GEOMECHANICS


PROSPECTS AND OPPORTUNITIES FOR A COMPREHENSIVE ASSESSMENT OF THE IMPACT HAZARD OF THE ARRAY USING MACHINE LEARNING ALGORITHMS IN ORE DEPOSIT

Authors:
  • P.A. Demenkov1, E.D. Silicheva1, M.A. Cherevko2, A.V. Dengaev3
  • 1 Saint-Petersburg Mining University, Saint Petersburg, 199106, Russian Federation
  • 2 ”Oilfield Service Solutions” LLC, Saint Petersburg, 190031, Russian Federation
  • 3 Gubkin Russian State University of Oil and Gas (National Research University), Moscow, 119991, Russian Federation, е-mail: demenkov_pa@pers.spmi.ru
  • Authors Information
  • Demenkov P.A. – Doctor of Engineering Sciences, Dean of the Faculty of Civil Engineering, Saint-Petersburg
  • Mining University, Saint Petersburg, 199106, Russian Federation, e-mail: demenkov_pa@pers.spmi.ru
  • Silicheva E.D. – Postgraduate Student of the Department of Mining Enterprises and Underground Structures,
  • Saint-Petersburg Mining University, Saint Petersburg, 199106, Russian Federation, e-mail: romnva@yandex.ru
  • Cherevko M.A. – PhD (Engineering), General Director, “Oilfield Service Solutions” LLC, Saint Petersburg, 190031,
  • Russian Federation, e-mail: Cherevko.MiA@gazprom-neft.ru
  • Dengaev A.V. – PhD (Engineering), Gubkin Russian State University of Oil and Gas (National Research University), Moscow, 119991, Russian Federation, e-mail: Dengaev.A@gubkin.ru
UDC: 622.83 c P.A. Demenkov1, E.D. Silicheva1, M.A. Cherevko2, A.V. Dengaev3, 2026
DOI: http://dx.doi.org/10.18796/0041-5790-2026-8-99-104

Abstract

This paper addresses the problem of predicting dynamic manifestations of rock pressure in blast-hazardous ore deposits within the Khibiny Massif. The relevance of this study stems from the complex and multifactorial nature of geomechanical processes. An analysis of the geomechanical and geophysical methods currently in use was conducted, and their key limitations, associated with a simplified account of the massif’s properties, were identified. The idea of using machine learning methods for data processing and the identification of precursors to hazardous geodynamic phenomena is considered. The paper describes an approach to constructing a composite model that combines clustering, time series analysis, and classification algorithms. The methodology for forming input datasets, including seismic, deformation, electrometric, and technological parameters, is described. The feasibility of the comprehensive use of machine learning methods in combination with traditional geomechanical concepts is demonstrated. It has been concluded that there is significant potential for the development of adaptive forecasting systems designed to improve the accuracy of impact resistance assessments and reduce the risk of accidents during mining operations.

Keywords: Impact hazard, ore deposits, machine learning, geomechanics, prediction of impact hazard, dynamic manifestations of rock pressure, artificial intelligence.

