Irkutsk National Research Technical University (Irkutsk, Russia)
R. A. Druz, Post-Graduate, druz01@inbox.ru
B. N. Olzoev, Candidate of Geographical Sciences, Associate Professor
The purpose of the study is to systematize Russian and foreign scientific publications for the period 2019-2026 on the use of neural networks and machine learning methods in mine surveying. The review methodology is based on the search and analysis of peer-reviewed sources in the international and domestic databases Scopus, Google Scholar, arXiv, MDPI, CyberLeninka and eLibrary, followed by classification by thematic areas and a comparative analysis of the achieved accuracy metrics. The results show that neural network methods are used in six key specialty: quarry segmentation (F1 up to 94.6 %), bench crest detection from point clouds (IoU up to 62.2 %), highwall slope stability monitoring (accuracy up to 97 %), mineral resource classification, mining productivity forecasting (R2 = 0.80), and digital twin generation. It has been established that the problem of automatic selection of bench crest remains the least solved and represents the greatest scientific groundwork for research in the field of camera processing of mining quarry survey data.
1. Digital revolution underground: unmanned dump trucks and artificial intelligence in Russian mines. Dobyvayushchaya promyshlennost. 2025. No. 6. pp. 46–50.
2. Available at: http://government.ru/docs/35964/ (accessed: 25.04.2026).
3. National Project “Data Economy and Digital Transformation of the State”. The Russian Government. Available at: http://government.ru/rugovclassifier/923/about/ (accessed: 04.04.2026).
4. On the inclusion of the federal project “Artificial Intelligence” in the national project “Data Economy” : information message. The Federal Service for Supervision of Transport. Available at: https://rostransnadzor.gov.ru/news/5950 (accessed: 20.04.2026).
5. Effective domestic practices of artificial intelligence technologies application in the fuel and energy complex. Digital Economy, 2024. 116 p.
6. Digitalization of the mining industry – 2024: dreams and reality. Dobyvayushchaya promyshlennost. 2024. No. 4. pp. 24–30.
7. Digital Economy summarized its analytical findings for the year. Digital Economy, 2024. Available at: https://d-economy.ru/news/ano-cifrovaja-jekonomika-podvelaanaliticheskie-itogi-goda-2/ (accessed: 28.04.2026).
8. Himmy O., Nguyen T. T., Vazhacharickal P. J., Buerkert A. Monitoring of granite quarries using deep learning and UAV photogrammetry in Bengaluru, India. PLoS One. 2025. Vol. 20(11). ID e0334493.
9. Balaska V., Papapetros I. T., Oikonomou K. M., Bampis L., Gasteratos A. UAV Object Detection and Positioning in a Mining Industrial Metaverse with Custom Geo-Referenced Data. Journal of Latex Class Files. 2025. Vol. 14, No. 8. DOI: 10.48550/arXiv.2506.13505
10. Cui P., Meng X., Zhang W. Step feature line extraction from large-scale point clouds of open-pit mine based on structural characteristics. Scientific Reports. 2024. Vol. 14. DOI: 10.1038/s41598-024-69368-6
11. Beretta F., Rodrigues Á. L., Peroni R. de L., Costa J. F. C. L. Using UAV for automatic lithological classification of open pit mining front. REM – International Engineering Journal. 2019. Vol. 72(1). pp. 17–23.
12. Weidner L., Walton G. Generalized Extraction of Bolts, Mesh, and Rock in Tunnel Point Clouds: A Critical Comparison of Geometric Feature-Based Methods Using Random Forest and Neural Networks. Remote Sensing. 2024. Vol. 16, Iss. 23. ID 4466.
13. Hosseinzadeh H., Nowrouzi G., Rafieenia E. Prediction of slope stability in open-pit mines using intelligent algorithms: SVM and RF optimized by genetic algorithm. Journal of Geomine. 2025. Vol. 3, No. 2. pp. 106–116.
14. Frainz G., Pedrosa H. Artificial Neural Network-Based Optimization of Open Pit Design in Iron Mining. Proceedings of the 3rd Workshop on the Future of Machine Learning in Geotechnics. Florence, 2025.
15. Deng T., He J., Sun J., Peng S., Pang X. et al. Intelligent optimization of slope step parameters in open pit mines containing weak interbedded layers based on machine learning and multi-objective optimization methods. Frontiers in Earth Science. 2025. Vol. 13. ID 1666375.
16. Li M., Ding K., Pang L., Shu Y., Qu Y. Deformation Monitoring and Prediction of Open-pit Mine Slope Based on GBInSAR Technology and LSTM Neural Network. ISPRS Annals of the Photogrammetry Remote Sensing and Spatial Information Sciences. 2026. Vol. X-3/W3-2025. pp. 173–178.
17. Letshwiti T. M., Shahsavar M., Moniri-Morad A., Sattarvand J. Deep learning-based image segmentation for highwall stability monitoring in open pit mines. Journal of Engineering Research. 2025. Vol. 13, Iss. 4. pp. 3595–3608.
18. Meller A. D., Galieva R. R., Kuleshova A. V., Petrosyan A. K., Glatko S. A. Monitoring deformations of metro transit tunnels using a neural network approach. Gornaya Promyshlennost. 2025. No. 2. pp. 163–166.
19. Rizaldy A., Afifi A. J., Ghamisi P., Gloaguen R. Improving Mineral Classification Using Multimodal Hyperspectral Point Cloud Data and Multi-Stream Neural Network. Remote Sensing. 2024. Vol. 16, Iss. 13. ID 2336.
20. AI in the Mining Industry: From Ore to Optimization. Ultralytics. Available at: https://www.ultralytics.com/ru/blog/ai-in-the-mining-industry-from-ore-to-optimization (accessed: 28.04.2026).
21. Kumah F. N., Saim A. K., Oppong M. N., Arthur C. K. Predicting open-pit mine production using machine learning techniques. Journal of Sustainable Mining. 2024. Vol. 23, No. 2. pp. 118–131.