留言板

尊敬的读者、作者、审稿人, 关于本刊的投稿、审稿、编辑和出版的任何问题, 您可以本页添加留言。我们将尽快给您答复。谢谢您的支持!

姓名
邮箱
手机号码
标题
留言内容
验证码

AI赋能煤地质学：进展、挑战与展望

代世峰,  许娜,  朱伟,  李鹏飞,  齐安良煜,  刘宇,  颜瑞雯,  赵正福

文章导航 > 地质力学学报  > 2026 >  32(5): 1049-1061
代世峰，许娜，朱伟，等，2026. AI赋能煤地质学：进展、挑战与展望[J]. 地质力学学报，32（5）：1049−1061 doi: 10.12090/j.issn.1006-6616.2026060
引用本文: 代世峰，许娜，朱伟，等，2026. AI赋能煤地质学：进展、挑战与展望[J]. 地质力学学报，32（5）：1049−1061 doi: 10.12090/j.issn.1006-6616.2026060
shu
DAI S F，XU N，ZHU W，et al.，2026. Artificial intelligence-empowered coal geology: advances, challenges, and prospects[J]. Journal of Geomechanics，32（5）：1049−1061 doi: 10.12090/j.issn.1006-6616.2026060
Citation: DAI S F，XU N，ZHU W，et al.，2026. Artificial intelligence-empowered coal geology: advances, challenges, and prospects[J]. Journal of Geomechanics，32（5）：1049−1061 doi: 10.12090/j.issn.1006-6616.2026060
shu

AI赋能煤地质学：进展、挑战与展望

doi: 10.12090/j.issn.1006-6616.2026060

  • 中国矿业大学（北京）地球科学与测绘工程学院，北京 100083

基金项目: 国家自然科学基金项目（42372191，42321002，42472230）
详细信息
    作者简介:

    代世峰（1970—），男，博士，教授，中国科学院院士，主要从事煤地质学、地球化学和煤系关键金属矿产的科学研究。Email：dsf@cumtb.edu.cn

    通讯作者:

    许娜（1982—），女，博士，教授，主要从事人工智能与地球科学研究。Email：xuna@cumtb.edu.cn

  • 中图分类号: P618.11；TP18；P595

Artificial intelligence-empowered coal geology: advances, challenges, and prospects

  • College of Geoscience and Survey Engineering, China University of Mining and Technology (Beijing), Beijing 100083, China

Funds: This research was financially supported by the National Natural Science Foundation of China (Grants Nos. 42372191, 42321002, and 42472230).
More Information
    Author Bio:

    代世峰，中国科学院院士，中国矿业大学（北京）教授，2025年获第十九次李四光地质科学奖科研奖。主要从事地质学和煤系关键金属矿产的科研和教学工作。作为负责人主持了国家自然科学基金创新研究群体项目、国家973项目、国家自然科学基金重大研究计划、国家重点研发计划项目等重要研究任务。在国内外主流期刊上发表论文200余篇，总被引（他引）3万余次。任JCR一区国际期刊International Journal of Coal Geology主编。入选科睿唯安全球高被引科学家(2019—2025)、爱思唯尔中国高被引学者(2014—2024)。曾获国际有机岩石学会最高奖John Castano奖(2021)、美国地质学会能源地质奖Gilbert H. Cady奖(2023)、以第一完成人2次获得国际有机岩石学会Dal Swaine奖(2017和2024)

