| Abstract PDF ENG. .PDF RUS | Full text PDF ENG |
Abstract. The study addresses the pressing scientific challenge of identifying informative features in the electromagnetic regular noise background of the VLF (very low frequency) range, which is related to creating a model for earthquake prediction. The aim of the study is to develop and test a methodology for detecting informative features by analyzing the power spectral density of electromagnetic radiation, using deep machine learning technologies. During the research, a comprehensive approach was applied, which included continuous monitoring of electromagnetic signals in the VLF range (0.3–30 kHz), as well as the data processing using convolutional neural networks. Based on the analysis of a dataset of Kamchatka earthquakes from 2016 to 2019 which included 29 major seismic events significant results were obtained: an original data preparation methodology for neural network classification was developed; high recognition accuracy (up to 96 %) was achieved; and the presence of earthquake precursors in the electromagnetic regular noise background of the VLF range was confirmed. The scientific novelty of the study lies in the development of a new approach for preparing input data in a graphical format and the application of modern neural network technologies for analyzing geophysical signals. This has made it possible to identify hidden patterns that precede seismic events. The practical significance of the study consists in creating a tool for monitoring earthquake precursors. This tool contributes to the development of early warning systems and confirms the potential of applying machine learning methods to analyze geophysical data and forecast natural phenomena.
Keywords:
earthquake, precursors, electromagnetic radiation, neural network analysis
For citation: Senkevich Yu.I., Malkin E.I., Druzhin G.I. Methodology for detecting for informative features before earthquakes in the electromagnetic regular noise background of the VLF range. Geosistemy perehodnykh zon = Geosystems of Transition Zones, 2026, vol. 10, No. 2, p. 225–237. (In Russ.).
https://doi.org/10.30730/gtrz.2026.10.2.225-237, https://www.elibrary.ru/gbwhpy
Äëÿ öèòèðîâàíèÿ: Ñåíêåâè÷ Þ.È., Ìàëêèí Å.È., Äðóæèí Ã.È. Ìåòîäèêà ïîèñêà èíôîðìàòèâíûõ ïðèçíàêîâ ïåðåä çåìëåòðÿñåíèÿìè â ýëåêòðîìàãíèòíîì ðåãóëÿðíîì øóìîâîì ôîíå ÎÍ×-äèàïàçîíà. Ãåîñèñòåìû ïåðåõîäíûõ çîí. 2026, ò. 10, ¹ 2, ñ. 225–237.
https://doi.org/10.30730/gtrz.2026.10.2.225-237, https://www.elibrary.ru/gbwhpy
References
1. Vershinin E.F. [Low-frequency noise emissions of the outer ionosphere and magnetosphere]: extended abstr. of diss. … Dr. of Sci. (Physics and Mathematics). Irkutsk, 1983, 28 p. (In Russ.).
2. Vershinin E.F., Ponomarev E.A. [On classification of continuous ULF radiation of the upper atmosphere]. In: Terrestrial magnetism, auroras and ultra-low-frequency radiation. Irkutsk: SibIZMIR, 1966, p. 35–43. (In Russ.).
3. Druzhin G.I., Toropchinova T.V., Shapaev V.I. Regular noise background in VLF radiation and world thunderstorm centers. Geomagnetizm i aeronomiya = Geomagnetism and Aeronomy. 1986,26(2):258. (In Russ.).
4. Druzhin G.I. Daily periods in VLF radiation and their connection with X-ray. Mezhdunarodnyy nauchno-issledovatel'skiy zhurnal = International Research Journal. 2015,8-2(39):98–102. (In Russ.).
5. Raspopov O.M. (ed.) [Low-frequency emissions in the Earth’s ionosphere and magnetosphere]. Apatity: Kol. fil. AN SSSR, 1981, 167 p. (In Russ.).
6. Druzhin G.I. Experience of Kamchatka earthquake prediction based on observations of electromagnetic VLF radiation. Vulkanologiya i seysmologiya = Volcanology and Seismology. 2002,6:51–62. (In Russ.).
