Detecting outliers in GNSS position time series using machine learning techniques
Hanoi University of Civil Engineering, Hanoi, Vietnam
- Received: 27th-Mar-2023
- Revised: 30th-July-2023
- Accepted: 24th-Aug-2023
- Online: 31st-Aug-2023
- Section: Civil Engineering
The Global Navigation Satellite System (GNSS) position time series is applied in studies that require high-precision positioning, such as monitoring tectonic movements and Earth deformation. Outliers in GNSS position time series can significantly impact the accuracy of station positioning and movement parameters, leading to distorted data analysis outcomes. This study investigates the effectiveness of three machine learning techniques, including-Isolation Forest, One-Class Support Vector Machines (O-C SVM), and Local Outlier Factor (LOF) for outlier detection in GNSS position time series, with a specific focus on the SYNT model where outliers account for a substantial proportion (15%). Through comprehensive analysis, our results highlight the exceptional performance of the Isolation Forest method. It demonstrates remarkable accuracy in identifying outliers, effectively detecting the majority of them, and achieving an area under the ROC curve close to 1. In contrast, the LOF method performs less effectively in outlier detection, while the O-C SVM method displays relatively higher accuracy in identifying normal data points. These findings emphasize the significant advantages of leveraging machine learning approaches in processing continuous GNSS measurement data. By effectively identifying and handling outliers, these techniques enhance the accuracy and reliability of data analysis in GNSS position time series, ultimately establishing their superiority in the field of data analysis.
Bevis, M., Jonathan, B., and Dana J., C. I. I., (2020). The Art and Science of Trajectory Modelling. In J.-P. Montillet and M. S. Bos (Eds.), Geodetic Time Series Analysis in Earth Sciences (1st ed., pp. 1–29). Springer International Publishing. https://doi.org/10.1007/978-3-030-21718-1
Breunig, M. M., Kriegel, H.-P., Ng, R. T., and Sander, J., (2000). LOF. Proceedings of the 2000 ACM SIGMOD International Conference on Management of Data, 93–104. https://doi.org/10.1145/342009.335388.
Dinh, T. T., Nguyen, D. H., Vu, N. Q., and long Nguyen, Q. (2023). Crustal displacement in Vietnam using CORS data during 2018-2021. Earth Sciences Research Journal, 27(1), 27-36. https://doi.org/10.15446/esrj.v27n1.102630
Gao, W., Li, Z., Chen, Q., Jiang, W., and Feng, Y., (2022). Modelling and prediction of GNSS time series using GBDT, LSTM and SVM machine learning approaches. Journal of Geodesy, 96(10), 71. https://doi.org/10.1007/s00190-022-01662-5.
Ito, C., Takahashi, H., and Ohzono, M., (2019). Estimation of convergence boundary location and velocity between tectonic plates in northern Hokkaido inferred by GNSS velocity data. Earth, Planets and Space, 71(1), 86. https://doi.org/10.1186/s40623-019-1065-z.
Kall, T., Oja, T., Kruusla, K., and Liibusk, A., (2021). New 3D velocity model of Estonia from GNSS measurements. Estonian Journal of Earth Sciences, 70(2), 107. https://doi.org/10.3176/earth.2021.08.
Kiani, M., (2020). A specifically designed machine learning algorithm for GNSS position time series prediction and its applications in outlier and anomaly detection and earthquake prediction. ArXiv Preprint ArXiv:2006.09067.
Klos, A., Bogusz, J. B., Bos, M. S., and Gruszczynska, M., (2020). Modelling the GNSS Time Series: Different Approaches to Extract Seasonal Signals. In J.-P. Montillet and M. S. Bos (Eds.), Geodetic Time Series Analysis in Earth Sciences (1st ed., pp. 2–4). Springer International Publishing. https://doi.org/10.1007/978-3-030-21718-1.
Métivier, L., Collilieux, X., Lercier, D., Altamimi, Z., and Beauducel, F., (2014). Global coseismic deformations, GNSS time series analysis, and earthquake scaling laws. Journal of Geophysical Research: Solid Earth, 119(12), 9095–9109. https://doi.org/10.1002/2014jb011280.
