journal article·2026-07-16Open access

Rockburst Damage Scale Prediction in Underground Mines Using SMOTE-Based Resampling and Ensemble Learning

Kairat Sarsembayev, Amoussou Coffi Adoko, Rashid Afshar, Candan Gokceoglu

Applied Sciences· Volume 16· Issue 14

Abstract

Rockburst risk in seismically active mines poses a significant threat to underground safety. This study aims to improve the prediction of rockburst-induced damage by addressing the challenge of class imbalance, which is commonly encountered in rockburst datasets. Various data-balancing techniques, including the Synthetic Minority Oversampling Technique (SMOTE) and its variants, namely SMOTE-Tomek, KM-SMOTE, SMOTE-ENN, SVM-SMOTE, Borderline-SMOTE, and Adaptive Synthetic (ADASYN) sampling, were applied to a dataset containing rockburst damage scales and selected influencing parameters. The data were collected from Canadian and Australian underground mining operations affected by mining-induced seismicity. Three machine learning classifiers, namely Random Forest (RF), CatBoost (CB), and Gradient Boosting (GB), were trained and evaluated using accuracy, recall, precision, and F1-score metrics. The five best-performing models were SMOTE-ENN-GB, SMOTE-ENN-CB, SMOTE-ENN-RF, KM-SMOTE-CB, and Borderline-SMOTE-CB, achieving testing accuracies ranging from 70% to 88%. SHAP analysis further revealed that stress conditions and peak particle velocity (PPV) are the dominant factors controlling rockburst severity, while geological factors and support conditions act as secondary contributing factors. Compared with previous studies using the same dataset, the proposed approach achieved substantial improvements in predictive performance, particularly for the minority and severe rockburst classes. It is concluded that SMOTE-based balancing techniques, when combined with ensemble learning algorithms, can significantly improve rockburst damage prediction and contribute to safer and more effective risk management in deep, seismically active mining environments.
Source: crossref · Quality: baseline

Research context

OpenAlex topics: Rock Mechanics and Modeling · Seismology and Earthquake Studies · Landslides and related hazards

SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.

Affiliations

School of Mining & Geosciences, Nazarbayev University, Astana 010000, Kazakhstan

Faculty of Computer and Information Sciences, Cappadocia University, Nevşehir 50420, Turkey

Funding

Ministry of Science and Higher Education of the Republic of Kazakhstan · Nazarbayev University

References (69)

