Large artificial intelligence models for coal mining: Development, applications and challenges

Abstract

Large-scale artificial intelligence (AI) models are increasingly shaping safety, efficiency, and sustainability in the mining industry. This paper reviews the development, applications, and challenges of domain-specific large AI models in coal mining. These models integrate heterogeneous multimodal data—text, images, video, audio, design data, point clouds, and time series—within multi-layered architectures encompassing infrastructure, data resources, algorithms, application services, and security. Application platforms supporting knowledge services, visual analysis, and intelligent scheduling demonstrate practical improvements in operational decision-making. Despite these advances, deployment faces challenges including fragmented data, limited labeled datasets, few-/zero-shot scenarios, industry-specific adaptation, robustness and interpretability, weak causal reasoning, edge computing limitations, cost–benefit trade-offs, and compatibility issues. Overcoming these barriers requires coordinated progress in data governance, model design, and industry standardization.

Keywords

large artificial intelligence models / domain-specific large language models / multimodal data / coal mining applications

References

[1] Ma YK, Nie BS, He XQ, Li XC, Meng JQ, Song DZ. Mechanism investigation on coal and gas outburst: An overview. Int. J. Miner. Metall. Mater., 2020, 277872

[2] Wang GF, Zhang JZ, Liu ZB, Pang YH, Wang T, Sang C. Progress in digital and intelligent technologies for complex giant systems in green coal development. Coal Sci. Technol., 2024, 52111

[3] L. Li, S.M. Ma, X. Liu, et al., Coal measure gas resources matter in China: Review, challenges, and perspective, Phys. Fluids, 36(2024), No. 7, art. No. 071301.

[4] B.Q. Lin and Y.J. Song, Coal price shocks and economic growth: A province-level study of China, Energy Policy, 193(2024), art. No. 114297.

[5] X.Z. Yan, D. Tong, Y.X. Zheng, et al., Cost-effectiveness uncertainty may bias the decision of coal power transitions in China, Nat. Commun., 15(2024), art. No. 2272.

[6] Naveed H, Khan AU, Qiu S, et al. . A comprehensive overview of large language models. ACM Trans. Intell. Syst. Technol., 2025, 1651

[7] G. Du and A. Chen, Coal mine accident risk analysis with large language models and Bayesian networks, Sustainability, 17(2025), No. 5, art. No. 1896.

[8] Teng TS. Volumetric mediation of the subterranean mine: Geologic intimacy in a Taiwan coal village. Environ. Plan. D Soc. Space, 2025, 433505

[9] E.S. Kliuiev, R.A. Ahaiev, K. Ye Dudlia, V.V. Vlasenko, and V.V. Zberovskyi, Analysis of quantitative and qualitative parameters of gas mixture in thermal processes of mine medium, IOP Conf. Ser.: Earth Environ. Sci., 1415(2024), No. 1, art. No. 012030.

[10] X.G. Cao, X.L. Wang, L.Y. Shi, X. Yang, X.Y. Zhang, and Y. Duan, A construction method for a coal mining equipment maintenance large language model based on multi-dimensional prompt learning and improved LoRA, Mathematics, 13(2025), No. 10, art. No. 1638.

[11] Jami HC, Singh PR, Kumar A, Bakshi BR, Ramteke M, Kodamana H. CCU-Llama: A knowledge extraction LLM for carbon capture and utilization by mining scientific literature data. Ind. Eng. Chem. Res., 2024, 634117585

[12] Pan GF, Wang FY, Shang CL, et al. . Advances in machine learning- and artificial intelligence-assisted material design of steels. Int. J. Miner. Metall. Mater., 2023, 3061003

[13] Thirunavukarasu AJ, Ting DSJ, Elangovan K, Gutierrez L, Tan TF, Ting DSW. Large language models in medicine. Nat. Med., 2023, 2981930

[14] Masalkhi M, Ong J, Waisberg E, Lee AG. Google Deep-Mind’s gemini AI versus ChatGPT: A comparative analysis in ophthalmology. Eye, 2024, 3881412

[15] Park J, Choo S. Generative AI prompt engineering for educators: Practical strategies. J. Spec. Educ. Technol., 2025, 403411

[16] Sunil B M, Liyakat KSS, Liyakat KKS. Al-driven IoT (AI IoT) in thermodynamic engineering. J. Mod. Thermodyn. Mech. Syst., 2025, 611

[17] Wang GF, Pang YH, Wang DD. Research on new quality productive forces cultivation and high-quality development of coal. China Coal, 2024, 50121

[18] E. Ullah, A. Parwani, M.M. Baig, and R. Singh, Challenges and barriers of using large language models (LLM) such as ChatGPT for diagnostic medicine with a focus on digital pathology–A recent scoping review, Diagn. Pathol., 19(2024), No. 1, art. No. 43.

