Analysis and Prediction of Crustal Movements Using Machine Learning on PS-InSAR Data

Öz

In this study, ground movements in the Bolvadin region were analyzed using the Synthetic Aperture Radar Interferometry (InSAR) technique. Surface deformations over different years were identified using the Persistent Scatterer (PS) InSAR method, and corresponding time series data were generated. Based on the obtained velocity data, future ground displacements were predicted using the Random Forest machine learning algorithm. During the modeling process, the two-year dataset was divided into four temporal periods. The model was trained using the first three periods to successfully predict deformation in the fourth, after which forward estimations were generated. The model’s predictions for the fourth period showed a high level of agreement with the observations, with the majority of differences falling within the ±1.5 mm range. The results demonstrate that machine learning-supported InSAR analyses contribute to the more reliable and precise detection of ground movements. Modeling velocity data from different years provides valuable insights into the identification of temporal trends. Additionally, the predicted deformations enabled a more detailed examination of the spatial and temporal distribution of ground movements in the region. This approach allows for a more comprehensive assessment of deformation processes and facilitates the effective utilization of large-scale satellite data.

Anahtar Kelimeler

• Sentinel-1
• PS-InSAR
• machine Learning
• Random forest

PS-InSAR Verileri Üzerinden Makine Öğrenimi ile Yerkabuğu Hareketlerinin Analizi ve Tahmini

Öz

Bu çalışmada, Bolvadin bölgesindeki zemin hareketleri Yapay Açıklı Uydu Radar İnterferometrisi (InSAR) tekniği ile analiz edilmiştir. Kalıcı Saçıcı (PS) InSAR yöntemi kullanılarak farklı yıllara ait yüzey deformasyonları belirlenmiş ve zaman serisi verileri oluşturulmuştur. Elde edilen hız verileri temel alınarak, Random Forest makine öğrenimi algoritmasıyla gelecekteki hareketler tahmin edilmiştir. Modelleme sürecinde iki yıllık veri seti dört döneme ayrılmış, ilk üç döneme ait verilerle yapılan eğitim sonucunda dördüncü dönemin hareketleri başarıyla tahmin edilmiş ve ardından ileriye yönelik tahminler gerçekleştirilmiştir. Modelin dördüncü döneme yönelik tahminleri, gözlemlerle yüksek uyum göstermiş ve farkların büyük kısmı ±1.5 mm sınırları içinde kalmıştır. Sonuçlar, makine öğrenimi destekli InSAR analizlerinin, zemin hareketlerinin daha güvenilir ve hassas bir şekilde belirlenmesine katkı sağladığını göstermektedir. Farklı yıllara ait hız verilerinin modellenmesi, zamansal eğilimlerin tespit edilmesi açısından önemli bilgiler sunmaktadır. Ayrıca, elde edilen deformasyon tahminleri, bölgedeki zemin hareketlerinin mekansal ve zamansal dağılımını daha ayrıntılı inceleme olanağı sağlamıştır. Bu yöntemle, deformasyon süreçleri daha kapsamlı biçimde değerlendirilerek büyük hacimli uydu verilerinin etkin kullanımı mümkün hale gelmektedir.

