Contemporary approaches to forecasting methane concentrations at longwall panels of coal mines: from empirical methods to an adaptive AI-agent

DOI: https://doi.org/10.30686/1609-9192-2026-4S-150-156

Читать на русскоя языке A.A. Sidorenko1, Yu.G. Sirenko2
1  Sibcore LLC, Moscow, Russian Federation
2  Empress Catherine II Saint Petersburg Mining University, Saint Petersburg, Russian Federation
Russian Mining Industry №4S/ 2026 p. 150-156

Abstract: Forecasting methane concentrations at longwall panels of coal mines determines both the safety of mining operations and the utilisation efficiency of high-capacity longwall complexes. None of the existing class of methods, i.e. empirical gas-balance calculations, geostatistical and geomechanical models, machine learning (ML) and deep learning (DL) methods, or physics-informed neural networks, simultaneously delivers a short-term CH4 concentration forecast over a 5–60 min time-span, scenario-based diagnostics of concentration rise causes, a routed Q-C-I mass-balance verification, forecast interpretability, and model transferability between the panels. A systematic analysis of these approaches was carried out, their limitations were identified, and functional requirements for a predictive-diagnostic system were formulated. A concept of an adaptive AI-agent is proposed as a decision-support system that operates in the read-only mode with respect to the gas monitoring system, gas protection system, multi-functional safety system and SCADA. The methodological core comprises the following: decomposition of five CH4 sources; an input information model as the basis for feature-space transferability between the panels; a routed Q-C-I balance verification with a diagnostic imbalance Δbal; a taxonomy of seven gas-rise scenarios S1–S7 with probability distribution assessment P(Sk); a SHAP-based forecast interpretability; and a model transfer via transfer learning with domain adaptation. The functional architecture of the AI-agent is built on the following three aerological management circuits: panel ventilation, isolated methane-air mixture drainage via the gas suction unit, and degassing of the mined-out area and the adjacent seams.

Keywords: underground coal mine, longwall panel, methane, aerological safety, forecasting, adaptive AI-agent, decision-support system, machine learning, deep learning, physics-informed neural networks

Acknowledgements: The authors express their gratitude to the team of the Grit-Neuro LLC for constructive discussion of the problem statement.

For citation: Sidorenko A.A., Sirenko Yu.G. Contemporary approaches to forecasting methane concentrations at longwall panels of coal mines: from empirical methods to an adaptive AI-agent. Russian Mining Industry. 2026;(4S):150–156. (In Russ.) https://doi.org/10.30686/1609-9192-2026-4S-150-156

Article info

Received: 03.06.2026

Revised: 29.07.2026

Accepted: 21.08.2026

Information about the authors

Andrei A. Sidorenko – Cand. Sci. (Eng.), Chief Expert in Mine Planning, Sibcore LLC, Moscow, Russian Federation; https://orcid.org/0000-0003-4224-193X; e-mail: This email address is being protected from spambots. You need JavaScript enabled to view it.

Yury G. Sirenko – Cand. Sci. (Eng.), Associate Professor, Empress Catherine II Saint Petersburg Mining University, Saint Petersburg, Russian Federation; https://orcid.org/0000-0002-9270-9046; e-mail: This email address is being protected from spambots. You need JavaScript enabled to view it.

References

1. Sidorenko S, Trushnikov V, Sidorenko A. Methane emission estimation tools as a basis for sustainable underground mining of gas-bearing coal seams. Sustainability. 2024;16(8):3457. https://doi.org/10.3390/su16083457

2. Sharma M., Maity T. Review on machine learning-based underground coal mines gas hazard identification and estimation techniques. Archives of Computational Methods in Engineering. 2024;31(1):371–388. https://doi.org/10.1007/s11831-023-09982-1

3. Demirkan D.C., Duzgun H.S., Juganda A., Brune J., Bogin G. Real-time methane prediction in underground longwall coal mining using AI. Energies. 2022;15(17):6486. https://doi.org/10.3390/en15176486

4. Chang H., Meng X., Wang X., Hu Z. Research on coal mine longwall face gas state analysis and safety warning strategy based on multi-sensor forecasting models. Scientific Reports. 2024;14:13795. https://doi.org/10.1038/s41598-024-64181-7