7. Asada T., Baba H., Kawazoe K., Sugiura M. An attempt to delineate very low frequency electromagnetic signals associated with earthquakes. Earth, Planets and Space. 2001,53:55–62. https://doi.org/10.1186/BF03352362
8. Eftaxias K., Kapiris P., Polygiannakis J., Peratzakis A., Kopanas J., Antonopoulos G., Rigas D. Experience of short term earthquake precursors with VLF-VHF electromagnetic emissions. Natural Hazards and Earth System Sciences. 2002,20:1–12. https://doi.org/10.5194/nhess-3-217-2003
9. Hayakawa M. Earthquake prediction with electromagnetic phenomena. AIP Conference Proceedings. 2016,17090(20002). https://doi.org/10.1063/1.4941201
10. Uvarov V.N. Characteristic patterns of electromagnetic manifestation of lithosphere dynamics. Vestnik KRAUNTs. Fiziko-matematicheskiye nauki = Bulletin of KRAESC. Physical and Mathematical Sciences. 2018,2(22):112–127. (In Russ.).
11. Gershenzon N., Bambakidis G. Modeling of seismo-electromagnetic phenomena. Russian Journal of Earth Sciences. 2001,3(4):247–275. https://doi.org/10.2205/2001ES000058
12. Wang J.-H. Piezoelectricity as a mechanism on generation of electromagnetic precursors before earthquakes. Geophysical Journal International. 2020,224(1):682–700. https://doi.org/10.1093/gji/ggaa429
13. Zhao J., Gao Y., Cheng Q., Zhou G., Chen C.-H., Zhang X., Sun Y.-Y. Numerical simulation of electromagnetic responses to an earthquake source due to the piezoelectric effect of '?m' symmetry. Journal of Geophysical Research: Solid Earth. 2024,129(5),e2023JB027756. https://doi.org/10.1029/2023JB027756
14. Wang W., Xue X., Shan J. Theoretical models of seismic electromagnetic radiation based on piezoelectric effects. Indian Journal of Geo-Marine Sciences. 2015,44(9):1275–1281.
15. Surkov V.V., Molchanov O.A., Hayakawa M. Pre-earthquake ULF electromagnetic perturbations as a result of inductive seismomagnetic phenomena during microfracturing. Journal of Atmospheric and Solar-Terrestrial Physics. 2003(2002),65(1):31–46. https://doi.org/10.1016/S1364-6826(02)00117-7
16. Salikhov N., Shepetov A., Pak G., Nurakynov S., Ryabov V., Zhukov V. Seismogenic effects in variation of the ULF/VLF emission in a complex study of the lithosphere–ionosphere coupling before an M6.1 earthquake in the region of Northern Tien Shan. Geosciences. 2025,15(6):203. https://doi.org/10.3390/geosciences15060203
17. Park S.K. Precursors to earthquakes: Seismoelectromagnetic signals. Surveys in Geophysics. 1996,17:493–516. https://doi.org/10.1007/BF01901642
18. Park S.K., Johnston M.J.S., Madden T.R., Morgan F.D., Morrison H.F. Electromagnetic precursors to earthquakes in the ULF band: a review of observations and mechanisms. Reviews of Geophysics. 1993,31:117–132. https://doi.org/10.1029/93RG00820
19. Nagao T., Enomoto Y., Fujinawa Y., Hata M., Hayakawa M., Huang Q., Izutsu J., Kushida Y., Maeda K., Oike K., Uyeda S., Yoshino T. Electromagnetic anomalies associated with 1995 Kobe earthquake. Journal of Geodynamics. 2002,33:349–359. https://doi.org/10.1016/S0264-3707(02)00004-2
20. Enomoto Y., Zheng Z. Possible evidences of earthquake lightning accompanying the 1995 Kobe earthquake inferred from the Nojima Fault Gouge. Geophysical Research Letters. 1998,25:2721–2724. https://doi.org/10.1029/98GL02015
21. Hayakawa M., Hobara Y., Ohta K., et al. The ultra-low-frequency magnetic disturbances associated with earthquakes. Earthquake Science. 2011,24:523–534. https://doi.org/10.1007/s11589-011-0814-2
