Intelligent prediction method of rockburst driven by microseismic temporal features in deep near-vertical coal seams

Abstract

Rockburst has become a major hazard constraining safe production and high-quality capacity release in China’s coal mines. During deep mining of near-vertical seams within the Tianshan seismic belt, the coupling of nonlinear coal-rock deformation responses with complex geological conditions markedly elevates rockburst risk. To meet the strategic demand for intelligent, safe, and efficient mining in rockburst-prone seams, this study integrates geophysics, spatial statistics, big data mining, and deep learning to investigate a steeply dipping coal mine in Xinjiang, China, and systematically analyze the relationship between microseismic activity parameters and mining-induced disturbances. On this basis, a temporal fusion feature identification method for microseismic indicators is proposed. By embedding temporal constraints into a deep-learning framework, an enhanced temporal fusion transformer (TFT) is developed to predict multiple microseismic indicators. Furthermore, an intelligent rockburst prediction and early-warning approach driven by fused microseismic parameters is established and validated in field applications. Results indicate that hazard risk in the sandwiched rock pillar and the B₆ roof areas increases with working-face advance, and the localized damage in the sandwiched rock pillar is more severe than that in the B₆ roof. To strengthen feature extraction, a WFTBlock is introduced by combining continuous wavelet transform, Fourier transform, and timestamp alignment to reveal the periodic evolution of spectral and phase characteristics in indicator sequences. The final multi-parameter TFT model is trained jointly with fused features and temporal inputs. Compared with the long short-term memory (LSTM) baseline, the proposed model reduces root mean square error (RMSE) by 47.9% and improves coefficient of determination (R²) by 54.5%, demonstrating substantially enhanced predictive accuracy. Overall, the proposed framework provides technical support for safe and efficient mining of steeply dipping seams and the secure development of key energy bases along the Belt and Road Initiative.

Keywords

near-vertical coal seams / rockburst / microseismic / spatiotemporal features / intelligent prediction

References

[1] Kang HP, Yang JW, Jiang PF, et al. . Theory, technology and application of grouted bolting in soft rock roadways of deep coal mines. Int. J. Miner. Metall. Mater., 2024, 3171463

[2] Xu HC, Lai XP, Shan PF, et al. . Energy dissimilation characteristics and shock mechanism of coal-rock mass induced in steeply-inclined mining: Comparison based on physical simulation and numerical calculation. Acta Geotech., 2023, 182843

[3] Li P, Cai MF, Miao SJ, Li Y, Wang Y. Correlation between the rock mass properties and maximum horizontal stress: A case study of overcoring stress measurements. Int. J. Miner. Metall. Mater., 2025, 32139

[4] H.C. Xu, K. Li, P.F. Shan, et al., Automatic picking method for the first arrival time of microseismic signals based on fractal theory and feature fusion, Fractal Fract., 9(2025), No. 11, art. No. 679.

[5] G. Xu, P.F. Shan, X.P. Lai, Q.X. Hu, S.T. Yang, and H.C. Xu, Thermomechanical behavior and damage mechanism of the lining backfill body of high-temperature thermal energy storage reservoirs in mines, Tunnelling Underground Space Technol., 171(2026), art. No. 107409.

[6] R. Zhan, B. Zhang, L. Liu, et al., A numerical study of damage evolution and crack propagation in backfill bodies of high-temperature thermal energy storage cavities in mines, Tunnelling Underground Space Technol., 171(2026), art. No. 107362.

[7] He XQ, Zhou C, Song DZ, et al. . Mechanism and monitoring and early warning technology for rockburst in coal mines. Int. J. Miner. Metall. Mater., 2021, 2871097

[8] W. Cai, L.M. Dou, G.Y. Si, et al., A new seismic-based strain energy methodology for coal burst forecasting in underground coal mines, Int. J. Rock Mech. Min. Sci., 123(2019), art. No. 104086.

[9] Pan YS, Wang AW. Disturbance response instability theory of rock bursts in coal mines and its application. Geohazard Mech., 2023, 111

[10] M. Khan, X.Q. He, A. Farid, et al., Geophysical characterization of mining-induced complex geological deformations in a deep coalmine, Lithosphere, 2021(2022), No. Special 4, art. No. 7564984.

