| Abstract PDF ENG. .PDF RUS | Full text PDF RUS |
Abstract. This study proposes an automatic classification approach for seismic events, designed to discriminate between earthquakes and anthropogenic explosions by employing the Random Forest algorithm. The model operates exclusively on features extracted from the signal recorded at a single seismic station without considering the source location or depth. The feature vector included amplitude ratios, along with temporal, spectral, and fractal parameters of the seismogram. A balanced dataset comprising more than 24000 seismic records from the Pacific Northwest Curated Seismic Dataset was utilized for training and validation. The trained classifier achieved an accuracy of about 94% on the test dataset. Feature importance analysis indicated that temporal, fractal, and spectral parameters contributed most to the classification, which is consistent with the underlying differences in the generation of natural and anthropogenic signals. The obtained results demonstrate that the proposed method ensures reliable and robust classification performance and can be applied for automatic filtering of anthropogenic events in seismic monitoring.
Keywords:
automatic classification, earthquakes, man-made explosions, machine learning, Random Forest, seismic signal, waveform features
For citation: Imashev S.A., Nigmatullin R.R. Discrimination between explosions and earthquakes based on informative seismic signal features using machine learning methods. Geosistemy perehodnykh zon = Geosystems of Transition Zones, 2025, vol. 9, No. 4, pp. 420–438. (In Russ.).
https://doi.org/10.30730/gtrz.2025.9.4.420-438, https://www.elibrary.ru/alymzd
Для цитирования: Имашев С.А., Нигматуллин Р.Р. Разделение взрывов и землетрясений на основе информативных характеристик сейсмического сигнала и методов машинного обучения. Геосистемы переходных зон, 2025, т. 9, № 4, с. 420–438.
https://doi.org/10.30730/gtrz.2025.9.4.420-438, https://www.elibrary.ru/alymzd
References
1. Kim W.Y., Aharonian V., Lerner-Lam A.L., Richards P.G. 1997. Discrimination of earthquakes and explosions in southern Russia using regional high-frequency three-component data from the IRIS/JSP Caucasus network. Bulletin of the Seismological Society of America, 87(3): 569–588. https://doi.org/10.1785/bssa0870030569
2. Hong T.-K. 2013. Seismic discrimination of the 2009 North Korean nuclear explosion based on regional source spectra. Journal of Seismology, 17(2): 753–769. https://doi.org/10.1007/s10950-012-9352-1
3. Kortstrom J., Uski M., Tiira T. 2016. Automatic classification of seismic events within a regional seismograph network. Computers & Geosciences, 87: 22–30. https://doi.org/10.1016/j.cageo.2015.11.006
4. Zhuravlev V.I., Lukk A.A., Sidorin A.Ya. 2022. On problems of detecting blasts in earthquake catalogs: Case study of Turkey and Iran. Seismic Instruments, 58: 45–54. https://doi.org/10.3103/s074792392201011x
5. Koper K.D., Burlacu R., Armstrong A.D., Herrmann R.B. 2024. Classifying small earthquakes, explosions and collapses in the western United States using physics-based features and machine learning. Geophysical Journal International, 239(2): 1257–1270. https://doi.org/10.1093/gji/ggae316
6. Habbak E.L., Abdalzaher M.S., Othman A.S., Mansour H. 2024. Enhancing the classification of seismic events with supervised machine learning and feature importance. Scientific Reports, 14(1): 30638. https://doi.org/10.1038/s41598-024-81113-7
7. Kim W., Simpson D.W., Richards P.G. 1993. Discrimination of earthquakes and explosions in the eastern United States using regional high-frequency data. Geophysical Research Letters, 20(14): 1507–1510. https://doi.org/10.1029/93GL01267
8. Del Pezzo E. 2003. Discrimination of earthquakes and underwater explosions using neural networks. Bulletin of the Seismological Society of America, 93(1): 215–223. https://doi.org/10.1785/0120020005
9. Walter W.R., Matzel E., Pasyanos M.E., Harris D.B., Gok R., Ford S.R. 2007. Empirical observations of earthquake-explosion discrimination using P/S ratios and implications for the sources of explosion S-waves. In: Proceedings of the 29th Monitoring Research Review: Ground-Based Nuclear Explosion Monitoring Technologies, p. 684–693.