    摘要
  • 摘要: 人工智能的快速发展正在改变地球科学的研究范式。煤地质学的研究对象是煤、煤层、含煤岩系、煤盆地以及与煤共伴生矿产，其物质组成极其复杂，具有强非均质性、多尺度性和显著时空变异性。煤地质学研究的主要方向（如煤岩学、煤质学、煤系关键金属及煤层气勘探开发）与人工智能方法高度契合，人工智能正在推动煤地质学由传统经验识别和局部统计分析向多源数据融合、智能预测、机理解释并重的新范式转变，并且为发现新的地质现象提供了可能。文章系统综述了人工智能在煤显微组分智能识别、煤炭质量智能预测、煤系关键金属赋存状态与资源潜力智能评价、煤层气智能勘探开发等研究中的进展。人工智能技术在提升显微组分图像识别、煤质参数预测、煤系关键金属赋存模式发现和综合评价、煤层气甜点区评价与产能预测的效率与精度等方面具有重要作用，同时也面临高质量数据集不足、跨区域泛化能力有限、模型解释性与地质机理契合性弱、知识约束不够以及工程场景落地不足等问题。未来应加强煤地质学标准化大数据库建设，推动煤地质学知识与数据驱动模型深度融合，发展煤地质学可解释、可迁移的智能模型，构建面向煤地质学重大科学问题与关键矿产资源绿色高效开发的智能研究范式。

     

    Abstract:   Objective  The rapid development of artificial intelligence (AI) is reshaping the research paradigm of geosciences. Coal geology focuses on coal, coal seams, coal-bearing strata, coal basins, and the mineral resources that coexist or are associated with coal-bearing strata. These research objects exhibit highly complex material compositions, multiscale characteristics, and pronounced spatiotemporal variability. Consequently, major research directions of coal geology, including coal petrology, coal quality evaluation, critical metals in coal-bearing strata, and coalbed methane exploration and development, are particularly well suited to AI-based approaches.   Methods  AI is driving coal geology beyond traditional, experience-based identification and localized statistical analysis toward a new paradigm integrating multi-source data fusion, intelligent prediction, and mechanistic interpretation. It also provides new opportunities for discovering previously unrecognized geological phenomena.  Results  This paper systematically reviews recent advances in AI applications to the intelligent identification of coal macerals, prediction of coal quality, assessment of the occurrence modes and resource potentials of critical metals in coal-bearing strata, and prediction of coalbed methane. AI technologies have significantly improved the efficiency and accuracy of maceral image recognition, coal quality parameter prediction, identification of critical metal occurrence patterns in coal, and comprehensive resource evaluation. However, several challenges remain, including the scarcity of high-quality datasets, limited cross-regional generalization capability, weak model interpretability, insufficient consistency with geological mechanisms, inadequate knowledge constraints, and limited implementation in engineering scenarios.  Conclusions  Future research should strengthen the development of standardized large-scale databases, promote the deep integration of geological knowledge with data-driven models, develop interpretable and transferable AI models, and establish an intelligent research paradigm oriented toward major scientific questions in coal geology and the green and efficient development of critical mineral resources.  Significance  This review highlights the transformative role of AI in advancing coal geology from experience-driven analysis toward knowledge-guided, intelligent research, providing methodological support for major scientific discoveries and the green and efficient development of coal-related resources.

     

