Moscow, Russian Federation
Moscow, Russian Federation
UDC 550.34.063
UDC 55
UDC 550.34
UDC 550.383
CSCSTI 37.01
CSCSTI 37.15
CSCSTI 37.25
CSCSTI 37.31
CSCSTI 38.01
CSCSTI 36.00
CSCSTI 37.00
CSCSTI 38.00
CSCSTI 39.00
CSCSTI 52.00
Russian Classification of Professions by Education 05.00.00
Russian Library and Bibliographic Classification 26
Russian Trade and Bibliographic Classification 63
BISAC SCI SCIENCE
Machine learning models based on regression analysis methods have been selected to identify areas of maximum risk for major seismic events. The performance of nine linear and nonlinear models was evaluated, resulting in the selection of the Random Forest model. The quality of training for the Random Forest model was improved through hyperparameter tuning as well as the use of clustering and polar coordinates. It allowed the improvement of quality of model training, increasing the value of the coefficient of determination to 0.86. An analysis was conducted on the applicability of two neural networks with deep learning: Multi-layer Perceptron (MLP) and Long Short-Term Memory (LSTM), using training parameters that were selected for the Random Forest model. Using this model and selected neural networks with deep learning, areas of maximum risk for seismic events were predicted for the entire globe, with a detailed analysis of predicted areas for the territory of the Russian Federation. As a result of the conducted research, the use of neural networks with deep learning made it possible to identify a greater (~40%) number of zones of maximum seismicity (with M>6) compared to the improved Random Forest model.
earthquake, seismically hazardous areas, monitoring, machine learning models, neural networks
1. Agarwal N., Arora I., Saini H., et al. A Novel Approach for Earthquake Prediction Using Random Forest and Neural Networks // EAI Endorsed Transactions on Energy Web. — 2023. — Vol. 10. — P. 1–6. — https://doi.org/10.4108/ew.4329.
2. Ajai V., Gandhimathi U. S., Suntosh B. D. S., et al. Machine Learning-Based Seismic Activity Prediction // Utilizing AI and Machine Learning for Natural Disaster Management. — IGI Global, 2024. — P. 293–306. — https://doi.org/10.4018/979-8-3693-3362-4.ch017. DOI: https://doi.org/10.31857/S0205961422060021; EDN: https://elibrary.ru/STVHFM
3. Akhoondzadeh M. and Marchetti D. Study of the Preparation Phase of Turkey’s Powerful Earthquake (6 February 2023) by a Geophysical Multi-Parametric Fuzzy Inference System // Remote Sensing. — 2023. — Vol. 15, no. 9. — P. 2224. — https://doi.org/10.3390/rs15092224. EDN: https://elibrary.ru/IAQEKB
4. Asim K. M., Idris A., Iqbal T., et al. Earthquake prediction model using support vector regressor and hybrid neural networks // PLOS ONE. — 2018. — Vol. 13, no. 7. — e0199004. — https://doi.org/10.1371/journal.pone.0199004. EDN: https://elibrary.ru/KZMCEV
5. Bogdanov V., Gavrilov V., Pulinets S., et al. Responses to the preparation of strong Kamchatka earthquakes in the lithosphere-atmosphere-ionosphere system, based on new data from integrated ground and ionospheric monitoring // E3S Web of Conferences. — 2020. — Vol. 196. — P. 14. — https://doi.org/10.1051/e3sconf/202019603005. DOI: https://doi.org/10.7868/S000233371601004X; EDN: https://elibrary.ru/VCPGFZ
6. Bolt B. Earthquakes. A Popular Outline. — M. : Mir, 1981. — 256 p. — (In Russian). DOI: https://doi.org/10.31857/S0205961423340018; EDN: https://elibrary.ru/RHSWXV