Anahtar Kelimeler

• Sentinel-1
• PS-InSAR
• makine öğrenimi
• rastgele orman

Kaynakça

1. Blasco, J. M. D. (2019). Persistent scatterer interferometry: A review of methods and applications. Remote Sensing, 11(8), 934. https://doi.org/10.3390/rs11080934
2. Breiman, L. (2001). Random forests. Machine Learning, 45(1), 5–32. https://doi.org/10.1023/A:1010933404324
3. Bürgmann, R., Rosen, P. A., & Fielding, E. J. (2000). Synthetic aperture radar interferometry to measure Earth's surface topography and its deformation. Annual Review of Earth and Planetary Sciences, 28(1), 169–209. https://doi.org/10.1146/annurev.earth.28.1.169
4. Ferretti, A., Prati, C., & Rocca, F. (2001). Permanent scatterers in SAR interferometry. IEEE Transactions on Geoscience and Remote Sensing, 39(1), 8–20. https://doi.org/10.1109/36.898661
5. Foumelis, M., Delgado Blasco, J. M., Brito, F., Pacini, F., Papageorgiou, E., Pishehvar, P., & Bally, P. (2022). SNAPPING services on the Geohazards Exploitation Platform for Copernicus Sentinel-1 surface motion mapping. Remote Sensing, 14(23), 6075. https://doi.org/10.3390/rs14236075
6. Ghorbanzadeh, O., Blaschke, T., Gholamnia, K., Meena, S. R., Tiede, D., & Aryal, J. (2019). Evaluation of different machine learning methods and deep-learning convolutional neural networks for landslide detection. Remote Sensing, 11(2), 196. https://doi.org/10.3390/rs11020196
7. Guo, X., Zhao, C., Li, G., Peng, M., & Zhang, Q. (2023). A multifactor-based random forest regression model to reconstruct a continuous deformation map in Xi’an, China. Remote Sensing, 15(19), 4795. https://doi.org/10.3390/rs15194795
8. Hastie, T., Tibshirani, R., & Friedman, J. (2009). The elements of statistical learning: Data mining, inference, and prediction (2nd ed.). Springer.

9. Hooper, A., Bekaert, D., Spaans, K., & Arıkan, M. (2012). Recent advances in SAR interferometry time series analysis for measuring crustal deformation. Tectonophysics, 514–517, 1–13. https://doi.org/10.1016/j.tecto.2011.10.013
10. Hooper, A., Zebker, H., Segall, P., & Kampes, B. (2004). A new method for measuring deformation on volcanoes and other natural terrains using InSAR persistent scatterers. Geophysical Research Letters, 31(23), L23611. https://doi.org/10.1029/2004GL021737
11. Joyce, K. E., Belliss, S. E., Samsonov, S. V., McNeill, S. J., & Glassey, P. J. (2009). A review of the status of satellite remote sensing and image processing techniques for mapping natural hazards and disasters. Progress in Physical Geography, 33(2), 183–207. https://doi.org/10.1177/0309133309339563
12. Malenovský, Z., Rott, H., Cihlar, J., Schaepman, M. E., García-Santos, G., Fernandes, R., & Berger, M. (2012). Sentinels for science: Potential of Sentinel-1, -2, and -3 missions for scientific observations of land, oceans, and ice. Remote Sensing of Environment, 120, 91–101. https://doi.org/10.1016/j.rse.2011.09.026
13. Ponte, R. M., Carson, M., Cirano, M., Domingues, C. M., Jevrejeva, S., Marcos, M., ... & Zhang, X. (2019). Towards comprehensive observing and modeling systems for monitoring and predicting regional-to-coastal sea level. Frontiers in Marine Science, 6, 437. https://doi.org/10.3389/fmars.2019.00437
14. Potin, P., Rosich, B., Miranda, N., & Grimont, P. (2016). Sentinel-1 mission status. Procedia Computer Science, 100, 1297–1304. https://doi.org/10.1016/j.procs.2016.09.179
15. Strozzi, T., Wiesmann, A., Kääb, A., & Schellenberger, T. (2017). Glacial and periglacial environment monitoring in the Swiss Alps using Sentinel-1 SAR interferometry. Remote Sensing, 9(12), 1238. https://doi.org/10.3390/rs9121238
16. Torres, R., Snoeij, P., Geudtner, D., Bibby, D., Davidson, M., Attema, E., ... & Rostan, F. (2012). GMES Sentinel-1 mission. Remote Sensing of Environment, 120, 9–24. https://doi.org/10.1016/j.rse.2011.05.028
17. Woodhouse, I. H. (2006). Introduction to microwave remote sensing. CRC Press. https://doi.org/10.1201/9781315272573