    • HTML全文

  • 图  1  煤显微组分智能识别发展主要技术路径

    Figure  1.  Development of coal maceral identification by AI

    下载: 全尺寸图片 幻灯片

    表  1  人工智能方法在HHV和HGI预测中的代表性应用

    Table  1.   Representative applications of AI methods in HHV and HGI prediction

    预测指标 输入变量 人工智能方法 预测效果 代表性文献
    HHV 工业分析指标：水分、灰分、挥
    发分、固定碳    		 SVR 测试集平均绝对误差为2.95%（中国
    煤样）和2.43%（美国煤样）；相关系数
    r分别为0.978和0.994。    		 Tan et al.，2015
    HHV 工业分析指标：水分、标准灰分、
    挥发分、固定碳    		 GBRT、MLR、SVR、GPR、ANN 测试集R2为0.9862（COALQUAL）和0.9541（Kentucky）；MAE为0.462和0.519 MJ/kg；MAPE均为0.019。 Xu et al.，2023a
    HHV 元素分析指标：C、H、O、N、S GS/MARS、MLP、MLR GS/MARS测试集R2=0.9921、r=0.9960、RMSE=0.1626，优于MLP（R2=0.9345）和MLR（R2=0.8683）。 García-Nieto et al.，2024
    HGI 工业分析、元素分析、氧化物和
    煤岩参数    		 RF R2=0.90；99%样品预测误差<4个HGI单位，60%样品预测误差<2个HGI单位；
    MSE=3.54。    		 Matin et al.，2016
    HGI 发热量、工业分析指标（水分、
    灰分、挥发分、固定碳）、全硫
    和黄铁矿含量。    		 ANN、SVR、LSTM ANN模型R2>0.9，整体表现为ANN
    最高、SVR次之、LSTM最低。    		 Lawal et al.，2025
    下载: 导出CSV
    • 参考文献(109)
  • [1] AKKAYA A V, 2013. Predicting coal heating values using proximate analysis via a neural network approach[J]. Energy Sources, Part A: Recovery, Utilization, and Environmental Effects, 35(3): 253-260. doi: 10.1080/15567036.2010.509090
    [2] ALPANA, CHAND S, MOHAPATRA S, et al., 2021. An intelligent system to identify coal maceral groups using Markov-fuzzy clustering approach[J]. Journal of Intelligent & Fuzzy Systems, 41: 5701-5707. doi: 10.3233/jifs-189889
    [3] BARREDO ARRIETA A B, DÍAZ-RODRÍGUEZ N, DEL SER J, et al., 2020. Explainable Artificial Intelligence (XAI): concepts, taxonomies, opportunities and challenges toward responsible AI[J]. Information Fusion, 58: 82-115. doi: 10.1016/j.inffus.2019.12.012
    [4] CHATTERJEE S, MASTALERZ M, DROBNIAK A, et al., 2022. Machine learning and data augmentation approach for identification of rare earth element potential in Indiana Coals, USA[J]. International Journal of Coal Geology, 259: 104054. doi: 10.1016/j.coal.2022.104054
    [5] CHELGANI S C, DEHGHAN F, HOWER J C, 2011. Estimation of some coal parameters depending on petrographic and inorganic analyses by using genetic algorithm and adaptive neuro-fuzzy inference systems[J]. Energy Exploration & Exploitation, 29(4): 479-494. doi: 10.1260/0144-5987.29.4.479
    [6] CHELGANI S C, HOWER J C, JORJANI E, et al., 2008. Prediction of coal grindability based on petrography, proximate and ultimate analysis using multiple regression and artificial neural network models[J]. Fuel Processing Technology, 89(1): 13-20. doi: 10.1016/j.fuproc.2007.06.004
    [7] CRELLING J C, 1983. Current uses of fluorescence microscopy in coal petrology[J]. Journal of Microscopy, 132(3): 251-266. doi: 10.1111/j.1365-2818.1983.tb04591.x
    [8] CRELLING J C, BENSLEY D F, 1984. Characterization of coal macerals by fluorescence microscopy[M]//WINANS R E, CRELLING J C, eds. Chemistry and characterization of coal macerals. Washington: American Chemical Society: 33-45.
    [9] DAI S F, BECHTEL A, EBLE C F, et al., 2020. Recognition of peat depositional environments in coal: a review[J]. International Journal of Coal Geology, 219: 103383. doi: 10.1016/j.coal.2019.103383
    [10] DAI S F, FINKELMAN R B, FRENCH D, et al., 2021. Modes of occurrence of elements in coal: a critical evaluation[J]. Earth-Science Reviews, 222: 103815. doi: 10.1016/j.earscirev.2021.103815
    [11] DAI S F, 2025. Critical metals in coal and coal-bearing sequences: a comparison between China and the United States[J]. Journal of China Coal Society, 50(1): 506-515. (in Chinese with English abstract)
