1. JGD
  2. All Volumes and Issues
  3. 1(38)2025
  4. Detection of geodynamic anomalies in GNSS time series using machine learning methods

Detection of geodynamic anomalies in GNSS time series using machine learning methods

JGD.
2025;
Volume 1(38)2025, Number 1(38)
: 37-48
https://doi.org/10.23939/jgd2025.01.037
Received: April 12, 2025
Authors:
  1. Ivan Brusak
  2. Kamil Maciuk
  3. Oleh Haidus
1
Department of Higher Geodesy and Astronomy of Lviv Polytechnic National University
2
AGH University of Krakow
3
Lviv Polytechnic National University

One of the applied geodetic tasks in geodynamics is the detection of anomalous deviations in GNSS time series, which may indicate deformations of the Earth's surface caused by various geophysical phenomena. It is important to note that geodynamic anomalies may be of a local nature, manifesting at a single GNSS station, or of a regional nature, occurring simultaneously across a group of GNSS time series. The objective of this article is to develop a method for detecting geodynamic anomalies in GNSS time series using machine learning algorithms. The method has been implemented in the Python environment and allows for the semi-automated analysis of large datasets. Among the machine learning methods, the Isolation Forest algorithm was selected for this study. The research provides a detailed step-by-step description of the program’s operation and its stages, enabling the analysis of both individual time series for identifying local anomalies and groups of time series for detecting concurrent regional geodynamic anomalies. The developed method was tested on data from 37 GNSS stations of the GeoTerrace network located in western Ukraine. As a result, seven distinct groups of horizontal and vertical anomalies were identified. One of the detected anomalies was established to correspond with previously investigated vertical crustal deformations caused by non-tidal atmospheric loading in December 2019. The study presents maps of the spatial distribution of the detected group height anomalies in November 2022 and January 2013. Some anomalies observed at certain GNSS stations are of unknown origin and may be due to unidentified local geodynamic factors or measurement errors. In addition to its relevance for geophysicists and geologists in detecting collective geodynamic anomalies, the proposed method also demonstrates potential for use in structural health monitoring of large engineering constructuctions using data from GNSS station networks.

GNSS time series
geodynamic anomalies
anomaly detection
machine learning algorithms
Isolation Forest
GeoTerrace GNSS network
  1. Bem, A. (2024). Seasonal variations of permanent stations in close vicinity to tectonic plate boundaries. Journal of Applied Geodesy. Advance online publication. https://doi.org/10.1515/JAG-2024-0080
  2. Bhardwaj, S. C., Shekhar, S., Vidyarthi, A., & Prakash, R. (2020). Satellite navigation and sources of errors in positioning: A review. In 2020 International Conference on Advances in Computing, Communication & Materials (ICACCM) (pp. 1-7). https://doi.org/10.1109/ICACCM50413.2020.9212941
  3. Breiman, L. (2001). Random forests. Machine Learning, 45(5-32). https://doi.org/10.1023/A:1010933404324
  4. Brusak, I., & Tretyak, K. (2020). About the phenomenon of subsidence in continental Europe in December 2019 based on the GNSS stations data. In International Conference of Young Professionals “GeoTerrace-2020” (Vol. 2020, No. 1, pp. 1-5). European Association of Geoscientists & Engineers. https://doi.org/10.3997/2214-4609.20205717
  5. Brusak, I., & Tretyak, K. (2021). On the impact of non-tidal atmospheric loading on the GNSS stations of regional networks and engineering facilities. In International Conference of Young Professionals “GeoTerrace-2021” (Vol. 2021, No. 1, pp. 1-5). European Association of Geoscientists & Engineers. https://doi.org/10.3997/2214-4609.20215K3013
  6. Brusak, I., Babchenko, V., Savchuk, N., Marchuk, V., Shkvarok, Y., & Turianytsia, M. (2024). New challenges for exploitation of continuously operating reference GNSS stations during hostilities. Case study of Ukraine. Geodesy Cartography and Aerial Photography, (99), 28-37. https://doi.org/10.23939/istcgcap2024.99.028
  7. Butt, J., Wieser, A., Gojcic, Z., & Zhou, C. (2021). Machine learning and geodesy: A survey. Journal of Applied Geodesy, 15(2), 117–133. https://doi.org/10.1515/jag-2020-0043