5. Gabov V.V., Zadkov D.A. Mathematical model of simple spalling formation during coal cutting with extracting machine. Journal of Physics: Conference Series. 2018;1015(5):052007. https://doi.org/10.1088/1742-6596/1015/5/052007

6. Martirosyan A.V., Ilyushin Y.V. The development of the toxic and flammable gases concentration monitoring system for coalmines. Energies. 2022;15(23):8917. https://doi.org/10.3390/en15238917

7. Tutak M., Krenicky T., Pirník R., Brodny J., Grebski W.W. Predicting methane concentrations in underground coal mining using a multi-layer perceptron neural network based on mine gas monitoring data. Sustainability. 2024;16(19):8388. https://doi.org/10.3390/su16198388

8. Ruban A.D., Zaburdyaev V.S., Zaburdyaev G.S., Matvienko N.G. Methane in mines and pits of Russia: forecast, extraction and use. Moscow: IPKON RAN; 2006. 312 p. (In Russ.)

9. Chang H., Wang X., Cristea A.I., Meng X., Hu Z., Pan Z. Explainable artificial intelligence and advanced feature selection methods for predicting gas concentration in longwall mining. Information Fusion. 2025;118:102976. https://doi.org/10.1016/j.inffus.2025.102976

10. Wang L., Jia B., Su G. Prediction of coal and gas outbursts based on physics informed neural networks and traditional machine learning models. Scientific Reports. 2025;15:29984. https://doi.org/10.1038/s41598-025-02320-4

11. Phuc L.Q., Linh N.K., Babyr N.V., Thang N.V. Stress environment and roof support needs for roadways ahead of the coal face: Case study from Ha Lam coal mine. Geology and Geophysics of Russian South. 2025;15(4):270–284. https://doi.org/10.46698/o0885-5581-1938-j

12. Özgen Karacan C., Ruiz F.A., Cotè M., Phipps S. Coal mine methane: A review of capture and utilization practices with benefits to mining safety and to greenhouse gas reduction. International Journal of Coal Geology. 2011;86(2-3):121–156. https://doi.org/10.1016/j.coal.2011.02.009

13. Vasilenko T., Kirillov A., Islamov A., Doroshkevich A. Study of hierarchical structure of fossil coals by small-angle scattering of thermal neutrons. Fuel. 2021;292:120304. https://doi.org/10.1016/j.fuel.2021.120304

14. Liang S.-S., Zhang D.-S., Fan G.-W., Kovalsky E., Fan Z.-L., Zhang L., Han X.-S. Mechanical structure and seepage stability of confined floor response to longwall mining of inclined coal seam. Journal of Central South University. 2023;30(9):2948–2965. https://doi.org/10.1007/s11771-023-5429-y

15. Bondarev A.V., Shabarov A.N., Shvankin M.V., Vasilenko T.A. Factors increasing the hazard of gas-dynamic phenomena in coal mines. Mining Informational and Analytical Bulletin. 2025;(11-1):77–95. (In Russ.) Available at: https://giab-online.ru/files/Data/2025/11-1/77.pdf (accessed: 23.03.2026).

16. Tien D.L., Trung T.V., Anh S.D., Babyr N.V. Ground pressure and methods to enhance roof stability in mechanized coal mining. International Journal of Engineering, Transactions A: Basics. 2026;39(4):862–869. https://doi.org/10.5829/ije.2026.39.04a.05

17. Nevskaya E.E., Guskov M.A., Samylovskaya E.E. Advanced risk assessment in coal mines: integrating fuzzy logic and linguistic variables for enhanced hazard management. International Journal of Engineering, Transactions B: Applications. 2025;38(12):2854–2864. https://doi.org/10.5829/ije.2025.38.12c.04

18. Kaledina N.O., Malashkina V.A. Indicator assessment of the reliability of mine ventilation and degassing systems functioning. Journal of Mining Institute. 2021;250:553–561. https://doi.org/10.31897/PMI.2021.4.8

19. Balovtsev S.V. Higher rank aerological risks in coal mines. Mining Science and Technology (Russia). 2022;7(4):310–319. https://doi.org/10.17073/2500-0632-2022-08-18