7. Bondur V. G., Garagash I. A., Gokhberg M. B., et al. Geomechanical models and ionospheric variations related to strongest earthquakes and weak influence of atmospheric pressure gradients // Doklady Earth Sciences. — 2007. — Vol. 414, no. 1. — P. 666–669. — https://doi.org/10.1134/S1028334X07040381. DOI: https://doi.org/10.31857/S0205961422050049; EDN: https://elibrary.ru/XKMAEM
8. Bondur V. G., Garagash I. A., Gokhberg M. B., et al. Connection between variations of the stress-strain state of the Earth’s crust and seismic activity: The example of Southern California // Doklady Earth Sciences. — 2010. — Vol. 430, no. 1. — P. 147–150. — https://doi.org/10.1134/S1028334X10010320. EDN: https://elibrary.ru/NDMJLV
9. Bondur V. G., Garagash I. A., Gokhberg M. B., et al. The evolution of the stress state in Southern California based on the geomechanical model and current seismicity // Izvestiya, Physics of the Solid Earth. — 2016. — Vol. 52, no. 1. — P. 117–128. — https://doi.org/10.1134/S1069351316010043. DOI: https://doi.org/10.31857/S0205-96142019636-47; EDN: https://elibrary.ru/IUMHHK
10. Bondur V. G., Tsidilina M. N., Gaponova E. V., et al. Satellite Registration of Anomalies of Various Geophysical Fields during the Preparation of Destructive Earthquakes in Turkey in February 2023 // Izvestiya, Atmospheric and Oceanic Physics. — 2023. — Vol. 59, no. 9. — P. 1009–1027. — https://doi.org/10.1134/s0001433823090049. DOI: https://doi.org/10.31857/S0002333720010044; EDN: https://elibrary.ru/EWBACJ
11. Bondur V. G., Tsidilina M. N., Gaponova E. V., et al. Combined Analysis of Anomalous Variations in Various Geophysical Fields during Preparation of the M5.6 Earthquake near Lake Baikal on September 22, 2020, Based on Satellite Data // Izvestiya, Atmospheric and Oceanic Physics. — 2022. — Vol. 58, no. 12. — P. 1532–1545. — https://doi.org/10.1134/S0001433822120052.
12. Bondur V. G. and Voronova O. S. Detection from Space of Anomalous Variations in Thermal Fields during Seismic Events in the Northern Caucasus in 2017-2022 // Izvestiya, Atmospheric and Oceanic Physics. — 2022. — Vol. 58, no. 12. — P. 1546–1556. — https://doi.org/10.1134/S0001433822120064. EDN: https://elibrary.ru/PDTRWX
13. Ermiş İ. and Cürebal İ. Earthquake Probability Prediction with Decision Tree Algorithm: The Example of Izmir, Türkiye // Journal of Artificial Intelligence and Data Science. — 2024. — Vol. 4, no. 2. — P. 59–67.
14. Fedotov S. A. Long-Term Seismic Forecast for the Kuril-Kamchatka Arc. — M. : Nauka, 2005. — 302 p. — (In Russian).
15. Frankel A. D., Petersen M. D., Mueller C. S., et al. Documentation for the 2002 Update of the National Seismic Hazard Maps. Open-File Report 02-420. — USGS, 2002. — 33 p. DOI: https://doi.org/10.3133/ofr02420; EDN: https://elibrary.ru/JUPCNZ
16. Gaponova E. V., Zverev A. T. and Tsidilina M. N. Detecting Lineament System Anomalies during Strong 6.4 and 7.1 Earthquakes in California from Satellite Imagery // Izvestiya, Atmospheric and Oceanic Physics. — 2020. — Vol. 56, no. 9. — P. 1062–1071. — https://doi.org/10.1134/S000143382009011X.
17. Gelfand I. M., Guberman Sh. A., Izvekova M. L., et al. On Criteria of High Seismicity // Doklady Akademii Nauk SSSR. — 1972. — Vol. 202, no. 6. — P. 1317–1320. — (In Russian).
18. Gvishiani A. D., Soloviev A. A. and Dzeboev B. A. Problem of Recognition of Strong-Earthquake-Prone Areas: a State-of-the-Art Review // Izvestiya, Physics of the Solid Earth. — 2020. — Vol. 56, no. 1. — P. 1–23. — https://doi.org/10.1134/s1069351320010048.
