Advanced methods and tools for geomechanical monitoring based on machine learning technologies

In the geomechanical monitoring of rockburst-hazardous deposits, modern rock pressure control systems record significant volumes of data. Processing such large data volumes necessitates the use of advanced methods and tools based on machine learning technologies. This work focuses on processing data from the «Prognoz-ADS» system at the Nikolaevskoye deposit. The hierarchical approach to data processing requires automatic classification of lower-level data – recorded impulses. The impulses are divided into three categories: natural acoustic emission, signals from drilling operations, and signals arising from blasting operations. The study examines the main stages of designing a machine learning classification model. The resulting model achieved accuracy exceeding 95%, enabling more comprehensive information on the state of the rock mass to be obtained and contributing to enhanced safety and efficiency of mining operations. 

Grunin A. P., Konstantinov A. V., Lomov M. E. Advanced methods and tools for geomechanical monitoring based on machine learning technologies. MIAB. Mining Inf. Anal. Bull. 2025;(12-2):166-179. [In Russ]. DOI: 10.25018/0236_1493_2025_122_0_166.

A.P. Grunin¹, Cand. Sci. (Eng.), Senior Researcher, e-mail: lexx188@mail.ru, ORCID ID: 0009-0002-2394-5608, 
A.V. Konstantinov¹, Researcher, e-mail: alex-sdt@yandex.ru, ORCID ID: 0000-0001-6481-292X, 
M.A. Lomov¹, Junior Researcher, e-mail 9241515400@mail.ru,
¹ Mining Institute of the Far Eastern Branch of Russian Academy of Sciences, 680000, Khabarovsk, Russia.

A.P. Grunin, e-mail: lexx188@mail.ru.

1. Kozyrev A. A., Batugin A. S., Zhukova S. A. On the effect of water saturation of rock mass on its seismic activity during mining of Khibiny apatite deposits. Gornyi Zhurnal. 2021, no. 1, pp. 31—36. [In Russ]. DOI: 10.17580/gzh.2021.01.06.

2. Rasskazov I. Yu., Anikin P. A., Grunin A. P., Migunov D. S., Tereshkin A. A. Improvement of technical means for local control of rockburst hazard during mining operations. Journal of Mining Sciences. 2023, no. 5, pp. 177—184. [In Russ]. DOI: 10.15372/FTPRPI20230519.

3. Abetov A., Kudaibergenova S., Sidorov V. Creation of geodynamic polygons and technologies for conducting geodynamic monitoring in the hydrocarbon fields. Engineering Journal of Satbayev University. 2021, vol. 143, no. 2, pp. 3—13. DOI: 10.51301/vest.su.2021.i2.01.

4. Rasskazov I. Yu., Anikin P. A., Grunin A. P., Konstantinov A. V. Methods and means of geomechanical monitoring for safe and effective subsoil development. Gornyi Zhurnal. 2025, no. 3, pp. 4—11. [In Russ]. DOI: 10.17580/gzh.2025.03.01.

5. Rasskazov I. Yu., Fedotova Yu. V., Anikin P. A., Migunov D. S., Konstantinov A. V. Improvement of geomechanical monitoring methods and tools based on digital technologies. Russian Mining Industry Journal. 2023, no. S5, pp. 18—24. [In Russ]. DOI: 10.30686/1609-9192-2023-5S-18-24.

6. Bychkov I. V., Vladimirov D. Ya., Oparin V. N., Potapov V. P., Shokin Yu. I. Mining informatics and big data problem in creating integrated monitoring systems for mining safety. Journal of Mining Sciences. 2016, no. 6, pp. 163—179.

7. Song Y., Wang E., Yang H., Liu C., Di Y., Li B., Chen D. Comprehensive early warning of rockburst hazards based on unsupervised learning. Physics of Fluids. 2024, vol. 36, no. 7, article 076628. DOI: 10.1063/5.0221722.

8. Grunin A. P., Sidlyar A. V., Kosmatov S. B. Reducing the error of seismic-acoustic event location in the rock mass geomechanical monitoring system «Prognoz-ADS». Bulletin of Pacific national university. 2024, no. 1(72), pp. 13—20. [In Russ].

9. Radisavlevich J. Application of artificial neural networks for predicting seismic vibration intensity at Veliki Krivelj copper mine. Journal of Mining Sciences. 2023, no. 2, pp. 34—47. [In Russ]. DOI: 10.15372/FTPRPI20230204.

10. Ahn H., Kim S., Lee K., Choi A., You K. Imbalanced seismic event discrimination using supervised machine learning. Sensors. 2022, vol. 22, article 2219. DOI: 10.3390/s22062219.

11. Zhang W. An improved DBSCAN algorithm for hazard recognition of obstacles in unmanned scenes. Soft Computing. 2023, vol. 27, pp. 18585—18604.

12. Schubert E., Sander J., Ester M., Kriegel H. P., Xu X. DBSCAN revisited, revisited: Why and how you should (still) use DBSCAN. ACM Transactions on Database Systems. 2017, vol. 42, no. 3, pp. 1—21. DOI: 10.1145/3068335.

13. Radeef Z. M., Hashem S. H., Gbashi E. K. New feature selection using principal component analysis. Journal of Soft Computing and Computer Applications. 2024, vol. 1, no. 2, article 1012. DOI: 10.70403/3008-1084.1012.

14. Das M. P., Dhar V. K., Verma S., Yadav K. K. Dimensionality reduction and sensitivity improvement for TACTIC Cherenkov data using t-SNE machine learning algorithm. Nuclear Instruments and Methods in Physics Research Section A. 2023, vol. 1057, article 168683. DOI: 10.1016/j.nima.2023.168683.

15. Jing R., Xue L., Li M., Yu L., Luo J. layerUMAP: A tool for visualizing and understanding deep learning models in biological sequence classification using UMAP. iScience. 2022, vol. 25, no. 12, article 105530. DOI: 10.1016/j.isci.2022.105530.

16. Butorin A., Mokhov G. Implementation of seismic facies analysis using the random forest classification. ProGREss’21, European Association of Geoscientists & Engineers. 2021, vol. 2021, pp. 1—5. DOI: 10.3997/2214-4609.202159080.

17. Oktafiani R., Hermawan A., Avianto D. Max depth impact on heart disease classification: decision tree and random forest. Jurnal RESTI (Rekayasa Sistem dan Teknologi Informasi). 2024, vol. 8, pp. 160—168.

18. Doke P., Shrivastava D., Pan C., Zhou Q., Zhang Y.-D. Using CNN with Bayesian optimization to identify cerebral micro-bleeds. Machine Vision and Applications. 2020, vol. 31, article 67. DOI: 10.1007/s00138-020-01087-0.

19. Markoulidakis J., Kopsiaftis G., Rallis I., Georgoulas I. Multiclass confusion matrix reduction method and its application on net promoter score classification problem. Technologies. 2021, vol. 9, no. 4, article 81. DOI: 10.1145/3453892.3461323.

20. Mazumder P., Baruah S. A hybrid model for predicting classification dataset based on random forest, support vector machine and artificial neural network. International Journal of Innovative Technology and Exploring Engineering. 2023, vol. 13, pp. 19—25. DOI: 10.35940/ijitee.A9757.1213123.