Russian Journal of Earth Sciences Russian Journal of Earth Sciences Russian Journal of Earth Sciences 1681-1208 88322 10.2205/2025ES000987 mfjoob ОРИГИНАЛЬНЫЕ СТАТЬИ ORIGINAL ARTICLES ОРИГИНАЛЬНЫЕ СТАТЬИ The Fundamentals of a Two-Stage Approach to Systematic Earthquake Prediction Основы двухэтапного подхода к систематическому прогнозу землетрясений https://orcid.org/0000-0003-1123-6433 Гитис Валерий Григорьевич Gitis Valeriy Grigor'evich gitis@iitp.ru

доктор технических наук;

doctor of technical sciences;

 https://orcid.org/0000-0001-7063-6176 Дерендяев Александр Борисович Derendyaev Alexander Borisovich wintsa@gmail.com

кандидат технических наук;

candidate of technical sciences;

 Федеральное государственное бюджетное учреждение науки Институт проблем передачи информации им. А.А. Харкевича Российской академии наук Moscow RU Kharkevich Institute Moscow RU Федеральное государственное бюджетное учреждение науки Институт проблем передачи информации им. А.А. Харкевича Российской академии наук Москва Россия IITP RAS Moscow Russian Federation 21 05 2025 21 05 2025 25 3 1 18 03 09 2024 15 01 2025 https://ras.editorum.ru/en/nauka/article/88322/view

Систематический прогноз землетрясений производится регулярно с постоянным интервалом в заранее выбранной сейсмически однородной зоне. Результатом каждой итерации прогноза является карта зоны тревоги, в которой ожидаются эпицентры целевых землетрясений. В рассматриваемой технологии реализованы следующие новые положения: 1 – Решение считается успешным, если на интервале прогноза все эпицентры целевых землетрясений попали в зону тревоги. 2 – Технология оптимизирует вероятность успешного обнаружения эпицентров землетрясений в серии прогнозов и вероятность успешного прогноза на очередной итерации. 3 – Технология позволяет оценить вероятность успешного решения на очередном интервале прогноза. Рассмотрены примеры применения метода для прогноза землетрясений Камчатки, Калифорнии и островной части Японии.

A systematic earthquake prediction is performed regularly at fixed intervals within a preselected seismically homogeneous zone. The result of each prediction iteration is a map highlighting the alarm zones, where the epicenters of target earthquakes are expected. The proposed methodology introduces the following innovations: 1 – A prediction is considered successful if all epicenters of the target earthquakes during the forecast interval fall within the alarm zone. 2 – The methodology optimizes both the probability of successfully detecting earthquake epicenters across a series of forecasts and the success rate of predictions in each individual iteration. 3 – The methodology enables the estimation of the probability of success for the next forecast interval. Examples of the method's application are demonstrated for predicting earthquakes in Kamchatka, California, and the island region of Japan.

 систематический прогноз землетрясений машинное обучение метод минимальной области тревоги временные ряды GPS systematic earthquake prediction machine learning the method of the minimum area of alarm GPS time series Работа частично поддержана Государственным заданием № 0061- 2022-0003 по теме «Исследование и разработка методов и сетевых технологий анализа больших пространственно-временных данных с целью многодисциплинарного анализа и прогнозирования природных и социально-экономических процессов». Работа выполнена с использованием данных Камчатского филиала ФИЦ «Единая Геофизическая служба РАН», National Earthquake Information Center (NEIC), Japan Meteorological Agency (JMA) и Nevada Geodetic Laboratory (NGL). The work was partially supported by State Task No. 0061-2022-0003 on the topic "Research and development of methods and network technologies for analyzing large spatial-temporal data for the purpose of multidisciplinary analysis and forecasting of natural and socio-economic processes". The work was carried out using data from the Kamchatka branch of the Federal Research Center "Unified Geophysical Service of the Russian Academy of Sciences", National Earthquake Information Center (NEIC), Japan Meteorological Agency (JMA) and Nevada Geodetic Laboratory (NGL).