Show source-provided references
1. Using legacy 3D seismic data and source parameters of mining-induced earthquakes to mitigate the risk of rockbursting in Kloof Gold Mine, South Africa10.1111/1365-2478.13319 ↗
2. Amiri, M., Khosravifard, A., Riazi, M., Veiskarami, M., Adoko, A.C., Amerian, D., Rahimi, A., Shiroodi, S.K., Saeidi, O., and Rahbar, M. (2026). Impact of Salt Creep and Well Shut-Down on Casing Collapse in the Lower Fars Formation, Southern Iran. Rock Mech. Rock Eng., in press.10.1007/s00603-025-05197-x ↗
3. Rockburst risk control and mitigation in deep mining10.1016/j.deepre.2024.100019 ↗
4. Feng, X.-T. (2018). Rockbursts in Some Bushveld Platinum Mines. Rockburst, Butterworth-Heinemann.
5. Prediction and prevention of rockburst in metal mines–A case study of Sanshandao gold mine10.1016/j.jrmge.2015.11.002 ↗
6. Heal, D., Hudyma, M., and Potvin, Y. (2006, January 17–21). Evaluating Rockburst Damage Potential in Underground Mining. Proceedings of the Golden Rocks 2006, The 41st U.S. Symposium on Rock Mechanics (USRMS), Golden, CO, USA.
7. Feng, X.-T. (2018). Rockbursts in European Coal Mines. Rockburst, Butterworth-Heinemann.
8. Rockbursting Potential of Kimberlite: A Case Study of Diavik Diamond Mine10.1007/s00603-017-1294-z ↗
9. Feng, X.-T. (2018). Case Histories of Rockburst at Coal Mines. Rockburst, Butterworth-Heinemann.
10. Feng, X.-T. (2018). Rock Bursts in Tunnels in the Himalayas—A Case Review. Rockburst, Butterworth-Heinemann.
11. Rockburst in Ostrava-Karvina Coalfield10.1016/j.proeng.2017.05.289 ↗
12. Feng, X.-T. (2018). Rockbursts in Tunnels in China. Rockburst, Butterworth-Heinemann.
13. Long-term prediction model of rockburst in underground openings using heuristic algorithms and support vector machines10.1016/j.ssci.2011.08.065 ↗
14. Rockburst prediction and prevention in underground space excavation10.1016/j.undsp.2023.05.009 ↗
15. Developing intelligent classification models for rock burst prediction after recognizing significant predictor variables, Section 1: Literature review and data preprocessing procedure10.1016/j.tust.2018.09.022 ↗
16. Classification of Rockburst in Underground Projects: Comparison of Ten Supervised Learning Methods10.1061/(ASCE)CP.1943-5487.0000553 ↗
17. Evaluation method of rockburst: State-of-the-art literature review10.1016/j.tust.2018.08.029 ↗
18. Rockburst prediction in hard rock mines developing bagging and boosting tree-based ensemble techniques10.1007/s11771-021-4619-8 ↗
19. Numerical modeling for rockbursts: A state-of-the-art review10.1016/j.jrmge.2020.09.011 ↗
20. Wang, H., Li, Z., Song, D., He, X., Sobolev, A., and Khan, M. (2021). An Intelligent Rockburst Prediction Model Based on Scorecard Methodology. Minerals, 11.10.3390/min11111294 ↗
21. Fuzzy Cognitive Map for Evaluating Critical Factors Causing Rockbursts in Underground Construction: A Fundamental Study10.1007/s00603-024-04045-8 ↗
22. Application of KM-SMOTE for rockburst intelligent prediction10.1016/j.tust.2023.105180 ↗
23. Toward Precise Long-Term Rockburst Forecasting: A Fusion of SVM and Cutting-Edge Meta-heuristic Algorithms10.1007/s11053-024-10371-z ↗
24. Evaluation of rockburst occurrence and intensity in underground structures using decision tree approach10.1007/s00366-018-00695-9 ↗
25. Li, D., Liu, Z., Armaghani, D.J., Xiao, P., and Zhou, J. (2022). Novel Ensemble Tree Solution for Rockburst Prediction Using Deep Forest. Mathematics, 10.10.3390/math10050787 ↗
26. Rockburst prediction in kimberlite using decision tree with incomplete data10.1016/j.jsm.2018.07.004 ↗
27. Machine learning methods for rockburst prediction-state-of-the-art review10.1016/j.ijmst.2019.06.009 ↗
28. Intelligent rockburst prediction model with sample category balance using feedforward neural network and Bayesian optimization10.1016/j.undsp.2021.12.009 ↗
29. Research on Rockburst Prediction Classification Based on GA-XGB Model10.1109/ACCESS.2021.3085745 ↗
30. Strength of ensemble learning in multiclass classification of rockburst intensity10.1002/nag.3111 ↗
31. Strength of Stacking Technique of Ensemble Learning in Rockburst Prediction with Imbalanced Data: Comparison of Eight Single and Ensemble Models10.1007/s11053-020-09787-0 ↗
32. Predicting rockburst with database using particle swarm optimization and extreme learning machine10.1016/j.tust.2020.103287 ↗
33. Investigating the effective parameters on the risk levels of rockburst phenomena by developing a hybrid heuristic algorithm10.1007/s00366-019-00908-9 ↗
34. Prediction of rockburst risk in underground projects developing a neuro-bee intelligent system10.1007/s10064-020-01788-w ↗
35. Machine learning-based classification of rock discontinuity trace: SMOTE oversampling integrated with GBT ensemble learning10.1016/j.ijmst.2021.08.004 ↗
36. Rock burst risk assessment in deep-buried underground caverns: A novel analysis method10.1007/s12517-020-05328-4 ↗