22. Devi M., Barbara A.K., Ruzhin Ya.Yu., Hayakawa M. Over-the-horizon anomalous VHF propagation and earthquake precursors. Surveys in Geophysics. 2012,33(5):1081–1106. https://doi.org/10.1007/s10712-012-9185-z
23. Hayakawa M., Itoh T., Hattori K., Yumoto K. ULF electromagnetic precursors for an earthquake at Biak, Indonesia on 17 February 1996. Geophysical Research Letters. 2000,27:1531–1534. https://doi.org/10.1029/1999GL005432
24. Ida Y., Yang D., Li Q., Sun H., Hayakawa M. Detection of ULF electromagnetic emissions as a precursor to an earthquake in China with an improved polarization analysis. Natural Hazards and Earth System Sciences. 2008,8:775–777. https://doi.org/10.5194/nhess-8-775-2008
25. Johnston M.J.S. Review of electric and magnetic fields accompanying seismic and volcanic activity. Surveys in Geophysics. 1997,18:441–475. https://doi.org/10.1023/a:1006500408086
26. Shvets A.V., Hayakawa M., Molchanov O.A., et al. A study of ionospheric response to regional seismic activity by VLF radio sounding. Physics and Chemistry of the Earth. 2004,29:627–637. https://doi.org/10.1016/j.pce.2003.08.063
27. Hayakawa M. Review of subionospheric VLF/LF radio signals for the study of seismogenic lower-ionospheric perturbations. Atmosphere. 2025,16(11):1312. https://doi.org/10.3390/atmos16111312
28. Uyeda S., Nagao T., Hattori K., Hayakawa M., Miyaki K., Molchanov O., Gladychev V., Baransky L., Chtchekotov A., Fedorov E., Pokhotelov O., Andreevsky S., Rozhnoi A., Khabazin Y., Gorbatikov A., Gordeev E., Chebrov V., Sinitzin V., Lutikov A., Yunga S., Kosarev G., Surkov V., Belyaev G. Geophysical observatory in Kamchatka region for monitoring of phenomena connected with seismic activity. Natural Hazards and Earth System Sciences. 2001,1:3–7. https://doi.org/10.5194/nhess-1-3-2001
29. Gokhberg M.B., Gufeld I.L., Rozhnoy A.A., Marenko V.F., Yampolsky V.S., Ponomarev E.A. Study of seismic influence on the ionosphere by super long-wave probing of the Earth-ionosphere wave-guide. Physics of the Earth and Planetary Interiors. 1989,57:64–67. https://doi.org/10.1016/0031-9201(89)90214-8
30. Buzevich A.V., Druzhin G.I., Firstov P.P., et al. Heliogeophysical effects preceding the Kronotskoye earthquake of December 5, 1997. In: [Kronotskoye earthquake in Kamchatka on December 5, 1997. Precursors, features, consequences]. Petropavlovsk-Kamchatsky, 1999, p. 177–188. (In Russ.).
31. Hulbert C., Rouet-Leduc B., Johnson P.A., Ren C.X., Riviere J., Bolton D.C., Marone C. Similarity of fast and slow earthquakes illuminated by machine learning. Nature Geoscience. 2018,12:69–74. https://doi.org/10.1038/s41561-018-0272-8
32. Rouet-Leduc B., Hulbert C., Lubbers N., Barros K., Humphreys C.J., Johnson P.A. Machine learning predicts laboratory earthquakes. Geophysical Research Letters. 2017,44(18):9276–9282. https://doi.org/10.1002/2017GL074677
33. Pu Y., Apel D.B., Wei C. Applying machine learning approaches to evaluating rockburst liability: A comparison of generative and discriminative models. Pure and Applied Geophysics. 2019,176:4503–4517. https://doi.org/10.1007/s00024-019-02197-1
34. Mousavi S.M., Horton S.P., Langston C.A., Samei B. Seismic features and automatic discrimination of deep and shallow induced-microearthquakes using neural network and logistic regression. Geophysical Journal International. 2016,207(1):29–46. https://doi.org/10.1093/gji/ggw258
35. Sharma M., Arora M. Prediction of seismicity cycles in the Himalayas using artificial neural network. Acta Geophysica Polonica. 2005,53(3):299–309.