Завьялов А. Д. Среднесрочный прогноз землетрясений: основы, методика, реализация. — Москва : Наука, 2006. — EDN: QKFPZD. Zavyalov A. D. Medium-term earthquake forecast: fundamentals, methodology, implementation. — Moscow : Nauka, 2006. — EDN: QKFPZD ; (in Russian). Молчан Г. М. Оптимальные стратегии в прогнозе землетрясений. Современные методы интерпретации сейсмологических данных // Вычислительная сейсмология. — 1991. — Т. 24. — С. 3—18. Molchan G. M. Optimal Strategies in Earthquake Forecasting. Modern Methods of Interpreting Seismological Data // Computational Seismology. — 1991. — Vol. 24. — P. 3–18. — (In Russian). Соболев Г. А. Основы прогноза землетрясений. — Москва : МАИК «Наука/Интерпериодика», 1993. — 313 с. — EDN: TGSIGH. Sobolev G. A. Fundamentals of Earthquake Forecasting. — Moscow : MAIK “Nauka/Interperiodica”, 1993. — P. 313. — EDN: TGSIGH ; (in Russian). Соболев Г. А., Пономарев A. В. Физика землетрясений и предвестники. — Москва : МАИК «Наука/Интерпериодика», 2003. — 270 с. — EDN: RVEBFL. Sobolev G. A., Ponomarev A. V. Physics of earthquakes and precursors. — Moscow : MAIK “Nauka/Interperiodica”, 2003. — P. 270. — EDN: RVEBFL ; (in Russian). Чебров В. Н., Дрознин Д. В., Кугаенко Ю. А. и др. Система детальных сейсмологических наблюдений на Камчатке в 2011 г. // Вулканология и сейсмология. — 2013. — № 1. — С. 18—40. — DOI: 10.7868/s0203030613010021. Chebrov V. N., Droznin D. V., Kugaenko Yu. A., et al. The system of detailed seismological observations in Kamchatka in 2011 // Journal of Volcanology and Seismology. — 2013. — Vol. 7, no. 1. — P. 16–36. — DOI: 10.1134/S0742046313010028. Чеброва А. Ю., Чемарёв A. С., Матвеенко E. А. и др. Единая информационная система сейсмологических данных в Камчатском филиале ФИЦ ЕГС РАН: Принципы организации, основные элементы, ключевые функции // Геофизические исследования. — 2020. — Т. 21, № 3. — С. 66—91. — DOI: 10.21455/gr2020.3-5. Chebrova A. Yu., Chemarev A. S., Matveenko E. A., et al. Seismological data information system in Kamchatka branch of GS RAS: Organization principles, main elements and key functions // Geophysical Research. — 2020. — Vol. 21, no. 3. — P. 66–91. — DOI: 10.21455/gr2020.3-5. — (In Russian). Amei A., Fu W., Ho C. H. Time series analysis for predicting the occurrences of large scale earthquakes // International Journal of Applied Science and Technology. — 2012. — Vol. 2, no. 7. Amei A., Fu W., Ho C. H. Time series analysis for predicting the occurrences of large scale earthquakes // International Journal of Applied Science and Technology. — 2012. — Vol. 2, no. 7. 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. — DOI: 10.1371/journal.pone.0199004. 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. — DOI: 10.1371/journal.pone.0199004. Barnhart W. D., Hayes G. P., Wald D. J. Global Earthquake Response with Imaging Geodesy: Recent Examples from the USGS NEIC // Remote Sensing. — 2019. — Vol. 11, no. 11. — P. 1357. — DOI: 10.3390/rs11111357. Barnhart W. D., Hayes G. P., Wald D. J. Global Earthquake Response with Imaging Geodesy: Recent Examples from the USGS NEIC // Remote Sensing. — 2019. — Vol. 11, no. 11. — P. 1357. — DOI: 10.3390/rs11111357. Blewitt G., Hammond W. C., Kreemer C. Harnessing the GPS Data Explosion for Interdisciplinary Science // Eos. — 2018. — Vol. 99. — P. 485. — DOI: 10.1029/2018eo104623. Blewitt G., Hammond W. C., Kreemer C. Harnessing the GPS Data Explosion for Interdisciplinary Science // Eos. — 2018. — Vol. 99. — P. 485. — DOI: 10.1029/2018eo104623. Bradley A. P. The use of the area under the ROC curve in the evaluation of machine learning algorithms // Pattern Recognition. — 1997. — Vol. 30, no. 7. — P. 1145–1159. — DOI: 10.1016/s0031-3203(96)00142-2. Bradley A. P. The use of the area under the ROC curve in the evaluation of machine learning algorithms // Pattern Recognition. — 1997. — Vol. 30, no. 7. — P. 1145–1159. — DOI: 10.1016/s0031-3203(96)00142-2. Corbi F., Sandri L., Bedford J., et al. Machine Learning Can Predict the Timing and Size of Analog Earthquakes // Geophysical Research Letters. — 2019. — Vol. 46, no. 3. — P. 1303–1311. — DOI: 10.1029/2018gl081251. Corbi