    [12] DIESSEL C F K, 1992. Coal facies and depositional environment[M]//DIESSEL C F K. Coal-bearing depositional systems. Berlin: Springer: 161-264.
    [13] EMINAGAOGLU M, OSKAY R G, KARAYIGIT A I, 2022. Evaluation of elemental affinities in coal using agglomerative hierarchical clustering algorithm: a case study in a thick and mineable coal seam (kM2) from Soma Basin (W. Turkey)[J]. International Journal of Coal Geology, 259: 104045. doi: 10.1016/j.coal.2022.104045
    [14] FAN J W, DU M L, LIU L, et al., 2023. Macerals particle characteristics analysis of tar-rich coal in northern Shaanxi based on image segmentation models via the U-Net variants and image feature extraction[J]. Fuel, 341: 127757. doi: 10.1016/j.fuel.2023.127757
    [15] FINKELMAN R B, 1994. Modes of occurrence of potentially hazardous elements in coal: levels of confidence[J]. Fuel Processing Technology, 39(1-3): 21-34. doi: 10.1016/0378-3820(94)90169-4
    [16] FINKELMAN R B, DAI S F, FRENCH D, 2019. The importance of minerals in coal as the hosts of chemical elements: a review[J]. International Journal of Coal Geology, 212: 103251. doi: 10.1016/j.coal.2019.103251
    [17] GARCÍA-NIETO P J, GARCÍA-GONZALO E, PAREDES-SÁNCHEZ J P, 2024. Estimation of the coal higher heating value for energy systems relied on ultimate analysis with machine learning techniques[J]. Fuel, 357: 130037. doi: 10.1016/j.fuel.2023.130037
    [18] GLAGOLEW A, 1934. Quantitative analysis with the microscope by the point method[J]. Engineering and Mining Journal, 135: 339-340.
    [19] GUO Y S, 2023. Selection of machine learning algorithms in coalbed methane content predictions[J]. Applied Geophysics, 20(4): 518-533. doi: 10.1007/s11770-022-0997-4
    [20] GUO Z X, ZHAO J Z, YOU Z J, et al., 2021. Prediction of coalbed methane production based on deep learning[J]. Energy, 230: 120847. doi: 10.1016/j.energy.2021.120847
    [21] HAN D X, YANG Q, 1980. Coalfield geology of China: volume II[M]. Beijing: China Coal Industry Publishing House. (in Chinese)
    [22] HAN D X, 1996. Coal petrolgy of China[M]. Xuzhou: China University of Mining and Technology Press. (in Chinese)
    [23] HATHERLY P, 2013. Overview on the application of geophysics in coal mining[J]. International Journal of Coal Geology, 114: 74-84. doi: 10.1016/j.coal.2013.02.006
    [24] HOWER J C, BAGHERIEH A H, DINDARLOO S R, et al., 2021. Soft modelling of the Hardgrove grindability index of bituminous coals: an overview[J]. International Journal of Coal Geology, 247: 103846. doi: 10.1016/j.coal.2021.103846
    [25] HOWER J C, FINKELMAN R B, EBLE C F, et al., 2022. Understanding coal quality and the critical importance of comprehensive coal analyses[J]. International Journal of Coal Geology, 263: 104120. doi: 10.1016/j.coal.2022.104120
    [26] HUTTON A C, COOK A C, 1980. Influence of alginite on the reflectance of vitrinite from Joadja, NSW, and some other coals and oil shales containing alginite[J]. Fuel, 59(10): 711-714. doi: 10.1016/0016-2361(80)90025-3
    [27] IWASZENKO S, RÓG L, 2021. Application of deep learning in petrographic coal images segmentation[J]. Minerals, 11(11): 1265. doi: 10.3390/min11111265
    [28] JORJANI E, HOWER J C, CHEHREH CHELGANI S, et al., 2008. Studies of relationship between petrography and elemental analysis with grindability for Kentucky coals[J]. Fuel, 87(6): 707-713. doi: 10.1016/j.fuel.2007.05.044
    [29] KARACAN C Ö, RUIZ F A, COTÈ M, et al., 2011. Coal mine methane: a review of capture and utilization practices with benefits to mining safety and to greenhouse gas reduction[J]. International Journal of Coal Geology, 86(2-3): 121-156. doi: 10.1016/j.coal.2011.02.009