  8. Costantino, G., Giffard-Roisin, S., Dalla Mura, M., & Socquet, A. (2024). Denoising of geodetic time series using spatiotemporal graph neural networks: Application to slow slip event extraction. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing. Advance online publication. https://doi.org/10.48550/arXiv.2405.03320
  9. Doskich, S. (2021). Deformations of the land crust of the Carpathian region according to the data of GNSS observation. Geodesy Cartography, and Aerial Photography, 93(1), 35-41. https://doi.org/ 10.23939/istcgcap2021.93.035
  10. Doskich, S., Savchuk, S., Dzhuman, B. (2023) Determination of horizontal deformation of the Earth's crust on the territory of Ukraine based on GNSS measurements. Geodynamics, 2 (35), pp. 89-98. https://doi.org/10.23939/jgd2023.02.089
  11. Doskich, S., & Serant, O. M. (2024). Verification of GNSS stations from the GeoTerrace network for further geodynamic studies using PS-NETM software. In International Conference of Young Professionals “GeoTerrace-2024” (Vol. 2024, No. 1, pp. 1-5). European Association of Geoscientists & Engineers. https://doi.org/10.3997/2214-4609.2024510008
  12. Earth System Modelling at GFZ. (n.d.). Retrieved April 19, 2025, from http://esmdata.gfz-potsdam.de
  13. Haidus, O., & Brusak, I. (2024). Development of the method for detecting anomalies in GNSS time series using machine learning algorithms. Modern Achievements of Geodesic Science and Industry, 2(48), 67–75. https://doi.org/10.33841/1819-1339-2-48-67-75
  14. Haidus, O., Maciuk, K., & Brusak, I. (2024). Semi-automatic anomaly detection in GNSS time series using machine learning algorithms. In International Conference of Young Professionals “GeoTerrace-2024” (Vol. 2024, No. 1, pp. 1-5). European Association of Geoscientists & Engineers. https://doi.org/10.3997/2214-4609.2024510048
  15. Hariri, S., Kind, M., & Brunner, R. (2021). Extended isolation forest. IEEE Transactions on Knowledge and Data Engineering, 33(4), 1479–1489. https://doi.org/10.1109/TKDE.2019.2947676
  16. Heizmann, M., & Braun, A. (2022). Implementing machine learning: Chances and challenges. Automatisierungstechnik. https://doi.org/10.1515/auto-2021-0149
  17. Khoda, O. (2024). Estimation of velocities of Ukrainian GNSS stations in the IGb08 reference frame. Kinematics and Physics of Celestial Bodies, 40(5), 257–268. https://doi.org/10.3103/S0884591324050039
  18. Li, M., Su, M., Zhang, B., & Yue, Y. (2025). Research on a DBSCAN-IForest optimisation-based anomaly detection algorithm for underwater terrain data. Water, 17(5), 626. https://doi.org/10.3390/w17050626
  19. Liu, F., Ting, K., & Zhou, Z.-H. (2008). Isolation forest. In Eighth IEEE International Conference on Data Mining (pp. 413–422). IEEE. https://doi.org/10.1109/ICDM.2008.17
  20. Liu, F., Ting, K., & Zhou, Z.-H. (2012). Isolation-based anomaly detection. ACM Transactions on Knowledge Discovery from Data, 6(1), 3. https://doi.org/10.1145/2133360.2133363
  21. Maciuk, K. (2016). The study of seasonal changes of permanent station coordinates based on weekly EPN solutions. Artificial Satellites, 51(1), 1–18. https://doi.org/10.1515/arsa-2016-0001
  22. Michel, A., Santamaría-Gómez, A., Boy, J. P., Perosanz, F., & Loyer, S. (2021). Analysis of GNSS displacements in Europe and their comparison with hydrological loading models. Remote Sensing, 13(22), 4523. https://doi.org/10.3390/rs13224523
  23. Nguyen, H. D. Q., & Tran, T. D. (2023). Detecting outliers in GNSS position time series using machine learning techniques. Journal of Mining and Earth Sciences, 64(4), 22–30. https://doi.org/10.46326/JMES.2023.64(4).03
  24. Nguyễn, H. D. Q., Pham, Q. N., Tran, V. D., et al. (2024). Application of outlier detection methods in GNSS time series analysis. Inżynieria Mineralna, (2), 95–102. https://doi.org/10.29227/IM-2024-02-95
  25. Özbey, V., Ergintav, S., & Tarı, E. (2024). GNSS time series analysis with machine learning algorithms: A case study for Anatolia. Remote Sensing, 16(17), 3309. https://doi.org/10.3390/rs16173309
  26. Özarpacı, S., Kılıç, B., Bayrak, O. C., et al. (2024). Machine learning approach for GNSS geodetic velocity estimation. GPS Solutions, 28, 65. https://doi.org/10.1007/s10291-023-01607-1
  27. Pedregosa, F., Varoquaux, G., Gramfort, A., Michel, V., Thirion, B., Grisel, O., Blondel, M., Prettenhofer, P., Weiss, R., Dubourg, V., Vanderplas, J., Passos, A., Cournapeau, D., Brucher, M., Perrot, M., & Duchesnay, E. (2011). Scikit-learn: Machine learning in Python. Journal of Machine Learning Research, 12, 2825–2830.
