Yinelemeli sinir ağlarıyla GNSS verilerinde birleştirilmiş ve bireysel model karşılaştırılması

Yıl 2025, Cilt: 10 Sayı: 1, 65 - 74

Merve Şimşek , Murat Taşkıran , Uğur Doğan

https://doi.org/10.29128/geomatik.1530761

Öz

Bu çalışmada, derin öğrenme algoritmalarından olan Uzun Kısa Süreli Bellek (LSTM) ve Geçitli Tekrarlayan Birim (GRU) ile GNSS istasyon verilerinin Kuzey, Doğu ve Düşey bileşenleri için ileriye dönük ayrı ayrı kestirimler yapılarak, istasyon bazında eğitilen modeller ve tüm istasyon verilerinin birlikte eğitildiği tek model performansları karşılaştırılarak model yönetiminin performanslar üzerine etkisi incelenmiştir. Her bir GNSS istasyonu için ayrı modellerin kullanıldığı Senaryo I ve toplu verilerle tek bir birleşik modelin kullanıldığı Senaryo II için model performansı, ortalama karekök hata (RMSE), ortalama mutlak hata (MAE) ve belirleme katsayısı (R²) kullanılarak Doğu, Kuzey ve Düşey bileşenler için değerlendirilmiştir. GRU algoritmasıyla Doğu bileşen için ortalama RMSE değeri Senaryo I ve II için sırayla 1.68 ve 1.67 mm, MAE değeri 1.24 ve 1.27 mm; Kuzey bileşen için RMSE değeri 1.70 ve 1.72 ve MAE değeri 1.32 ve 1.33 mm, Düşey bileşen için RMSE 4.50 ve 4.43 mm ve MAE 3.58 ve 3.50 mm’dir. Bulgular tek model yaklaşımının model yönetimini basitleştirilerek özellikle daha homojen veri özelliklerine sahip bölgelerde, ayrı ayrı eğitilmiş modellerle karşılaştırılabilir doğruluk elde edebileceğini göstermektedir.