19. Haykin S. Neural Networks: A Comprehensive Foundation. Second Edition. — 2nd ed. — New Jersey : Prentice Hall, 2006. — 1104 p. EDN: https://elibrary.ru/KFPDUV
20. Jarah N. B., Alasadi A. H. H. and Hashim K. M. A New Algorithm for Earthquake Prediction Using Machine Learning Methods // Journal of Computer Science. — 2024. — Vol. 20, no. 2. — P. 150–156. — https://doi.org/10.3844/jcssp.2024.150.156. DOI: https://doi.org/10.31857/S002342060000347-9; EDN: https://elibrary.ru/FMYAEC
21. Jiao Q., Liu Q., Lin C., et al. Spatiotemporal Analysis of Atmospheric Chemical Potential Anomalies Associated with Major Seismic Events (Ms ≥ 7) in Western China: A Multi-Case Study // Remote Sensing. — 2025. — Vol. 17, no. 2. — P. 311. — https://doi.org/10.3390/rs17020311. EDN: https://elibrary.ru/RVEBFL
22. Kashkin V. B., Romanov A. A., Grigoriev A. S., et al. Troposphere Effects of Tuva Earthquakes Detected with Spase Technology // Journal of Siberian Federal University. Engineering & Technologies. — 2012. — Vol. 5, no. 2. — P. 220–228. — (In Russian). EDN: https://elibrary.ru/YSKDSD
23. Keilis-Borok V. I. Lithosphere Dynamics and Earthquake Prediction // Priroda. — 1989. — No. 12. — P. 10–18. — (In Russian). EDN: https://elibrary.ru/QKFCPL
24. Khain V. E. and Khalilov E. N. Cycles in Geodynamic Processes: Their Possible Nature. — M. : Nauchnyi Mir, 2009. — 520 p. — (In Russian).
25. Kosobokov V. G. Earthquake Prediction and Geodynamic Processes. Part 1. Earthquake Prediction: Fundamentals, Implementation, Prospects. (Computational Seismology; Vol. 36). — M. : GEOS, 2005. — 179 p. — (In Russian).
26. Liperovsky V. A., Pokhotelov O. A., Meister K. V., et al. Physical models of coupling in the lithosphere-atmosphereionosphere system before earthquakes // Geomagnetism and Aeronomy. — 2008. — Vol. 48, no. 6. — P. 795–806. — https://doi.org/10.1134/s0016793208060133. — (In Russian). EDN: https://elibrary.ru/NRLJMH
27. Liu C. and Macedo J. Machine learning-based models for estimating seismically-induced slope displacements in subduction earthquake zones // Soil Dynamics and Earthquake Engineering. — 2022. — Vol. 160. — P. 107323. — https://doi.org/10.1016/j.soildyn.2022.107323. DOI: https://doi.org/10.4108/ew.4329; EDN: https://elibrary.ru/DSYGXP
28. Mahmoudi J., Arjomand M. A., Rezaei M., et al. Predicting the Earthquake Magnitude Using the Multilayer Perceptron Neural Network with Two Hidden Layers // Civil Engineering Journal. — 2016. — Vol. 2, no. 1. — P. 1–12. DOI: https://doi.org/10.28991/cej-2016-00000008
29. Mallouhy R., Jaoude C. A., Guyeux C., et al. Major earthquake event prediction using various machine learning algorithms // 2019 International Conference on Information and Communication Technologies for Disaster Management (ICT-DM). — IEEE, 2019. — P. 1–7. — https://doi.org/10.1109/ict-dm47966.2019.9032983. DOI: https://doi.org/10.3390/rs15092224; EDN: https://elibrary.ru/JIRJKY
30. Mignan A., Rinaldi A. P., Lanza F., et al. A Multi-LASSO model to forecast induced seismicity at enhanced geothermal systems // Geoenergy Science and Engineering. — 2024. — Vol. 236. — P. 212746. — https://doi.org/10.1016/j.geoen.2024.212746. DOI: https://doi.org/10.1371/journal.pone.0199004; EDN: https://elibrary.ru/YHZRJB
31. Mogi K. Earthquake Prediction. — Tokyo : Academic Press, 1985. — 382 p. DOI: https://doi.org/10.1051/e3sconf/202019603005; EDN: https://elibrary.ru/DUMEAA
32. Novianti P., Setyorini D. and Rafflesia U. K-Means cluster analysis in earthquake epicenter clustering // International Journal of Advances in Intelligent Informatics. — 2017. — Vol. 3, no. 2. — P. 81–89. — https://doi.org/10.26555/ijain.v3i2.100.
33. Osipov V. I., Shoigu S. K. and Sobolev G. A. Natural Hazards of Russia. Seismic Hazards. — M. : KRUK, 2000. — 296 p. — (In Russian).