  28. Pierdicca, R., & Paolanti, M. (2022). GeoAI: A review of artificial intelligence approaches for the interpretation of complex geomatics data. Geoscientific Instrumentation, Methods and Data Systems, 11, 195–218. https://doi.org/10.5194/gi-11-195-2022
  29. Pipitone, C., Maltese, A., Lo Brutto, M., & Dardanelli, G. (2023). A review of selected applications of GNSS CORS and related experiences at the University of Palermo (Italy). Remote Sensing, 15(22), 5343. https://doi.org/10.3390/rs15225343
  30. Ramavath, A. K., & Perumalla, N. K. (2023). A machine-learning approach to estimate satellite-based position errors. Journal of Applied Geodesy, 18(2), 335–344. https://doi.org/10.1515/jag-2023-0051
  31. Savchuk, S., Doskich, S., Gołda, P., & Rurak, A. (2023). The seasonal variations analysis of permanent GNSS station time series in the central-east of Europe. Remote Sensing, 15(15), 3858. https://doi.org/10.3390/rs15153858
  32. Savchuk, S., Dvulit, P., Kerker, V., Michalski, D., & Michalska, A. (2024). Python Software Tool for Diagnostics of the Global Navigation Satellite System Station (PS-NETM)–Reviewing the New Global Navigation Satellite System Time Series Analysis Tool. Remote Sensing, 16(5), 757. https://doi.org/10.3390/rs16050757
  33. Savchyn, I., Otruba, Y., & Tretyak, K. (2021). The first Ukrainian permanent GNSS station in Antarctica: Processing and analysis of observation data. Ukrainian Antarctic Journal, (2), 3–11. https://doi.org/10.33275/1727-7485.2.2021.674
  34. Savchyn, I., Tretyak, K., Petrov, S., Zaiats, O., & Brusak, I. (2019). Monitoring of mine fields at Stebnyk potassium deposit area by a geodetic and geotechnical method. In First EAGE Workshop on Assessment of Landslide and Debris Flows Hazards in the Carpathians (Vol. 2019, No. 1, pp. 1-5). European Association of Geoscientists & Engineers. https://doi.org/10.3997/2214-4609.201902169
  35. Search Earthquake Catalog at USGS. (n.d.). Retrieved April 19, 2025, from https://earthquake.usgs.gov/earthquakes/search/
  36. Steigenberger, P. (2017). Accuracy of current and future satellite navigation systems (Doctoral dissertation). Technische Universität München.
  37. Tretyak, K., Bisovetskyi, Y., Savchyn, I., Korlyatovych, T., Chernobyl, O., & Kukhtarov, S. (2024a). Monitoring of spatial displacements and deformation of hydraulic structures of hydroelectric power plants of the Dnipro and Dnister cascades (Ukraine). Journal of Applied Geodesy, 18(2), 345–357. https://doi.org/10.1515/jag-2023-0021
  38. Tretyak, K., Brusak, I., & Babchenko, V. (2024b). Recent deformations of the Earth’s crust in Ukraine based on GNSS network data from GeoTerrace and SYSTEM.NET. Geodynamics, 2(37), 56–68. https://doi.org/10.23939/jgd2024.02.056
  39. Williams, S. D. P., & Penna, N. T. (2011). Non-tidal ocean loading effects on geodetic GPS heights. Geophysical Research Letters, 38(14). https://doi.org/10.1029/2011GL046940