Anahtar Kelimeler

GNSS, Zaman Serisi Kestirimi, Derin Öğrenme, Yinelemeli Sinir Ağları

Kaynakça

• Altamimi, Z., Rebischung, P., Métivier, L., & Collilieux, X. (2016). ITRF2014: A new release of the International Terrestrial Reference Frame modeling nonlinear station motions. Journal of geophysical research: solid earth, 121(8), 6109-6131.
• Bevis, M., Alsdorf, D., Kendrick, E., Fortes, L. P., Forsberg, B., Smalley Jr, R., & Becker, J. (2005). Seasonal fluctuations in the mass of the Amazon River system and Earth's elastic response. Geophysical research letters, 32(16).
• Blewitt, G., & Lavallée, D. (2002). Effect of annual signals on geodetic velocity. Journal of Geophysical Research: Solid Earth, 107(B7), ETG-9.
• Chen, Q., Jiang, W., Meng, X., Jiang, P., Wang, K., Xie, Y., & Ye, J. (2018). Vertical deformation monitoring of the suspension bridge tower using GNSS: A case study of the forth road bridge in the UK. Remote Sensing, 10(3), 364.
• Chung J, Gulcehre C, Cho K, et al (2014). Empirical evaluation of gated recurrent neural networks on sequence modeling. arXiv preprint arXiv:
• Demiryege, İ., & Ulukavak, M. (2022). Derin öğrenme tabanlı iyonosferik TEC tahmini. Geomatik, 7(2), 80-87.
• Deng, Z., Jiang, S., Mo, J., & Yu, S. (2017). Design of a new carrier tracking loop in a positioning receiver. In Automotive, Mechanical and Electrical Engineering (pp. 157-160). CRC Press.
• Hochreiter S, Schmidhuber J (1997). Long short-term memory. Neural Computation 9(8):1735–1780
• Hu, W. H., Rea, C., Yuan, Q. P., Erickson, K. G., Chen, D. L., Shen, B., ... & EAST Team. (2021). Real-time prediction of high-density EAST disruptions using random forest. Nuclear Fusion, 61(6), 066034.
• Jiang Y, Liao L, Luo H, et al (2023) Multi-scale response analysis and displacement prediction of landslides using deep learning with jtfa: A case study in the three gorges reservoir, china. Remote Sensing 15(16):3995.
• Jiang, W., Wang, J., Li, Z., Li, W., & Yuan, P. (2024). A new deep self-attention neural network for GNSS coordinate time series prediction. GPS Solutions, 28(1), 3.
• Li, X., Ge, M., Dai, X., Ren, X., Fritsche, M., Wickert, J., & Schuh, H. (2015). Accuracy and reliability of multi-GNSS real-time precise positioning: GPS, GLONASS, BeiDou, and Galileo. Journal of Geodesy, 89(6), 607-635.
• Li, Z., Chen, P., Zheng, N., & Liu, H. (2021). Accuracy analysis of GNSS-IR snow depth inversion algorithms. Advances in space research, 67(4), 1317-1332.
• Liao, K., Wu, Y., Miao, F., Li, L., & Xue, Y. (2020). Using a kernel extreme learning machine with grey wolf optimization to predict the displacement of step-like landslide. Bulletin of Engineering Geology and the Environment, 79, 673-685.
• Lian, C., Zeng, Z., Yao, W., & Tang, H. (2015). Multiple neural networks switched prediction for landslide displacement. Engineering geology, 186, 91-99.
• Meng, X., Dodson, A. H., Roberts, G. W., Cosser, E., Barnes, J., & Rizos, C. (2004). Impact of GPS Satellite Geometry on Structural Deformation Monitoring: analytical and empirical studies. Journal of Geodesy, 77(2), 809-822
• Miao, X., Liu, Y., Zhao, H., & Li, C. (2018). Distributed online one-class support vector machine for anomaly detection over networks. IEEE transactions on cybernetics, 49(4), 1475-1488.
• Mufundirwa, A., Fujii, Y., & Kodama, J. (2010). A new practical method for prediction of geomechanical failure-time. International Journal of Rock Mechanics and Mining Sciences, 47(7), 1079-1090
• Ohta, Y., Kobayashi, T., Tsushima, H., Miura, S., Hino, R., Takasu, T., ... & Umino, N. (2012). Quasi real‐time fault model estimation for near‐field tsunami forecasting based on RTK‐GPS analysis: Application to the 2011 Tohoku‐Oki earthquake (Mw 9.0). Journal of Geophysical Research: Solid Earth, 117(B2).
• Raj, N., & Brown, J. (2023). Prediction of Mean Sea Level with GNSS-VLM Correction Using a Hybrid Deep Learning Model in Australia. Remote Sensing, 15(11), 2881.
• Serwa, A., Qasimi, A. B., & Isazade, V. (2024). Registration of interferometric DEM by deep artificial neural networks using GPS control points coordinates as network target. International Journal of Engineering and Geosciences, 9(2), 292-301.
• Şimşek, M., Özarpacı, S., & Doğan, U., (2019). Yer Kabuğu Hareketlerinin Belirlenmesinde Web Tabanlı Çevrimiçi GNSS Servislerinin Performans Analizi. Geomatik , vol.4, no.2, 147-159.
• Tregoning, P., Burgette, R., McClusky, S. C., Lejeune, S., Watson, C. S., & McQueen, H. (2013). A decade of horizontal deformation from great earthquakes. Journal of Geophysical Research: Solid Earth, 118(5), 2371-2381.
• Wang, J., Nie, G., Gao, S., Wu, S., Li, H., & Ren, X. (2021). Landslide deformation prediction based on a GNSS time series analysis and recurrent neural network model. Remote Sensing, 13(6), 1055.
• Xi, R., Meng, X., Jiang, W., An, X., & Chen, Q. (2018). GPS/GLONASS carrier phase elevation-dependent stochastic modelling estimation and its application in bridge monitoring. Advances in Space Research, 62(9), 2566-2585.
• Xie, P., Zhou, A., & Chai, B. (2019). The application of long short-term memory (LSTM) method on displacement prediction of multifactor-induced landslides. IEEE Access, 7, 54305-54311.
• Xie, Y., Wang, J., Li, H., Dong, A., Kang, Y., Zhu, J., ... & Yang, Y. (2024). Deep Learning CNN-GRU Method for GNSS Deformation Monitoring Prediction. Applied Sciences, 14(10), 4004.
• Xing Y, Yue J, Chen C (2019a). Interval estimation of landslide displacement prediction based on time series decomposition and long short-term memory network. IEEE Access 8:3187–3196
• Xing Y, Yue J, Chen C, et al (2019b). Dynamic displacement forecasting of dashuitian landslide in china using variational mode decomposition and stack long short-term memory network. Applied Sciences 9(15):2951.
• Yang, B., Yin, K., Lacasse, S., & Liu, Z. (2019). Time series analysis and long short-term memory neural network to predict landslide displacement. Landslides, 16, 677-694.
• Yang, C., Yin, Y., Zhang, J., Ding, P., & Liu, J. (2024). A graph deep learning method for landslide displacement prediction based on global navigation satellite system positioning. Geoscience Frontiers, 15(1), 101690.
• Yi, T. H., Li, H. N., & Gu, M. (2013). Experimental assessment of high-rate GPS receivers for deformation monitoring of bridge. Measurement, 46(1), 420-432.
• Yu, J., Meng, X., Shao, X., Yan, B., & Yang, L. (2014). Identification of dynamic displacements and modal frequencies of a medium-span suspension bridge using multimode GNSS processing. Engineering Structures, 81, 432-443.
• Yurdakul, Ö., & Kalaycı, İ. (2022). The effect of GLONASS on position accuracy in CORS-TR measurements at different baseline distances. International journal of engineering and geosciences, 7(3), 229-246.
• Zhu X, Xu Q, Tang M, et al (2017). Comparison of two optimized machine learning models for predicting displacement of rainfall-induced landslide: A case study in sichuan province, china. Engineering Geology 218:213–222.