34. Piscini A., Santis A. De, Marchetti D., et al. A Multi-parametric Climatological Approach to Study the 2016 AmatriceNorcia (Central Italy) Earthquake Preparatory Phase // Pure and Applied Geophysics. — 2017. — Vol. 174, no. 10. — P. 3673–3688. — https://doi.org/10.1007/s00024-017-1597-8. DOI: https://doi.org/10.3844/jcssp.2024.150.156; EDN: https://elibrary.ru/XKTDAG
35. Pushcharovsky Yu. M. Introduction into Tectonics of the Pacific Segment of the Earth. Transactions, vol. 234. — M. : Nauka, 1972. — 228 p. — (In Russian). DOI: https://doi.org/10.3390/rs17020311; EDN: https://elibrary.ru/ZEWSLK
36. Pushcharovsky Yu. M. Tectonic Provinces of the Atlantic Ocean // Geotectonics. — 2009. — No. 3. — P. 3–13. — (In Russian). DOI: https://doi.org/10.1016/j.soildyn.2022.107323; EDN: https://elibrary.ru/CBCMCU
37. Ranjan G. S. K., Verma A. K. and Radhika S. K-Nearest Neighbors and Grid Search CV Based Real Time Fault Monitoring System for Industries // 2019 IEEE 5th International Conference for Convergence in Technology (I2CT). — IEEE, 2019. — P. 1–5. — https://doi.org/10.1109/i2ct45611.2019.9033691.
38. Saito A., Tsugawa T., Otsuka Y., et al. Acoustic resonance and plasma depletion detected by GPS total electron content observation after the 2011 off the Pacific coast of Tohoku Earthquake // Earth, Planets and Space. — 2011. — Vol. 63, no. 7. — P. 863–867. — https://doi.org/10.5047/eps.2011.06.034.
39. Sherman S. I. and Zlogodukhova O. G. Seismic Belts and Zones of the Earth: Formalization of Notions, Positions in the Lithosphere, and Structural Control // Geodynamics & Tectonophysics. — 2011. — Vol. 2, no. 1. — P. 1–34. — https://doi.org/10.5800/gt-2011-2-1-0031. — (In Russian). DOI: https://doi.org/10.1016/j.geoen.2024.212746; EDN: https://elibrary.ru/GUPDHV
40. Shukla S. S., Dhanya J., Kumar P., et al. An Ensemble Random Forest Model for Seismic Energy Forecast // Natural Hazards and Earth System Sciences Discussion [preprint]. — 2024. — P. 40. — https://doi.org/10.5194/nhess-2024-129.
41. Smirnov V. M., Smirnova E. V., Tsidilina M. N., et al. Seismoinospheric variations during strong earthquakes on the example of the earthquake of 2010 in Chile // Kosmicheskie issledovaniia. — 2018. — Vol. 56, no. 4. — P. 283–292. — https://doi.org/10.31857/s002342060000347-9. — (In Russian). DOI: https://doi.org/10.1007/s00024-017-1597-8; EDN: https://elibrary.ru/YKAKYS
42. Sobolev G. A. and Ponomarev A. V. Physics of Earthquakes and Precursors. — M. : Nauka, 2003. — 270 p. — (In Russian).
43. Ulomov V. I. Seismicity of the Russian Territory // Environmental and Climate Change. Natural and Related Technogenic Catastrophes. Vol. 1. — M. : IFZ RAN, 2008. — P. 13–18. — (In Russian). DOI: https://doi.org/10.5047/eps.2011.06.034; EDN: https://elibrary.ru/PHJJEP
44. Vardaan V. K., Bhandarkar T., Satish N., et al. Earthquake trend prediction using long short-term memory RNN // International Journal of Electrical and Computer Engineering (IJECE). — 2019. — Vol. 9, no. 2. — P. 1304–1312. — https://doi.org/10.11591/ijece.v9i2.pp1304-1312.
45. Vikulin A. V., Akmanova D. R., Osipova N. A., et al. Recurrence of Strong Earthquakes and Migration of Their Sources along the Seismic Belt // Vestnik of Kamchatka State Technical University. — 2009. — No. 10. — P. 17–25. — (In Russian). DOI: https://doi.org/10.11591/ijece.v9i2.pp.1304-1312; EDN: https://elibrary.ru/RQNLRR
46. Wei M. and Gao K. Machine Learning Predicts the Slip Duration and Friction Drop of Laboratory Earthquakes in Sheared Granular Fault // Journal of Geophysical Research: Machine Learning and Computation. — 2024. — Vol. 1, no. 4. — https://doi.org/10.1029/2024JH000398. EDN: https://elibrary.ru/OGHBQV