[19] F. Busch, L. Hoffmann, C. Rueger, et al., Current applications and challenges in large language models for patient care: A systematic review, Commun. Med., 5(2025), No. 1, art. No. 26.

[20] Ong JCL, Chang SY, William W, et al. . Ethical and regulatory challenges of large language models in medicine. Lancet Digit. Health, 2024, 66e428

[21] Wang GF, Fu JX, Wang ZX. Important progress in coal mine intelligence and directions for high-quality development. J. Intell. Mine, 2025, 612

[22] Wang GF, Ren HW, Fu JX. Challenge and path of high-quality development in coal mine intelligent construction. Coal Sci. Technol., 2025, 5311

[23] X.G. Cao, W.T. Xu, J.B. Zhao, Y. Duan, and X. Yang, Research on large language model for coal mine equipment maintenance based on multi-source text, Appl. Sci., 14(2024), No. 7, art. No. 2946.

[24] Wang Y, Zu ZS, Wang ZH. A metadata standard construction method based on intelligent mine data classification and coding standards. J. Mine Autom., 2024, 507130

[25] Wang HJ. Construction exploration and application prospect of the large model in mining industry. Coal Sci. Technol., 2024, 521145

[26] Mao SJ, Chen ZX, Chen HZ, et al. . Development and application of a coal mine intelligent management and control platform based on a transparent geological assurance system. J. Intell. Min., 2024, 5344

[27] Yuan G. A method for intelligent monitoring question answering on coal mine safety based on the integration of knowledge graph and large language model. 2025 10th International Conference on Intelligent Computing and Signal Processing (ICSP). 2025784

[28] S. Chaudhari, P. Aggarwal, V. Murahari, et al., RLHF deciphered: A critical analysis of reinforcement learning from human feedback for LLMs, ACM Comput. Surv., 58(2025), No. 2, art. No. 53.

[29] Li ZW, Liu F, Yang WJ, Peng SH, Zhou J. A survey of convolutional neural networks: Analysis, applications, and prospects. IEEE Trans. Neural Netw. Learn. Syst., 2022, 33126999

[30] Li Y, Qu C. Research on lightweight compression algorithms and deployment optimization for large language models on mobile terminals. Proceedings of the 2nd Guangdong-Hong Kong-Macao Greater Bay Area International Conference on Digital Economy and Artificial Intelligence. 2025164

[31] China Academy of Information and Communications Technology, Research Report on the Benchmark Testing System of Large Models (2024) [2025-10-09]. http://m.toutiao.com/group/7395016249845056039/

[32] P. Kumar, Large language models (LLMs): Survey, technical frameworks, and future challenges, Artif. Intell. Rev., 57(2024), No. 10, art. No. 260.

[33] Raiaan MAK, Mukta MSH, Fatema K, et al. . A review on large language models: Architectures, applications, taxonomies, open issues and challenges. IEEE Access, 2024, 1226839

[34] Yan LX, Sha LL, Zhao LX, et al. . Practical and ethical challenges of large language models in education: A systematic scoping review. Br. J. Educ. Technol., 2024, 55190

[35] G.F. Wang, H.W. Ren, G.R. Zhao, et al., Research and practice of intelligent coal mine technology systems in China, Int. J. Coal Sci. Technol., 9(2022), No. 1, art. No. 24.

[36] B.B. Yu, B. Wang, and Y.T. Zhang, Application of artificial intelligence in coal mine ultra-deep roadway engineering: A review, Artif. Intell. Rev., 57(2024), No. 10, art. No. 262.

[37] B. Zeng, X.Y. Yang, P.D. Hu, et al., Towards a digitally enabled intelligent coal mine integrated energy system: Evolution, conceptualization, and implementation, Sustain. Energy Technol. Assess., 73(2025), art. No. 104128.

