Application of machine learning methods to study  the relationships between seismicity  and geodynamic features  of the Dnister Hydropower Complex

Ivan Brusak; Oleg Haidus; Bohdan Kuplovskyi

doi:10.24028/gj.v48i2.350985

Authors

Ivan Brusak Lviv Polytechnic National University, Institute of Geodesy, Lviv, Ukraine, Ukraine
Oleg Haidus Lviv Polytechnic National University,Institute of Geodesy,Lviv,Ukraine, Ukraine
Bohdan Kuplovskyi Department of Seismicity of the Carpathian Region,Institute of Geophysics,National Academy of Sciences of Ukraine,Lviv,Ukraine, Ukraine

DOI:

https://doi.org/10.24028/gj.v48i2.350985

Keywords:

Seismicity, recent geodynamics, reservoir-triggered seismicity, water level changes, Dnister Hydro Power Complex, machine learning

Abstract

This study investigates the seismicity and recent geodynamic features of the Dnister Hydropower Complex in Ukraine, emphasizing the application of machine learning methods to analyze their interrelationships. The complex, situated in a seismically active transitional zone, is influenced by natural tectonic processes and anthropogenic activities, including the operations of the Dnister Hydroelectric Power Plant and active water level changes at the Dnister Reservoir. Data from digital seismic stations of the Carpathian Seismological Network, permanent Global Navigation Satellite System stations of GeoTerrace and SystemNet networks, as well as reservoir water level records of Dnister Reservoir, were collected and analyzed together. Machine learning algorithms, including Random Forest, Isolation Forest, and DBSCAN clustering, were employed to identify patterns and correlations between crustal deformations, water level fluctuations, and seismic events. Results reveal a significant association between water level changes — both short-term and long-term — and earthquake occurrences, suggesting that hydrological variations impact seismic activity. Geodynamic analysis indicates heterogeneous deformation patterns, with increased velocities in seismically active southwestern regions. Global Navigation Satellite System data shows velocities increasing by about 2 mm/year near the Dnister Hydropower Complex. Seismicity near the Dnister Hydropower Complex from 2012 to 2023 was characterized by peak earthquake years of 2014—2016 and 2022, each with over 100 events. The total seismic energy released increased from lg(ΣE)=7.5 in 2012 to 10 in 2016, then steadily declined to 7 by 2023. The findings enhance understanding of the mechanisms of induced seismicity related to reservoir operations and provide valuable insights for risk assessment and mitigation strategies in hydroelectric regions. This integrated approach demonstrates the effectiveness of machine learning in deciphering complex geodynamic and seismic interactions in tectonically sensitive environments.

References

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/istcgcap 2024.99.028.

Brusak, I., Maciuk, K., & Haidus, O. (2025). Detection of geodynamic anomalies in GNSS time series using machine learning methods. Geodynamics, 1(38), 37—48. https://doi.org/10.23939/jgd2025.01.037.

Brusak, I., Tretyak, K., & Pronyshyn, R. (2022). Preliminary studies of seismicity caused by the water level changes in Dnister upper reservoir. International Conference of Young Professionals «GeoTerrace-2022» (pp. 1—4). https://doi.org/10.3997/2214-4609.2022590022.

DBN V.1.1-12:2014. Construction in the seismic regions of Ukraine. (2014). Kyiv: Ministry of Regional Development of Ukraine (in Ukrainian).

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), 89—98. https://doi.org/10.23939/jgd 2023.02.089.

Fazilova, D., Makhmudov, M., & Khalimov, B. (2025). The analysis of crustal deformation patterns in the Tashkent region, Uzbekistan, derived from GNSS data over the period 2018–2023. Geodesy and Geodynamics, 16(2), 137—146. https://doi.org/10.1016/j.geog.2024.07.001.

Hurskyi, D.S., & Kruglov, S.S. (Eds.). (2007). Tectonic map of Ukraine.1:1000 000. Kyiv: Publ. of the Ukrainian State Geological Prospecting Institute, 95 p. (in Ukrainian).

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.

Kao, H., Hyndman, R., Jiang, Y., Visser, R., Smith, B., Babaie Mahani, A., Lucinda, L., Hadi, G. & He, J. (2018). Induced seismicity in western Canada linked to tectonic strain rate: Implications for regional seismic hazard. Geophysical Research Letters, 45(20), 1—12. https://doi.org/10.1029/2018GL079288.

Naumowicz, B., Kowalczyk, K., & Pelc-Mieczkowska, R. (2024). PPP Solution-based model of absolute vertical movements of the Earth’s crust in Poland with consideration of geological, tectonic, hydrological and mineral information. Earth and Space Science, 11(12), e2023EA003268. https://doi.org/10.1029/2023EA003268.

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.