36. Nardi A., Pignatelli A., Spagnuolo E. A neural network based approach to classify VLF signals as rock rupture precursors. Scientific Reports. 2022,12,13744. https://doi.org/10.1038/s41598-022-17803-x
37. Lawhern V.J., Solon A.J., Waytowich N.R., et al. EEGNet: a compact convolutional neural network for EEG-based brain-computer interfaces. Journal of Neural Engineering. 2018,15(5),056013. https://doi.org/10.1088/1741-2552/aace8c
38. Ince T., Kiranyaz S., Gabbouj M.A. Generic and robust system for automated patient-specific classification of ECG signals. IEEE Transactions on Instrumentation and Measurement. 2009,56(5):1415–1426. doi:10.1109/TBME.2009.2013934
39. Graves A., Mohamed A.R., Hinton G. Speech recognition with deep recurrent neural networks. In: IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). 2013, p. 6645–6649. https://doi.org/10.1109/ICASSP.2013.6638947
40. Bergen K.J., Johnson P.A., de Hoop M.V., Beroza G.C. Machine learning for data-driven discovery in solid Earth geoscience. Science. 2019,363(6433). https://doi.org/10.1126/science.aau0323
41. Kong Q., Trugman D.T., Ross Z.E., Bianco M.J., Meade B.J., Gerstoft P. Machine learning in seismology: turning data into insights. Seismological Research Letters. 2018,90(1):3–14. https://doi.org/10.1785/0220180259
42. Nikitin V.V., Duchkov A.A., Andersson F. Using NVidia CUDA to accelerate seismic data processing via wavelet packet decomposition. Vychislitel'nyye metody i programmirovaniye = Numerical Methods and Programming. 2017,18(3):293–311. (In Russ.).
43. Wu N., Green B., Ben X., O'Banion S. Deep transformer models for time series forecasting: the influenza prevalence case. arXiv. 2020. URL: https://doi.org/10.48550/arXiv.2001.08317
44. Perol T., Gharbi M., Denolle M. Convolutional neural network for earthquake detection and location. Science Advances. 2018,4(2),e1700578. https://doi.org/10.1126/sciadv.1700578
45. Efitorov A., Dolenko S. A new type of a wavelet neural network. Optical Memory and Neural Networks (Information Optics). 2018,27(3):152–160. https://doi.org/10.3103/s1060992x18030050
46. Efitorov A., Dolenko S.A., Dolenko T. Use of wavelet neural networks to solve inverse problems in spectroscopy of multi-component solutions. Studies in Computational Intelligence. 2020,856:285–294. https://doi.org/10.1007/978-3-030-30425-6_33
47. Malkin E.I., Druzhin G.I. Hardware-software system and method of observing VLF radiation in Kamchatka. Vestnik KRAUNTs. Fiziko-matematicheskiye nauki = Bulletin of KRAESC. Physical and Mathematical Sciences. 2025,51(2):122–141. (In Russ.). https://doi.org/10.26117/2079-6641-2025-51-2-122-141
48. Catalogue of earthquakes of Kamchatka and the Commander Islands (1962 – present). Unified Information System of Seismological Data of KS FRC EGS RAS. (In Russ.). URL: http://sdis.emsd.ru/info/earthquakes/catalogue.php (accessed 12.05.2026).