References

  1. Синегубов В.Ю. Разработка комплексного подхода к прогнозу напряженного состояния породного массива и апробация на месторождении Олений ручей // Вестник Кузбасского государственного технического университета. 2025. № 2. C. 68-79. DOI: 10.26730/1999-4125- 2025-2-68-79. Sinegubov V.Yu. Development of a Comprehensive Approach for Predicting the Stress State of the Rock Mass and Its Testing at the Oleniy Ruchey Deposit. Bulletin of Kuzbass State Technical University. 2025;(2):68-79. (In Russ.). DOI: 10.26730/1999-4125-2025-2-68-79.
  2. Оценка влияния очистных работ на формирование нарушенных зон в массиве на контурах выработок большого сечения при освоении месторождений апатит-нефелиновых руд / В.Ю. Синегубов, М.Г. Попов, М.А. Вильнер и др. // Горный журнал. 2021. № 8. С. 24-30. DOI: 10.17580/gzh.2021.08.04. Sinegubov V.Yu., Popov M.G., Vilner M.A., Sotnikov R.O. Assessment of the Influence of Extraction Works on the Formation of Disturbed Zones in the Rock Mass Around Large Cross-Section Mine Workings During the Development of Apatite-Nepheline Ore Deposits. Gornyij Zhurnal. 2021;(8):24-30. (In Russ.). DOI: 10.17580/ gzh.2021.08.04.
  3. Trushko V.L., Baeva E.K., Blinov A.A. Experimental Investigation on the Mechanical Properties of the Frozen Rocks at the Yamal Peninsula, Russian Arctic. Eng. 2025;(6):76. DOI: 10.3390/eng6040076.
  4. Протосеня А.Г., Кумов В.В. Влияние структуры массива грунта в смешанном забое тоннеля на форму и размер мульды осадок земной поверхности // Горный информационно-аналитический бюллетень (научно-технический журнал). 2024. № 4. C. 5-21. DOI: 10.25018/0236_1493_2024_4_0_5. Protosenya A.G., Kumov V.V. Effect of soil body structure of mixedtype tunnel face on shape and size of subsidence trough on ground surface. MIAB. Mining Inf. Anal. Bull. 2024;(4):5-21. (In Russ.). DOI: 10.25018/0236_1493_2024_4_0_5.
  5. Protosenya A., Ivanov A. Data-Driven Prediction of Stress-Strain Fields Around Interacting Mining Excavations in Jointed Rock: A Comparative Study of Surrogate Models. Mining. 2026;6(1):4. DOI: 10.3390/mining6010004.
  6. Моделирование полей напряжений и оценка удароопасности конструктивных элементов системы разработки Южно-Хинганского месторождения марганцевых руд / М.И. Рассказов, И.Ю.Рассказов, М.И. Потапчук и др. // Горная промышленность.
  7. № 5S. C. 72-79. DOI: 10.30686/1609-9192-2023-5s-72-79. Rasskazov M.I., Rasskazov I.Yu., Potapchuk M.I., Tsoi D.I., Tereshkin A.A. Modeling of stress fields and estimation of the impact hazard of structural elements of the mining system of the Yuzhno-Khingansk manganese ore deposit. Russian Mining Industry. 2023;(5S):72-79. (In Russ.). DOI: 10.30686/1609-9192-2023-5S-72-79.
  8. Господариков А.П., Зацепин М.А., Киркин А.П. Определение потенциала удароопасности горных пород Норильского промышленного района // Записки Горного института. 2025. № 272. С. 83-90. Gospodarikov A.P., Zatsepin M.A., Kirkin A.P. Determination of impact hazard potential of rocks in the Norilsk Industrial Region. Journal of Mining Institute. 2025;(272):83-90. (In Russ.).
  9. Козырев А.А., Кузнецов Н.Н., Шоков А.Н. Оценка удароопасности скальных горных пород Ждановского месторождения (Кольский полуостров). // Горная промышленность. 2022. № 6. C. 75-82. DOI: 10.30686/1609-9192-2022-6-75-82. Kozyrev A.A., Kuznetsov N.N., Shokov A.N. Rockburst hazard assessment of hard rocks in the Zhdanovskoe deposit (Kola Peninsula). Russian Mining Industry. 2022;(6):75-82. (In Russ.). DOI: 10.30686/1609-9192-2022-6-75-82.
  10. Гусев В.Н., Одинцов Е.Е., Жерлыгина Е.С. Расчет сдвижений и деформаций массива горных пород с учетом натурных данных // Горный журнал. 2025. № 4. С.18-25. DOI: 10.17580/gzh.2025.04.03. Gusev V.N., Odintsov E.E., Zherlygina E.S. Calculation of displacements and deformations in rock mass with regard to field data. Gornyij Zhurnal. 2025;(4):18-25 (In Russ). DOI: 10.17580/gzh.2025.04.03.
  11. Алгоритмы и измерительный комплекс классификации источников сейсмических сигналов, определения расстояния и азимута до пункта возбуждения поверхностных волн / Д.Л. Зайцев, В.М. Брыксин, К.С. Белотелов и др. // Информатика и автоматизация. 2022. Т. 21. №. 6. С. 1211-1239. DOI: https://doi.org/10.15622/ia.21.6.5. Zaitsev D.L., Bryksin V.M., Belotelov K.S., Kompaniets Yu.I., Yakovlev R.N. Algorithms and Measuring Complex for Classification of Seismic Signal Sources, Determination of Distance and Azimuth to the Point of Excitation of Surface Waves. Informatics and Automation. 2022;21(6):1211-1239. (In Russ.). DOI: https://doi.org/10.15622/ia.21.6.5.