F., Sandri L., Bedford J., et al. Machine Learning Can Predict the Timing and Size of Analog Earthquakes // Geophysical Research Letters. — 2019. — Vol. 46, no. 3. — P. 1303–1311. — DOI: 10.1029/2018gl081251. Gitis V., Derendyaev A. The Method of the Minimum Area of Alarm for Earthquake Magnitude Prediction // Frontiers in Earth Science. — 2020. — Vol. 11. — DOI: 10.3389/feart.2020.585317. Gitis V., Derendyaev A. The Method of the Minimum Area of Alarm for Earthquake Magnitude Prediction // Frontiers in Earth Science. — 2020. — Vol. 11. — DOI: 10.3389/feart.2020.585317. Gitis V., Derendyaev A. A Technology for Seismogenic Process Monitoring and Systematic Earthquake Forecasting // Remote Sensing. — 2023. — Vol. 15, no. 8. — P. 2171. — DOI: 10.3390/rs15082171. Gitis V., Derendyaev A. A Technology for Seismogenic Process Monitoring and Systematic Earthquake Forecasting // Remote Sensing. — 2023. — Vol. 15, no. 8. — P. 2171. — DOI: 10.3390/rs15082171. Gitis V., Derendyaev A., Petrov K. Analyzing the Performance of GPS Data for Earthquake Prediction // Remote Sensing. — 2021. — Vol. 13, no. 9. — P. 1842. — DOI: 10.3390/rs13091842. Gitis V., Derendyaev A., Petrov K. Analyzing the Performance of GPS Data for Earthquake Prediction // Remote Sensing. — 2021. — Vol. 13, no. 9. — P. 1842. — DOI: 10.3390/rs13091842. Gitis V. G., Derendyaev A. B., Pirogov S. A., et al. Adaptive estimation of seismic parameter fields from earthquake catalogs // Journal of Communications Technology and Electronics. — 2015. — Vol. 60, no. 12. — P. 1459–1465. — DOI: 10.1134/s1064226915120098. Gitis V. G., Derendyaev A. B., Pirogov S. A., et al. Adaptive estimation of seismic parameter fields from earthquake catalogs // Journal of Communications Technology and Electronics. — 2015. — Vol. 60, no. 12. — P. 1459–1465. — DOI: 10.1134/s1064226915120098. Gitis V. G., Derendyaev A. B., Pirogov S. A., et al. Earthquake prediction using the fields estimated by an adaptive algorithm // Proceedings of the 7th International Conference on Web Intelligence, Mining and Semantics. — 2017. — P. 1–8. — DOI: 10.1145/3102254.3102269. Gitis V. G., Derendyaev A. B., Pirogov S. A., et al. Earthquake prediction using the fields estimated by an adaptive algorithm // Proceedings of the 7th International Conference on Web Intelligence, Mining and Semantics. — 2017. — P. 1–8. — DOI: 10.1145/3102254.3102269. Kagan Y. Y. Earthquakes: Models, Statistics, Testable Forecasts. — Wiley, 2013. — DOI: 10.1002/9781118637913. Kagan Y. Y. Earthquakes: Models, Statistics, Testable Forecasts. — Wiley, 2013. — DOI: 10.1002/9781118637913. Kail R., Burnaev E., Zaytsev A. Recurrent Convolutional Neural Networks Help to Predict Location of Earthquakes // IEEE Geoscience and Remote Sensing Letters. — 2022. — Vol. 19. — P. 1–5. — DOI: 10.1109/lgrs.2021.3107998. Kail R., Burnaev E., Zaytsev A. Recurrent Convolutional Neural Networks Help to Predict Location of Earthquakes // IEEE Geoscience and Remote Sensing Letters. — 2022. — Vol. 19. — P. 1–5. — DOI: 10.1109/lgrs.2021.3107998. Kaplan S. M., McFall R. W. The Statistical Properties of Noise Applied to Radar Range Performance // Proceedings of the IRE. — 1951. — Vol. 39, no. 1. — P. 56–60. — DOI: 10.1109/jrproc.1951.230422. Kaplan S. M., McFall R. W. The Statistical Properties of Noise Applied to Radar Range Performance // Proceedings of the IRE. — 1951. — Vol. 39, no. 1. — P. 56–60. — DOI: 10.1109/jrproc.1951.230422. King C. Y. Gas geochemistry applied to earthquake prediction: An overview // Journal of Geophysical Research: Solid Earth. — 1986. — Vol. 91, B12. — P. 12269–12281. — DOI: 10.1029/jb091ib12p12269. King C. Y. Gas geochemistry applied to earthquake prediction: An overview // Journal of Geophysical Research: Solid Earth. — 1986. — Vol. 91, B12. — P. 12269–12281. — DOI: 10.1029/jb091ib12p12269. Kossobokov V., Shebalin P. Earthquake Prediction // Nonlinear Dynamics of the Lithosphere and Earthquake Prediction. — Berlin : Springer Berlin Heidelberg, 2003. — P. 141–207. — DOI: 10.1007/978-3-662-05298-3_4. Kossobokov V., Shebalin P. Earthquake Prediction // Nonlinear Dynamics of the