37. Ensemble stacking rockburst prediction model based on Yeo–Johnson, K-means SMOTE, and optimal rockburst feature dimension determination10.1038/s41598-022-19669-5 ↗
38. Investigation and application of data balancing and combined discriminant model in rock burst severity prediction10.1038/s41598-024-81307-z ↗
39. Rockburst prediction model using machine learning based on microseismic parameters of Qinling water conveyance tunnel10.1007/s11771-023-5233-8 ↗
40. Novel stacking models based on SMOTE for the prediction of rockburst grades at four deep gold mines10.1016/j.undsp.2024.03.004 ↗
41. Han, H., Wang, W.-Y., and Mao, B.-H. (2005). Borderline-SMOTE: A New Over-Sampling Method in Imbalanced Data Sets Learning. Advances in Intelligent Computing, Springer.10.1007/11538059_91 ↗
42. Heal, D. (2010). Observations and Analysis of Incidences of Rockburst Damage in Underground Mines. [Ph.D. Dissertation, The University of Western Australia].
43. Kulgatov, A., and Adoko, A.C. (2022, January 26–29). Revisiting Rockburst Predictive Models for Seismically Active Mines. Proceedings of the 56th U.S. Rock Mechanics/Geomechanics Symposium, Santa Fe, NM, USA.10.56952/ARMA-2022-0827 ↗
44. Feasibility of stochastic gradient boosting approach for predicting rockburst damage in burst-prone mines10.1016/S1003-6326(16)64312-1 ↗
45. Duan, W. (2016). An Assessment of the Significance of Factors Affecting the Occurence of Rockburst Damage. Civil and Resource Engineering, The University of Western Australia.
46. Potvin, Y. (2015). Evaluation of the adjusted rockburst damage potential method for dynamic ground support selection in extreme rockburst conditions. Design Methods 2015: Proceedings of the International Seminar on Design Methods in Underground Mining, Australian Centre for Geomechanics.
47. Strategies and tactics to control seismic risks in mines
48. Rock instability and risk analyses in open stope mine design10.1139/t96-064 ↗
49. SMOTE: Synthetic minority over-sampling technique
50. SMOTE for learning from imbalanced data: Progress and challenges, marking the 15-year anniversary
51. LR-SMOTE—An improved unbalanced data set oversampling based on K-means and SVM10.1016/j.knosys.2020.105845 ↗
52. A study of the behavior of several methods for balancing machine learning training data10.1145/1007730.1007735 ↗
53. A hybrid sampling algorithm combining M-SMOTE and ENN based on Random forest for medical imbalanced data10.1016/j.jbi.2020.103465 ↗
54. Borderline over-sampling for imbalanced data classification10.1504/IJKESDP.2011.039875 ↗
55. Zheng, X. (2020). SMOTE Variants for Imbalanced Binary Classification: Heart Disease Prediction, University of California.
56. Haibo, H., Yang, B., Garcia, E.A., and Shutao, L. (2008, January 1–8). ADASYN: Adaptive synthetic sampling approach for imbalanced learning. Proceedings of the 2008 IEEE International Joint Conference on Neural Networks (IEEE World Congress on Computational Intelligence), Hong Kong, China.10.1109/IJCNN.2008.4633969 ↗
57. Random Forests10.1023/A:1010933404324 ↗
58. CatBoost for big data: An interdisciplinary review10.1186/s40537-020-00369-8 ↗
59. Artificial Neural Networks, Gradient Boosting and Support Vector Machines for electric vehicle battery state estimation: A review10.1016/j.est.2022.105384 ↗
60. A fast algorithm for two-dimensional Kolmogorov–Smirnov two sample tests10.1016/j.csda.2016.07.014 ↗
61. Potvin, Y. (2015). Empirical design methods in practice. Proceedings of the International Seminar on Design Methods in Underground Mining, Australian Centre for Geomechanics.
62. Application of Data Analysis Techniques to Identify Rockburst Mechanisms, Triggers, and Contributing Factors in Cave Mining10.1007/s00603-022-03206-x ↗
63. Chicco, D., and Jurman, G. (2020). The advantages of the Matthews correlation coefficient (MCC) over F1 score and accuracy in binary classification evaluation. BMC Genom., 21.10.1186/s12864-019-6413-7 ↗
64. Multi-level intelligent warning modeling of pre-drilled sandstone containing three holes using an integration of statistical analysis and LightGBM algorithm10.1016/j.tafmec.2026.105596 ↗
65. AI-aided short-term decision making of rockburst damage scale in underground engineering10.1016/j.undsp.2025.02.005 ↗
66. Evaluating short-term rock burst damage in underground mines using a systems approach10.1080/17480930.2019.1657654 ↗
67. Establishing a Bayesian Network model for predicting rockburst damage potential10.1088/1755-1315/861/6/062094 ↗
68. Sansyzbekov, G., and Adoko, A.C. (2021, January 18–25). Quantifying Underground Excavation Damage Induced by Mine Seismicity. Proceedings of the 55th U.S. Rock Mechanics/Geomechanics Symposium, Virtual.
69. Predicting rockburst damage scale in seismically active mines using a classifier ensemble approach10.1088/1755-1315/1124/1/012102 ↗