Montillet, J.-P., and Bos, M. S., (2020). Geodetic Time Series Analysis in Earth Sciences (J.-P. Montillet and M. S. Bos, Eds.; 1st ed.). Springer International Publishing. https://doi.org/10.1007/978-3-030-21718-1.
Montillet, J.-P., Williams, S. D. P., Koulali, A., and McClusky, S. C., (2015). Estimation of offsets in GPS time-series and application to the detection of earthquake deformation in the far-field. Geophysical Journal International, 200(2), 1207–1221. https://doi.org/10.1093/gji/ggu473.
Phong, D. V., Trọng, N. G., Chiến, N. V., Thành, N. H., Hà, L. L., Quân, N. V., and Quang, P. N. (2023). Phân tích chuyển dịch thẳng đứng vỏ Trái đất sử dụng hàm ANN từ kết quả xử lý chuỗi dữ liệu GNSS theo thời gian. Tạp Chí Khí Tượng Thủy Văn, 752, 41–50. https://doi.org/10.36335/VNJHM.2022(752).41-50.
Riel, B., Simons, M., Agram, P., and Zhan, Z., (2014). Detecting transient signals in geodetic time series using sparse estimation techniques. Journal of Geophysical Research: Solid Earth, 119(6), 5140–5160. https://doi.org/10.1002/2014JB011077.
Schölkopf, B., Platt, J. C., Shawe-Taylor, J., Smola, A. J., and Williamson, R. C., (2001). Estimating the Support of a High-Dimensional Distribution. Neural Computation, 13(7), 1443–1471. https://doi.org/10.1162/089976601750264965.
Teferle, F. N., Williams, S. D. P., Kierulf, H. P., Bingley, R. M., and Plag, H.-P., (2008). A continuous GPS coordinate time series analysis strategy for high-accuracy vertical land movements. Physics and Chemistry of the Earth, Parts A/B/C, 33(3–4), 205–216. https://doi.org/10.1016/j.pce.2006.11.002.
Tran, D. T., Nguyen, Q. L., and Nguyen, D. H., (2021). General Geometric Model of GNSS Position Time Series for Crustal Deformation Studies -A Case Study of CORS Stations in Vietnam. Journal of the Polish Mineral Engineering Society, 1(2), 183–198. https://doi.org/10.29227/IM-2021-02-16.
Tran, D. T., Nocquet, J.-M., Luong, N. D., and Nguyen, D. H., (2022). Determination of Helmert transformation parameters for continuous GNSS networks: a case study of the Géoazur GNSS network. Geo-Spatial Information Science, 1–14. https://doi.org/10.1080/10095020.2022.2138569.
Trần, Đ. T., Vũ, Đ. C., and Đào, D. T., (2014). Phương pháp Dikin phát hiện trị đo chứa sai số thô. Tạp Chí Khoa Học và Công Nghệ, Viện Hàn Lâm Khoa Học Việt Nam, 52(4B), 519–526. https://www.researchgate.net/publication/277599309_Phuong_phap_Dikin_phat_hien_tri_do_chua_sai_so_tho.
Tran, T. D., Dao, T. D., Vu, T. S., Luong, D. N., Vu, C. D., Bui, S. N., and Ha, H. T., (2016). Outlier detection in GNSS position time series. Science and Technology Development Journal, 19(2), 43–50. https://doi.org/10.32508/stdj.v19i2.665
Trọng, T. Đ., and Huy, N. Đ. (2023). Nghiên cứu xác định thời gian tắt dần sau động đất trong chuỗi tọa độ GNSS liên tục. Tạp chí Khoa học Công nghệ Xây dựng (KHCNXD)-ĐHXDHN. https://stce.huce.edu.vn/index.php/vn/article/view/2659.
Tsai, M.-C., Yu, S.-B., Shin, T.-C., Kuo, K.-W., Leu, P.-L., Chang, C.-H., and Ho, M.-Y. (2015). Velocity Field Derived from Taiwan Continuous GPS Array (2007 - 2013). Terrestrial, Atmospheric and Oceanic Sciences, 26(5), 527. https://doi.org/10.3319/TAO.2015.05.21.01(T).