  12. Обоснование и разработка отклонителя непрерывного действия с полным отбором керна для бурения геологоразведочных скважин / П.А. Блинов, Н.М. Силичев, В.В. Никишин и др. // Известия Томского плитехнического университета. Инжиниринг георесурсов. 2025. Т. 336 № 7. С. 17-28. DOI: 10.18799/24131830_2025_7_4780. Blinov P.A., Silichev N.M., Nikishin V.V., Gorelikov G.G. Justification and Development of a Continuous-Action Deviator with Full Core Extraction for Drilling Geological Exploration Wells. Izvestiya of Tomsk Polytechnic University. Engineering of Georesources. 2025;336(7): 17-28. (In Russ). DOI: 10.18799/24131830_2025_7_4780.
  13. Исследование возможности применения методов неразрушающего контроля для оценки прочностных свойств горных пород в условиях подземного рудника Гремячинского месторождения / Д.Н. Петров, В.И. Абашин, М.А. Карасев и др. // Горный информационно-аналитический бюллетень (научно-технический журнал). 2024. № 12-1. С. 227-244. DOI: 10.25018/0236_1493_2024_121_0_227. Petrov D.N., Abashin V.I., Karasev M.A., Selikhov A.A. Non-destructive testing applicability in rock mass strength estimation in underground mine at the Gremyachinsk deposit. MIAB. Mining Inf. Anal. Bull. 2024;12(1): 227-244. (In Russ.). DOI: 10.25018/0236_1493_2024_121_0_227.
  14. Господариков А.П., Ревин И.Е., Морозов К.В. Композитная модель анализа данных сейсмического мониторинга при ведении горных работ на примере Кукисвумчоррского месторождения АО ?Апатит? // Записки Горного института. 2023. №. 262. С. 571-580. DOI: 10.31897/PMI.2023.9. Gospodarikov A.P., Revin I.E., Morozov K.V. Composite model of seismic monitoring data analysis during mining operations on the example of the Kukisvumchorrskoye deposit of AO Apatit. Journal of Mining Institute. 2023;(262):571-580. (In Russ.). DOI: 10.31897/PMI.2023.9.
  15. Tadeusiewicz R. Neural networks in mining sciences-general overview and some representative examples. Archives of Mining Sciences. 2015;60(4):971-984. DOI: 10.1515/amsc-2015-0064.
  16. Reshetnyak S., Zotov V., Kuziev D., Kozlova O. Enhancing performance efficiency of electric consumers within surface infrastructure of coal mines. Eurasian Mining. 2025;(1):100-104. DOI: 10.17580/em.2025.01.20.
  17. Basnet P.M.S., Mahtab S., Jin A. A comprehensive review of intelligent machine learning based predicting methods in long-term and short-term rock burst prediction. Tunnelling and Underground Space Technology. 2023;(142):105434. DOI: 10.1016/j.tust.2023.105434.
  18. Zhou J., Koopialipoor M., Li E., Armaghani D.J. Prediction of rockburst risk in underground projects developing a neuro-bee intelligent system. Bull. Eng. Geol. Environ. 2020;79(8):4265-4279. DOI: 10.1007/s10064-020-01788-w.
  19. Cai M. Rockburst risk control and mitigation in deep mining. Deep Resources Engineering. 2024;1(2):100019. DOI: 10.1016/j.deepre. 2024.100019.
  20. Zhang Y. et al. Rockburst prediction using artificial intelligence techniques: A review. Rock Mechanics Bulletin. 2024;3(3):100129. DOI: 10.1016/j.rockmb.2024.100129.
  21. Zhang Junming Xia, Qiyuan Wu, Hai Wei, Sailei Hu, Zhen Du, Bing Yang, Yuejing Xiong, Huaixing. Research on rock burst prediction based on an integrated model. Scientific Reports. 2025. DOI: 15. 10.1038/s41598-025-91518-7.
  22. Blah?t Jan, Racek, Ond?ej. Modern Methods of Rock Mass Characterisation and Rockfall Monitoring: A Review. Landslides: detection, prediction and monitoring: technological developments. 2023:1-38. DOI: 10.1007/978-3-031-23859-8_1.
  23. Di Y., Wang E., Li Z., Liu X., Huang T., Yao J. Comprehensive early warning method of microseismic, acoustic emission, and electromagnetic radiation signals of rock burst based on deep learning. International Journal of Rock Mechanics and Mining Sciences. 2023;(170):105519 DOI: 10.1016/j.ijrmms.2023.105519.
  24. Pu Y., Apel D.B., Prusek S., Walentek A., Cichy T. Back-analysis for initial ground stress field at a diamond mine using machine learning approaches. Natural Hazards. 2021;105(1):191-203. DOI: 10.1007/s11069-020-04304-1.

For citation

Demenkov P.A., Silicheva E.D., Cherevko M.A., Dengaev A.V. Prospects and opportunities for a comprehensive assessment of the impact hazard of the array using machine learning algorithms in ore deposits. Ugol’. 2026;(8):99-104. (In Russ.). DOI: 10.18796/0041-5790-2026-8-99-104.

Paper Info
Received: June 24, 2026
Reviewed: July 17, 2026
Accepted: July 30, 2026
SPECIAL ISSUE




Hot from the press
Partners

“UGOL'” Journal Edition LLC
Leninsky Prospekt, 2А, office 819 Moscow, 119049, Russian Federation
phone/fax: +7 (499) 237-22-23
E-mail: ugol1925@mail.ru
www.ugolinfo.ru
Copyright © 2026 All Rights Reserved