Lithosphere and Earthquake Prediction. — Berlin : Springer Berlin Heidelberg, 2003. — P. 141–207. — DOI: 10.1007/978-3-662-05298-3_4. Lighthill J. A Critical Review of VAN: Earthquake Prediction from Seismic Electrical Signals. — Singapore : World Scientific, 1996. — DOI: 10.1142/3006. Lighthill J. A Critical Review of VAN: Earthquake Prediction from Seismic Electrical Signals. — Singapore : World Scientific, 1996. — DOI: 10.1142/3006. Mignan A., Broccardo M. Neural Network Applications in Earthquake Prediction (1994-2019): Meta-Analytic and Statistical Insights on Their Limitations // Seismological Research Letters. — 2020. — Vol. 91, no. 4. — P. 2330– 2342. — DOI: 10.1785/0220200021. Mignan A., Broccardo M. Neural Network Applications in Earthquake Prediction (1994-2019): Meta-Analytic and Statistical Insights on Their Limitations // Seismological Research Letters. — 2020. — Vol. 91, no. 4. — P. 2330– 2342. — DOI: 10.1785/0220200021. Molchan G. Space-Time Earthquake Prediction: The Error Diagrams // Pure and Applied Geophysics. — 2010. — Vol. 167, no. 8/9. — P. 907–917. — DOI: 10.1007/s00024-010-0087-z. Molchan G. Space-Time Earthquake Prediction: The Error Diagrams // Pure and Applied Geophysics. — 2010. — Vol. 167, no. 8/9. — P. 907–917. — DOI: 10.1007/s00024-010-0087-z. Obara K., Kasahara K., Hori S., et al. A densely distributed high-sensitivity seismograph network in Japan: Hi-net by National Research Institute for Earth Science and Disaster Prevention // Review of Scientific Instruments. — 2005. — Vol. 76, no. 2. — DOI: 10.1063/1.1854197. Obara K., Kasahara K., Hori S., et al. A densely distributed high-sensitivity seismograph network in Japan: Hi-net by National Research Institute for Earth Science and Disaster Prevention // Review of Scientific Instruments. — 2005. — Vol. 76, no. 2. — DOI: 10.1063/1.1854197. Okada Y., Kasahara K., Hori S., et al. Recent progress of seismic observation networks in Japan -Hi-net, F-net, K-NET and KiK-net- // Earth, Planets and Space. — 2014. — Vol. 56, no. 8. — P. 15–28. — DOI: 10.1186/BF03353076. Okada Y., Kasahara K., Hori S., et al. Recent progress of seismic observation networks in Japan -Hi-net, F-net, K-NET and KiK-net- // Earth, Planets and Space. — 2014. — Vol. 56, no. 8. — P. 15–28. — DOI: 10.1186/BF03353076. Panakkat A., Adeli H. Neural network models for earthquake magnitude prediction using multiple seismicity indicators // International Journal of Neural Systems. — 2007. — Vol. 17, no. 01. — P. 13–33. — DOI: 10.1142/s0129065707000890. Panakkat A., Adeli H. Neural network models for earthquake magnitude prediction using multiple seismicity indicators // International Journal of Neural Systems. — 2007. — Vol. 17, no. 01. — P. 13–33. — DOI: 10.1142/s0129065707000890. Rhoades D. A. Mixture Models for Improved Earthquake Forecasting with Short-to-Medium Time Horizons // Bulletin of the Seismological Society of America. — 2013. — Vol. 103, no. 4. — P. 2203–2215. — DOI: 10.1785/0120120233. Rhoades D. A. Mixture Models for Improved Earthquake Forecasting with Short-to-Medium Time Horizons // Bulletin of the Seismological Society of America. — 2013. — Vol. 103, no. 4. — P. 2203–2215. — DOI: 10.1785/0120120233. Shebalin P. N., Narteau C., Zechar J. D., et al. Combining earthquake forecasts using differential probability gains // Earth, Planets and Space. — 2014. — Vol. 66, no. 1. — P. 1–14. — DOI: 10.1186/1880-5981-66-37. Shebalin P. N., Narteau C., Zechar J. D., et al. Combining earthquake forecasts using differential probability gains // Earth, Planets and Space. — 2014. — Vol. 66, no. 1. — P. 1–14. — DOI: 10.1186/1880-5981-66-37. Soloviev A. A., Gvishiani A. D., Gorshkov A. I., et al. Recognition of earthquake-prone areas: Methodology and analysis of the results // Izvestiya, Physics of the Solid Earth. — 2014. — Vol. 50, no. 2. — P. 151–168. — DOI: 10.1134/s1069351314020116. Soloviev A. A., Gvishiani A. D., Gorshkov A. I., et al. Recognition of earthquake-prone areas: Methodology and analysis of the results // Izvestiya, Physics of the Solid Earth. — 2014. — Vol. 50, no. 2. — P. 151–168. — DOI: 10.1134/s1069351314020116.