[38] J.X. Shi, X.Y. Zhao, L.B. Zeng, Y.Z. Zhang, and S.Q. Dong, Identification of coal structures by semi-supervised learning based on limited labeled logging data, Fuel, 337(2023), art. No. 127191.

[39] W.J. Yang, X.H. Zhang, B. Ma, et al., An open dataset for intelligent recognition and classification of abnormal condition in longwall mining, Sci. Data, 10(2023), art. No. 416.

[40] L. Wang, B.S. Jia, and G.R. Su, Prediction of coal and gas outbursts based on physics informed neural networks and traditional machine learning models, Sci. Rep., 15(2025), art. No. 29984.

[41] Vettoruzzo A, Bouguelia MR, Vanschoren J, Rögnvaldsson T, Santosh K. Advances and challenges in meta-learning: A technical review. IEEE Trans. Pattern Anal. Mach. Intell., 2024, 4674763

[42] W.P. Cao, Y.H. Wu, Y.X. Sun, et al., A review on multimodal zero-shot learning, Wires Data Min. Knowl. Discov., 13(2023), No. 2, art. No. e1488.

[43] A.G. Khoee, Y.N. Yu, and R. Feldt, Domain generalization through meta-learning: A survey, Artif. Intell. Rev., 57(2024), No. 10, art. No. 285.

[44] Du ZP, Shit M, Deng JK. Boosting object detection with zero-shot day-night domain adaptation. 2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). 202412666

[45] Gao H, Guo JC, Wang GL, Zhang Q. Cross-domain correlation distillation for unsupervised domain adaptation in nighttime semantic segmentation. 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). 20229903

[46] N. Paeedeh, M. Pratama, M.A. Ma’sum, W. Mayer, Z.H. Cao, and R. Kowlczyk, Cross-domain few-shot learning via adaptive transformer networks, Knowl. Based Syst., 288(2024), art. No. 111458.

[47] Matloob S, Li Y, Khan KZ. Safety measurements and risk assessment of coal mining industry using artificial intelligence and machine learning. Open J. Bus. Manag., 2021, 931198

[48] Y. Uchida, K. Fujiwara, T. Saito, and T. Osaka, Causal plot: Causal-based fault diagnosis method based on causal analysis, Processes, 10(2022), No. 11, art. No. 2269.

[49] Nadim K, Ragab A, Ouali MS. Data-driven dynamic causality analysis of industrial systems using interpretable machine learning and process mining. J. Intell. Manuf., 2023, 34157

[50] Wang GF, Pang YH, Ren HW, et al. . System engineering and key technologies research and practice of smart mine. J. China Coal Soc., 2024, 491181

[51] Jiang DY, Wei LK, Wang C, Fan JY, Ren YW. Discussion on the technology architecture and key basic support technology for intelligent mine edge—Cloud collaborative computing. J. China Coal Soc., 2020, 451484

[52] Ding EJ, Yu X, Xia B, et al. . Development of mine informatization and key technologies of intelligent mines. J. China Coal Soc., 2022, 471564

[53] L.F. Tao, H.F. Liu, G.A. Ning, W.Y. Cao, B.H. Huang, and C. Lu, LLM-based framework for bearing fault diagnosis, Mech. Syst. Signal Process., 224(2025), art. No. 112127.

[54] Gallifant J, Afshar M, Ameen S, et al. . The TRIPOD-LLM reporting guideline for studies using large language models. Nat. Med., 2025, 31160

[55] S. Pahune and Z. Akhtar, Transitioning from MLOps to LLMOps: Navigating the unique challenges of large language models, Information, 16(2025), No. 2, art. No. 87.

[56] Wang JQ, Shi EZ, Hu HW, et al. . Large language models for robotics: Opportunities, challenges, and perspectives. J. Autom. Intell., 2025, 4152

[57] You XS, Ge SR, Guo YN, Miao B. Digital twin-driven control construction for three machines of smart coal mining face. J. China Coal Soc., 2024, 4973265

[58] Guo YN, Yang F, Ge SR, Huang Y, You XS. Novel knowledge-driven active management and control scheme of smart coal mining face with digital twin. J. China Coal Soc., 2023, 48Suppl.1334

[59] Liu XQ. Criminal risks and criminal law responses in the era of artificial intelligence. Stud. Law Bus., 2018, 3513

RIGHTS & PERMISSIONS

University of Science and Technology Beijing