Semi-automatic anomaly detection in GNSS time series using machine learning algorithms

GNSS & Satellite Geodesy

Authors

First and Last Name Academic degree E-mail Affiliation
Oleh Haidus No haidus.oleh [at] gmail.com Lviv Polytechnic National University, Lviv, Ukraine
Lviv, Ukraine
Kamil Maciuk Ph.D. maciuk [at] agh.edu.pl AGH University of Krakow, Krakow, Poland
Krakow, Poland
Іvan Brusak Ph.D. ivan.v.brusak [at] lpnu.ua Lviv Polytechnic National University, Lviv, Ukraine
Lviv, Ukraine

I and my co-authors (if any) authorize the use of the Paper in accordance with the Creative Commons CC BY license

First published on this website: 23.08.2024 - 14:14
Abstract 

The research presents semi-automatic method for anomaly detection in GNSS time series using Isolation Forest algorithm including detailed method stages as well as chosen parameters of algorithm. The method including data collection and preprocessing, isolation forest model creation and training, anomaly detection as well as results visualization are fully implemented in Python. The method includes two options for GNSS time series analysis. First include the analysis of separate time series on local anomalies both in vertical and horizontal (both North and East) components. Second allows to identify simultaneous group anomalies in the network of GNSS stations. As an example, the method is tested on 37 time series of daily solutions of Geoterrace GNSS network, Ukraine. Some detected semi-automatic anomalies coincide with those detected in previous studies such as non-tidal atmospheric loading as well as some expluatetion changes confirmed by stations log-files. The rest anomalies will require detailed consideration by geophysicists in further research.

References 

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

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

Breiman, L. (2001) Random Forests. Machine Learning 45, 5–32. https://doi.org/10.1023/A:1010933404324

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

Hariri, S., Kind, M., Brunner, R. (2021) Extended Isolation Forest in IEEE Transactions on Knowledge and Data Engineering, vol. 33, no. 4, pp. 1479-1489 https://doi.org/10.1109/TKDE.2019.2947676

Hochreiter, S., & Schmidhuber, J. (1997). Long Short-Term Memory. Neural Computation, 9(8), 1735-1780. https://doi.org/10.1162/neco.1997.9.8.1735

Liu, F., Ting, K., & Zhou, Z.-H. (2008). Isolation Forest. In 2008 Eighth IEEE International Conference on Data Mining (pp. 413-422). IEEE. https://doi.org/10.1109/ICDM.2008.17

Liu, F., Ting, K., & Zhou, Z.-H. (2012). Isolation-Based Anomaly Detection. ACM Transactions on Knowledge Discovery from Data, 6(1), Article No.: 3, pp. 1-39. https://doi.org/10.1145/2133360.2133363

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. https://doi.org/10.48550/arXiv.1201.0490

Savchyn, I., Tretyak, K., Marusazh, K., & Korliatovych, T. (2021a). Processing and analysis of measurement results of the Ukrainian GNSS station ASAV (Argentina Islands, West Antarctica). In International Conference of Young Professionals «GeoTerrace-2021» (Vol. 2021, No. 1, pp. 1-5). European Association of Geoscientists & Engineers. https://doi.org/10.3997/2214-4609.20215K3032

Savchyn, І., Otruba, Y., & Tretyak, K. (2021b). 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

Tretyak, K., Korliatovych, T., Brusak, I., (2021). Applying the statistical method of GNSS time series analysis for the detection of vertical displacements of Dnister HPP-1 dam. In International Conference of Young Professionals «GeoTerrace-2021». European Association of Geoscientists & Engineers. https://doi.org/10.3997/2214-4609.20215K3012