[11] Dong LJ, Yan XH, Wang J, Tang Z. Case study of microseismic tomography and multi-parameter characteristics under mining disturbances. J. Cent. South Univ., 2023, 3072252

[12] Deng J, Gong YL, Li SJ. Induced mechanism of tunnel rockbursts based on dynamic buckling of rock plates. Geohazard Mech., 2025, 3115

[13] Zhao TB, Guo WY, Zhang DX, et al. . Theoretical framework for stress relief-support reinforcement cooperative control of rock bursts in deep coal mining. Geohazard Mech., 2024, 2149

[14] Zhou CH, Li YA, Yin JM, Wang Y, Zhou C, Guo XF. Multivariate early warning method for rockbursts based on comprehensive microseismic and electromagnetic radiation monitoring. Chin. J. Geotech. Eng., 2020, 423457

[15] Zhou CH, Li YA, Yin JM, Wang Y, Zhou C. Study on the characteristics of microseismicity and electromagnetic radiation activity of the underground powerhouse at Huanggou pumped storage power station subjected to the excavation. Chin. J. Rock Mech. Eng., 2019, 38S23583

[16] Tang LZ, Wang LH, Zhang J, Li XB. Seismic apparent stress and deformation in a deep mine under large-scale mining and areal hazardous seismic prediction. Chin. J. Rock Mech. Eng., 2011, 3061168

[17] Tang LZ, Zhang J, Li XB, Wang LH, Zhou JX, Liu T. Research on response of mine microseismicity to mining rate based on quantitative seismology. Chin. J. Rock Mech. Eng., 2012, 3171349

[18] Xia YX, Kang LJ, Qi QX, et al. . Five indexes of microseismic and their application in rock burst forecastion. J. China Coal Soc., 2010, 35122011

[19] Cai W, Dou LM, Li ZL, Liu J, Gong SY, He J. Microseismic multidimensional information identification and spatiotemporal forecasting of rock burst: A case study of Yima Yuejin coal mine, Henan, China. Chin. J. Geophys., 2014, 5782687

[20] Chen L, Wu SC, Jin AB, Zhang CJ, Li X. Rockburst prediction and evaluation model for hard rock engineering based on extreme gradient boosting ensemble learning and SHAP value. Geotech. Geol. Eng., 2023, 4173923

[21] Y.Y. Di, E.Y. Wang, Z.H. Li, X.F. Liu, T. Huang, and J.J. Yao, Comprehensive early warning method of microseismic, acoustic emission, and electromagnetic radiation signals of rock burst based on deep learning, Int. J. Rock Mech. Min. Sci., 170(2023), art. No. 105519.

[22] Xue KL, Qi Y, Duan HF, Cao AY, Wang AW. Prediction of coal and gas outburst hazard using kernel principal component analysis and an enhanced extreme learning machine approach. Geohazard Mech., 2024, 24279

[23] Wang G, Zhao HR, Dai LP, Wang HJ, Lyu JG, Zhang JZ. Development of a portable coal rock charge monitoring instrument and its application for rockburst control. Geohazard Mech., 2024, 23216

[24] Lai XP, Xu HC, Shan PF, et al. . Research on the mechanism of rockburst induced by mined coal-rock linkage of sharply inclined coal seams. Int. J. Miner. Metall. Mater., 2024, 315929

[25] H.C. Xu, K. Li, B. Zhang, et al., Thermo-mechanical damage characteristics and fracture behavior of backfill bodies in thermal energy storage cavities: An experimental and numerical study, Tunn. Undergr. Space Technol., 175(2026), art. No. 107715.

[26] H.C. Xu, X.P. Lai, S. Zhang, et al., Precursor information recognition of rockburst in the coal-rock mass of meizoseismal area based on multiplex microseismic information fusion and its application: A case study of Wudong coal mine, Lithosphere, 2022(2022), Special 11, art. No. 7349759.

[27] Brady BT, Leighton FW. Seismicity anomaly prior to a moderate rock burst: A case study. Int. J. Rock Mech. Min. Sci. Geomech. Abstr., 1977, 143127

[28] Fujii Y, Ishijima Y. Numerical simulation of microseismicity induced by deep longwall coal mining. Min. Sci. Technol., 1991, 123265

[29] Zhang CX, Li XB, Kang Q, Dong LJ, Ma J. Mining disaster risk assessment based on the microseismic activity parameters. J. Saf. Environ., 2017, 1741276

[30] Liu PY, Wu BL, Li NQ, et al. . WFTNet: Exploiting global and local periodicity in long-term time series forecasting. ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). 2024art. No. 5960

[31] Lim B, Arık S, Loeff N, Pfister T. Temporal Fusion Transformers for interpretable multi-horizon time series forecasting. Int. J. Forecast., 2021, 3741748

[32] Chen DP, Yin SH, Long WG, et al. . Heterogeneous information phase space reconstruction and stability prediction of filling body-surrounding rock combination. Int. J. Miner. Metall. Mater., 2024, 3171500

[33] Cai MF, Feng ZL, Guo QF, Yin X, Ma MH, Xi X. Roughness characterization and shearing dislocation failure for rock–backfill interface. Int. J. Miner. Metall. Mater., 2024, 3161167

Rights & permissions

University of Science and Technology Beijing