Machine Learning for Seismic Bump Prediction: A Comparative Study of Different Algorithms and Features

Fei  Li

doi:10.6180/jase.202605_29(5).0002

Machine Learning for Seismic Bump Prediction: A Comparative Study of Different Algorithms and Features

Environmental Engineering Computer Science and Information Engineering

Fei LiThis email address is being protected from spambots. You need JavaScript enabled to view it.

School of Zhengzhou University of Light Industry; Zhengzhou Henan, 450000, China

Received: September 11, 2024
Accepted: July 12, 2025
Publication Date: August 25, 2025

Copyright The Author(s). This is an open access article distributed under the terms of the Creative Commons Attribution License (CC BY 4.0), which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are cited.

Download Citation: ||https://doi.org/10.6180/jase.202605_29(5).0002

Predicting seismic events is crucial to preventing rock rupture events in coal mines. This endeavor involves analyzing long-term historical relationships between seismic data, or patterns and trends from the length of time series observations, to understand changing stress conditions and predict future events. In this exploration, the goal is to evaluate machine learning (ML) models’ efficiency in predicting seismic events from historical data. More specifically, two metaheuristic algorithms, Coati Optimization Algorithm (COA) and Dwarf Mongoose Optimization Algorithm (DMOA), are used to further improve the Random Forest Classification (RFC) scheme. These additions created two hybrid schemes: Random Forest with Coati Optimization (RFCO) and Random Forest with Dwarf Mongoose Optimization (RFDM). Drawing on the experimental outcomes, RFDM was superior to the RFC model, which achieved an accuracy of 0.940 at its maximum during the All phase, with 0.962 accuracy, 0.965 precision, and 0.963 recall. However, both models were improved upon by the RFCO model, with results of 0.990 accuracy, precision, and recall across all three metrics. The results support the proposed hybrid method and demonstrate how improved forecasting of seismic bumps can improve safety in mining operations. Improvements in early warning systems will reduce the risk of rock bursts, protect miner safety, and assist sustainability in coal mining.

Keywords: RandomForest Classification, Seismic Bump, Dwarf Mongoose Optimization Algorithm, Machine Learning Algorithm

