing Images. Remote Sensing, 16(2), 277. https://doi.org/10.3390/rs16020277
• Wangchuk, S., & Bolch, T. (2020). Mapping of glacial lakes using Sentinel-1 and Sentinel-2 data and a random forest classifier: strengths and challenges. Science of Remote Sensing, 2, 100008. https://doi.org/10.1016/j.srs.2020.100008
• Wei, X., Xu, W., Bao, K., Hou, W., Su, J., Li, H., & Miao, Z. (2020). A water body extraction methods comparison based on FengYun Satellite data: a case study of Poyang Lake Region, China. Remote Sensing, 12(23), 3875. https://doi.org/10.3390/rs12233875
• Yang, L., Wang, L., Abubakar, G. A., & Huang, J. (2021). High-resolution rice mapping based on SNIC segmentation and multi-source remote sensing images. Remote Sensing, 13(6), 1148. https://doi.org/10.3390/rs13061148
• Zhou, L., Pan, S., Wang, J., & Vasilakos, A. V. (2017a). Machine learning on big data: opportunities and Challenges. Neurocomputing, 237, 350-361. https://doi.org/10.1016/j.neucom.2017.01.026
• Zhou, Y., Dong, J., Xiao, X., Xiao, T., Yang, Z., Zhao, G., ... & Qin, Y. (2017b). Open surface water mapping algorithms: A comparison of water-related spectral indices and sensors. Water, 9(4), 256. https://doi.org/10.3390/w9040256
• Xue, H., Xu, X., Zhu, Q., Yang, G., Long, H., Li, H., ... & Li, Y. (2023). Object-Oriented Crop Classification Using Time Series Sentinel Images from Google Earth Engine. Remote Sensing, 15(5), 1353. https://doi.org/10.3390/rs15051353