20. Kobylkin S.S., Kharisov A.R. Design features of coal mines ventilation using a room-and-pillar development system. Journal of Mining Institute. 2020;245:531–538. https://doi.org/10.31897/PMI.2020.5.4

21. Slastunov S., Kolikov K., Batugin A., Sadov A., Khautiev A. Improvement of intensive in-seam gas drainage technology at kirova mine in kuznetsk coal basin. Energies. 2022;15(3):1047. https://doi.org/10.3390/en15031047

22. Babyr N.V., Kuziev D.A., Sazankova E.S., Dobler M.O. Influence of cyclic impacts of powered roof support on weakening of immediate roof rocks. Eurasian Mining. 2026;(1):14–19. Available at: https://www.rudmet.ru/journal/2523/article/41017/ (accessed: 05.02.2026).

23. Slastunov S.V., Ponizov A.V., Sadov A.P., Khautiev A.B.-M. Integrated technology for multistage drainage of coal seams before high-rate cutting. Gornyi Zhurnal. 2021;(2):101–106. (In Russ.) https://doi.org/10.17580/gzh.2021.02.14

24. Kabanov E.I., Korshunov G.I. Kornev A.V., Myakov V.V. Analysis of the causes of methane explosions, flashes and ignitions at coal mines of Russia in 2005–2019. Mining Informational and Analytical Bulletin. 2021;(2-1):18–29. (In Russ.) https://doi.org/10.25018/0236-1493-2021-21-0-18-29

25. Karpov G.N., Kovalski E.R., Nosov A.A. Longwall recovery room erecting method for flat coal seam mining. Mining Informational and Analytical Bulletin. 2022;(6-1):54–67. (In Russ.) https://doi.org/10.25018/0236_1493_2022_61_0_54

26. Gendler S.G., Prokhorova E.A. Methodical framework for selecting occupational safety management priorities in underground coal mining on the basis of integrated occupational illness and injury risk dynamics analysis. Gornyi Zhurnal. 2023;(9):41–48. (In Russ.) https://doi.org/10.17580/gzh.2023.09.06

27. Gendler S.G., Gabov V.V., Babyr N.V., Prokhorova E.A. Justification of engineering solutions on reduction of occupational traumatism in coal longwalls. Mining Informational and Analytical Bulletin. 2022;(1):5–19. (In Russ.) https://doi.org/10.25018/0236_1493_2022_1_0_5

28. Smirnyakov V.V., Rodionov V.A., Smirnyakova V.V., Orlov F.A. The influence of the shape and size of dust fractions on their distribution and accumulation in mine workings when changing the structure of air flow. Journal of Mining Institute. 2022;253:71–81. https://doi.org/10.31897/PMI.2022.12

29. Borowski G., Smirnov Y., Ivanov A., Danilov A. Effectiveness of carboxymethyl cellulose solutions for dust suppression in the mining industry. International Journal of Coal Preparation and Utilization. 2022;42(8):2345–2356. https://doi.org/10.1080/19392699.2020.1841177

30. Rodionov V.A., Tursenev S.A., Skripnik I.L., Ksenofontov Y.G. Results of the study of kinetic parameters of spontaneous combustion of coal dust. Journal of Mining Institute. 2020;246:617–622. https://doi.org/10.31897/PMI.2020.6.3

31. Romanchenko S.B., Naganovskiy Y.K., Kornev A.V. Innovative ways to control dust and explosion safety of mine workings. Journal of Mining Institute. 2021;252:927–936. https://doi.org/10.31897/PMI.2021.6.14

32. Gabov V. V., Zadkov D. A., Pryaluhin A. F., Sadovsky M. V., Molchanov V. V. Mining combine screw executive body design. Mining Informational and Analytical Bulletin. 2023;(11-1):51–71. (In Russ.) https://doi.org/10.25018/0236_1493_2023_111_0_51

33. Zubov V.P., Golubev D.D. Prospects for the use of modern technological solutions in the flat-lying coal seams development, taking into account the danger of the formation of the places of its spontaneous combustion. Journal of Mining Institute. 2021;250:534–541. https://doi.org/10.31897/PMI.2021.4.6