Pospisil, L., Bartonek, D., Hefty, J., & Machotka, R. (2019). Geodetic Signs of the Recent Kinematical and Geodynamical Deformation of the Carpathian Arc. IOP Conference Series: Earth and Environmental Science (Vol. 221, No 1, p. 012001). https://doi.org/10.1088/1755-1315/221/1/012001.

Pronyshyn, R., Kuplovskyi, B., Prokopyshyn, V., Stetskiv, O., Nischimenko, I., Keleman, I., Gerasymenyuk, G., & Batіuk, A. (2024). Seismicity of the Carpathians in 2023. Geofizychnyi Zhurnal, 46(5), 82—92. https://doi.org/10.24028/gj.v46i5.309221 (in Ukrainian).

Pronyshyn, R., Kuplovskyi, B., Prokopyshyn, V., Stetskiv, O., Nischimenko, I., Keleman, I., Gerasymenyuk, H., & Batiuk, A. (2025). The seismicity of the Carpathians in 2024. Geofizychnyi Zhurnal, 47(5), 95—105. https://doi.org/10.24028/gj.v47i5.335308 (in Ukrainian).

Sarnavski, V., & Ovsiannikov, M. (2005). Tectonic structure and geodynamic mode of rock masses in the zone of interaction with hydromechanical structures of HPP and PSPP (on the example of the Dnister complex hydro unit). In Modern achievements of geodetic science and production (pp. 193—206). Lviv: Publ. house of the National University «Lviv Polytechnic» (in Ukrainian).

Savchyn, I., & Pronyshyn, R. (2020) Differentiation of recent local geodynamic and seismic processes of technogenic-loaded territories based on the example of Dnister Hydro Power Complex (Ukraine). Geodesy and Geodynamics, 11(5), 391—400. https://doi.org/10.1016/j.geog.2020.06.001.

Sidorov, I., Perij, S., & Sarnavski, V. (2015). Determination of the earth surface movements in areas of Dnister PSPP using satellite and ground geodetic methods. Geodynamics, 19(2), 15—25. https://doi.org/10.23939/jgd2015.02.015 (in Ukrainian).

State geological map of Ukraine on scale of 1:200.000. sheets M-35-XXVIII (Bar). M-35-XXXIV (Mohyliv-Podilskyi (within Ukraine). (2007). Ministry of Environmental Protection of Ukraine. State Geological Service UkrDGRI, 206 p. (in Ukrainian).

Tretyak, K., Brusak, I., Savchuk, N., Kozak, A., & Babchenko, V. (2025). Geodynamic features of territories around Ukraine’s hydroelectric power plants based on GNSS CORS data. Geodynamics, 2(39), 70—82. https://doi.org/10.23939/jgd2025.02.070.

Tretyak, K., Brusak, I., & Babchenko, V. (2024a). Recent deformations of the Earth’s crust in Ukraine based on GNSS network data from Geoterrace and System.Net. Geodynamics,

(37), 56—68. https://doi.org/10.23939/jgd2024. 02.056.

Tretyak, K., Brusak, I., & Pronyshyn, R. (2024b). Reservoir-triggered seismicity: case study of the Dnister Hydro Power Complex (Ukraine). Geofizychnyi Zhurnal, 46(1), 38—51. https://doi.org/10.24028/gj.v46i1.298659.

Tretyak, K., & Romaniuk, V. (2018). The research of interrelation between seismic activity and modern vertical movements of the European permanent GNSS-stations. Acta Geodynamics et Geomaterial, 15(2), 143—164. https://doi.org/10.13168/AGG.2018.0010.

Ukrhydroenergo. (2025). Ukrhydroenergo — the leading hydropower company in Ukraine. Ukrhydroenergo. Retrieved from https://uhe.gov.ua/diyalnist/proekti.

Verbytskyi, S.T., Verbytskyi, Y.T., Stetskiv, O.T., & Nischimenko, I.M. (2019). Automated subsystem for processing and analyzing seismic data from the Carpathian region. Geofizicheskiy Zhurnal, 41(2), 171—181. https://doi.org/ 10.24028/gzh.0203-3100.v41i2.2019.164467 (in Ukrainian).

Wu, S., Ouyang, H., Li, H., Li, Z., Li, H., & He, Y. (2025). GNSS time series analysis of the crustal movement network of China: Detecting the optimal order of the polynomial term and its effect on the deterministic model. Geodesy and Geodynamics, 16(4), 378—386. https://doi.org/10.1016/j.geog.2024.12.002.

Zyhar, A., Yushchenko, Yu., & Savchyn, I. (2023). A study of the influence of water level fluctuations on the geodynamic situation in the natural and technical geosystem of the Dnister HPP and PSPP cascade. Geodesy, Cartography and Aerial Photography, (97), 24—31. https://doi.org/10.23939/istcgcap2023.97.024.