[1] E. Çelık, M. Atalay, and H. Bayer. “Earthquake pre diction using seismic bumps with artificial neural networks and support vector machines”. In: 2014 22nd Signal Processing and Communications Applications Conference (SIU). IEEE, 2014, 730–733. DOI: 10.1109/SIU.2014.6830333.
[2] N. Tsumura, N. Komada, J. Sano, S. Kikuchi, S. Yamamoto, T. Ito, T. Sato, T. Miyauchi, T. Kawamura, and M.Shishikura, (2009) “A bump on the upper sur face of the Philippine Sea plate beneath the Boso Peninsula, Japan inferred from seismic reflection surveys: A possible asperity of the 1703 Genroku earthquake" Tectono physics 472: 39–50. DOI: 10.1016/j.tecto.2008.05.009.
[3] F. M. Boler, S. Billington, and R. K. Zipf, (1997) “Seismological and energy balance constraints on the mechanism of a catastrophic bump in the Book Cliffs Coal Mining District, Utah, USA" International Journal of Rock Mechanics and Mining Sciences 34: 27–43. DOI: 10.1016/S1365-1609(97)80031-7.
[4] S. B. L. Cebry, K. Sorhaindo, and G. C. McLaskey, (2023) “Laboratory earthquake rupture interactions with a high normal stress bump" Journal of Geophysical Research: Solid Earth 128: e2023JB027297. DOI: 10.1029/2023JB027297.
[5] R. Rout and S. K. Pani. “Wireless Sensor Network Enabled Real-Time Monitoring of Environmental Status in Underground Mines using Machine Learning TechniquesandSeismicBumpDatabases”.In:7.2022, 1059–1067.
[6] E. C. Westman, K. A. Heasley, P. L. Swanson, and S. Peterson. “A correlation between seismic tomography, seismic events and support pressure”. In: ARMA USRock Mechanics/Geomechanics Symposium. ARMA, 2001, ARMA–01.
[7] M. Mokoatle, T. Coleman, and P. Mokilane. “A comparative study of over-sampling techniques as ap plied to seismic events”. In: Southern African conference for artificial intelligence research. Springer, 2023, 331–345. DOI: 10.1007/978-3-031-49002-6_22.
[8] P.Bharadwaj,W.Mulder,andG.Drijkoningen, (2016) “Full waveform inversion with an auxiliary bump functional" Geophysical Journal International 206: 1076 1092. DOI: 10.1093/gji/ggw129.
[9] K. Netti and Y. Radhika, (2016) “Minimizing loss of accuracy for seismic hazard prediction using Naive Bayes Classifier" IRJET 3: 75–77.
[10] S. Lasocki and B. Orlecka-Sikora, (2008) “Seismic hazard assessment under complex source size distribution of mining-induced seismicity" Tectonophysics 456: 28–37. DOI: 10.1016/j.tecto.2006.08.013.
[11] V. V. Nosov, (2015) “Bump hazard evaluation of a rock mass area as a result of its seismic acoustic activity registration" Journal of Mining Institute 216: 62–75.
[12] J. L. Ellenberger and K. A. Heasley, (2000) “Coal mine seismicity and bumps: historical case studies and current field activity": 1–9.
[13] K. Y. Haramy and J. P. McDonnell. Causes and control of coal mine bumps. US Department of the Interior, Bureau of Mines, 1988, 1–35.
[14] R. Sabapathy, P. S. Paul, and P. K. Mandal, (2019) “Evaluation of bump-proneness of underground coal mines using burst energy coefficient" Arabian Journal of Geo sciences 12: 579. DOI: 10.1007/s12517-019-4746-9.
[15] M. Alber, R. Fritschen, M. Bischoff, and T. Meier, (2009) “Rock mechanical investigations of seismic events in a deep longwall coal mine" International Journal of Rock Mechanics and Mining Sciences 46: 408–420. DOI: 10.1016/j.ijrmms.2008.07.014.
[16] S. W. Wang, D. B. Mao, J. F. Pan, J. G. Chen, F. B. Chen, and H. Lan, (2015) “Measurement on the whole process of abutment pressure evolution and microseismic activities at the lateral strata of goaf" Journal of China Coal Society 40: 2772–2779. DOI: 10.13225/j.cnki.jccs. 2015.0080.
[17] J.-G. LV, Y.-D. JIANG, and Y.-X. ZHAO, (2013) “Hi erarchical monitoring for coal bumps and its study and application of early warning methods" Journal of China Coal Society 38: 1161–1167.
[18] M.Y. I. N. WANGandT.Q.I. U. LAN,(2017) “Study on prediction of mine water inflow volume based on ARIMA product seasonal model" Coal Science and Technology: DOI: 10.13199/j.cnki.cst.2017.11.033.
[19] Q. Yang and X. Wu, (2006) “10 challenging problems in data mining research" International Journal of Information Technology & Decision Making 5: 597–604. DOI: 10.1142/S0219622006002258.
[20] M.Y. I. N. WANGandT.Q.I. U. LAN,(2017) “Study on prediction of mine water inflow volume based on ARIMA product seasonal model" Coal Science and Technology: DOI: 10.13199/j.cnki.cst.2017.11.033.
[21] Y. LeCun, Y. Bengio, and G. Hinton, (2015) “Deep learning" nature 521: 436–444. DOI: 10.1038/nature14539.
[22] J. Zhou, X. Li, and H. S. Mitri, (2015) “Comparative performance of six supervised learning methods for the development of models of hard rock pillar stability prediction" Natural Hazards 79: 291–316. DOI: 10.1007/s11069 015-1842-3.
[23] J. Zhou, X. Li, and H. S. Mitri, (2016) “Classification of rockburst in underground projects: comparison of ten supervised learning methods" Journal of Computing in Civil Engineering 30: 04016003. DOI: 10.1061/(ASCE)CP.1943-5487.0000553.
[24] J. Zhou, X. Li, and X. Shi, (2012) “Long-term prediction model of rockburst in underground openings using heuristic algorithms and support vector machines" Safety science 50: 629–644. DOI: 10.1016/j.ssci.2011.08.065.
[25] J. Zhou, X. Li, S. Wang, and W. Wei, (2013) “Identifi cation of large-scale goaf instability in underground mine using particle swarm optimization and support vector ma chine" International Journal of Mining Science and Technology 23: 701–707. DOI: 10.1016/j.ijmst.2013.08.014.
[26] M. Bayat, M. Bayat, M. Kia, H. R. Ahmadi, and I. Pakar, (2018) “Nonlinear frequency analysis of beams resting on elastic foundation using max-min approach" Geomechanics & engineering 16: 355–361. DOI: 10.12989/gae.2018.16.4.355.
[27] H.R. Ahmadi, A. M. Allahyari, and H. M. Allahyari, (2022) “Identifying damages in girders of bridges using square time-frequency distribution and neural network" Amirkabir Journal of Civil Engineering 54: 3287 3312. DOI: 10.22060/ceej.2022.19812.7262.
[28] E. Khajavi, A. R. T. Khanghah, and A. J. Khiavi. “An efficient prediction of punching shear strength in reinforced concrete slabs through boosting methods and metaheuristic algorithms”. In: Structures. 74. El sevier, 2025, 108519. DOI: 10.1016/j.istruc.2025. 108519.
[29] A. Parmar, R. Katariya, and V. Patel. “A review on random forest: An ensemble classifier”. In: International conference on intelligent data communication tech nologies and internet of things. Springer, 2018, 758–763. DOI: 10.1007/978-3-030-03146-6_86.
[30] A. Aulia, A. Rahman, and J. J. Q. Velasco. “Strategic well test planning using random forest”. In: SPE Intelligent Energy International Conference and Exhibition. SPE, 2014, SPE–167827. DOI: 10.2118/167827-MS.
[31] M. Pal, (2005) “Random forest classifier for re mote sensing classification" International journal of remote sensing 26: 217–222. DOI: 10.1080/01431160412331269698.
[32] R. Genuer, J.-M. Poggi, and C. Tuleau, (2008) “Random Forests: some methodological insights" arXiv preprint arXiv:0811.3619: DOI: 10.48550/arXiv.0811.3619.
[33] M. Dehghani, Z. Montazeri, E. Trojovská, and P. Trojovský, (2023) “Coati Optimization Algorithm: A new bio-inspired metaheuristic algorithm for solving op timization problems" Knowledge-based systems 259: 110011. DOI: 10.1016/j.knosys.2022.110011.
[34] J. O. Agushaka, A. E. Ezugwu, and L. Abualigah, (2022) “Dwarf mongoose optimization algorithm" Computer methods in applied mechanics and engineering 391: 114570. DOI: 10.1016/j.cma.2022.114570.