10. Orlic N., Loncaric S. 2010. Earthquake-explosion discrimination using genetic algorithm-based boosting approach. Computers & Geosciences, 36(2): 179–185. https://doi.org/10.1016/j.cageo.2009.05.006
11. Wang R., Schmandt B., Kiser E. 2020. Seismic discrimination of controlled explosions and earthquakes near Mount St. Helens using P/S ratios. JGR Solid Earth, 125(10). https://doi.org/10.1029/2020jb020338
12. Saad O.M., Inoue K., Shalaby A., Sarny L., Sayed M.S. 2018. Autoencoder based features extraction for automatic classification of earthquakes and explosions. In: Proceedings of 17th International Conference on Computer and Information Science (ICIS). Singapore, p. 445–450. https://doi.org/10.1109/icis.2018.8466464
13. Kong Q., Wang R., Walter W.R., Pyle M., Koper K., Schmandt B. 2022. Combining deep learning with physics based features in explosion-earthquake discrimination. Geophysical Research Letters, 49(13). https://doi.org/10.1029/2022gl098645
14. Ertuncay D., Lorenzo A.D., Costa G. 2024. Seismic signal discrimination of earthquakes and quarry blasts in North-East Italy using deep neural networks. Pure and Applied Geophysics, 181(4): 1139–1151. https://doi.org/10.1007/s00024-024-03440-0
15. Kim S., Lee K., You K. 2020. Seismic discrimination between earthquakes and explosions using support vector machine. Sensors, 20(7): 1879. https://doi.org/10.3390/s20071879
16. Hong M., Zhang H., Wu L., Chen J., Dai L., Wang L. 2025. Using deep convolutional neural networks for earthquake and explosion classification. IEEE Access, 13: 56144–56159. https://doi.org/10.1109/access.2025.3552127
17. Houng S.E. 2017. Discrimination between natural earthquakes and explosions based on the azimuthal distribution of S/P amplitude ratios. Bulletin of the Seismological Society of America, 108(1): 218–229. https://doi.org/10.1785/0120160322
18. Silkin K.Yu. 2022. New heuristics based on wavelet analysis of a single sensor record for earthquake and explosion detection. Seismic Instruments, 58: 552–566. https://doi.org/10.3103/s0747923922050103
19. Ni Y., Hutko A., Skene F., Denolle M., Malone S., Bodin P., Hartog R., Wright A. 2023. Curated Pacific Northwest AI-ready Seismic Dataset. Seismica, 2(1). https://doi.org/10.26443/seismica.v2i1.368
20. Kharita A., Denolle M.A., West M.E. 2024. Discrimination between icequakes and earthquakes in southern Alaska: an exploration of waveform features using Random Forest algorithm. Geophysical Journal International, 237(2): 1189–1207. https://doi.org/10.1093/gji/ggae106
21. Abdalzaher M.S., Moustafa S.S.R., Abd-Elnaby M., Elwekeil M. 2021. Comparative performance assessments of machine-learning methods for artificial seismic sources discrimination. IEEE Access, 9: 65524–65535. https://doi.org/10.1109/access.2021.3076119
22. Morozov A.N. 2008. Method of identification of explosive seismicity on territories of the Arkhangelsk region. Vestnik KRAUNTs. Nauki o Zemle, 1(11): 177?184. (In Russ.).
23. Fisk M.D. 2006. Source spectral modeling of regional P/S discriminants at Nuclear Test Sites in China and the Former Soviet Union. Bulletin of the Seismological Society of America, 96(6): 2348–2367. https://doi.org/10.1785/0120060023
24. Sychev V.N., Imashev S.A. 2017. Estimation of Hurst exponent of seismic signal. Geosistemy perehodnykh zon = Geosystems of Transition Zones, 1(2): 50–61. (In Russ.). http://dx.doi.org/10.30730/2541-8912.2017.1.2.050-061
25. Imashev S., Cheshev M., Mishchenko M. 2019. Fractal analysis of seismoacoustic signals of near-surface sedimentary rocks in Kamchatka. Geofizika, 36(2): 153–169. https://doi.org/10.15233/gfz.2019.36.15
26. Breiman L. 2001. Random Forests. Machine Learning, 45(1): 5–32. https://doi.org/10.1023/a:1010933404324
27. Elkhouly S.H., Ali G. 2024. Seismic discrimination between nuclear explosions and natural earthquakes using multi-machine learning techniques. Pure and Applied Geophysics. https://doi.org/10.1007/s00024-024-03463-7
28. Pedregosa F., Varoquaux G., Gramfort A., Michel V., Thirion B., Grisel O., Blondel M., Louppe G., Prettenhofer P., Weiss R. 2011. Scikit-learn: machine learning in Python. Journal of Machine Learning Research, 12: 2825–2830.