    [30] LAWAL A I, BADA S O, ONIFADE M, 2025. Prediction of HGI of South African coalfields: a comparative application of ANN, SVR and LSTM models[J]. International Journal of Coal Preparation and Utilization, 45(2): 325-341. doi: 10.1080/19392699.2024.2339319
    [31] LEI M, RAO Z Y, WANG H D, et al., 2021. Maceral groups analysis of coal based on semantic segmentation of photomicrographs via the improved U-net[J]. Fuel, 294: 120475. doi: 10.1016/j.fuel.2021.120475
    [32] LESTER E, WATTS D, CLOKE M, 2002. A novel automated image analysis method for maceral analysis[J]. Fuel, 81(17): 2209-2217.
    [33] LI X X, LI X J, XIE H G, et al., 2024. Enhanced coalbed methane well production prediction framework utilizing the CNN-BL-MHA approach[J]. Scientific Reports, 14(1): 14689. doi: 10.1038/s41598-024-65606-z
    [34] LIN R, DAVIS A, BENSLEY D F, et al., 1986. Vitrinite secondary fluorescence: its chemistry and relation to the development of a mobile phase and thermoplasticity in coal[J]. International Journal of Coal Geology, 6(3): 215-228. doi: 10.1016/0166-5162(86)90002-9
    [35] LIU C, GONG B, WU H Q, et al., 2025a. Intelligent coalbed methane drainage optimization: a deep reinforcement learning-driven life-cycle strategy[J]. Energy and AI, 22: 100598. doi: 10.1016/j.egyai.2025.100598
    [36] LIU C, YANG Y, CHEN L, et al., 2025b. Rare earth resource in fly ashes from coal power plants of China: based on machine learning model and unit-based estimation[J]. International Journal of Coal Geology, 303: 104743. doi: 10.1016/j.coal.2025.104743
    [37] LIU M, WANG P Z, CHEN S M, et al., 2019. The classification of inertinite macerals in coal based on the multifractal spectrum method[J]. Applied Sciences, 9(24): 5509. doi: 10.3390/app9245509
    [38] LIU Y, FENG J Y, WANG C X, et al., 2026. Hydrocarbon resources resulting from plant terrestrialization: a review[J]. Earth-Science Reviews, 277: 105457. doi: 10.1016/j.earscirev.2026.105457
    [39] MASON D M, GANDHI K N, 1983. Formulas for calculating the calorific value of coal and coal chars: development, tests, and uses[J]. Fuel Processing Technology, 7(1): 11-22. doi: 10.1016/0378-3820(83)90022-X
    [40] MATIN S S, CHELGANI S C, 2016. Estimation of coal gross calorific value based on various analyses by random forest method[J]. Fuel, 177: 274-278. doi: 10.1016/j.fuel.2016.03.031
    [41] MATIN S S, HOWER J C, FARAHZADI L, et al., 2016. Explaining relationships among various coal analyses with coal grindability index by Random Forest[J]. International Journal of Mineral Processing, 155: 140-146. doi: 10.1016/j.minpro.2016.08.015
    [42] MENG L C, ZHU W, XU N, et al., 2026. Explainable AI for coal Hardgrove grindability index prediction: a genetic programming and linear regression approach[J]. Fuel, 404: 136072. doi: 10.1016/j.fuel.2025.136072
    [43] MLYNARCZUK M, SKIBA M, 2017. The application of artificial intelligence for the identification of the maceral groups and mineral components of coal[J]. Computers & Geosciences, 103: 133-141. doi: 10.1016/j.cageo.2017.03.011
    [44] MONDAL D, HAN S J, SANG S X, et al., 2024. Application of artificial neural network to evaluate coalbed methane exploration potential: a case study from Permian Longtan Formation, Shuicheng, Guizhou[J]. Natural Resources Research, 33(2): 609-636. doi: 10.1007/s11053-023-10301-5
    [45] MOORE T A, FERM J C, 1992. Composition and grain size of an Eocene coal bed in southeastern Kalimantan, Indonesia[J]. International Journal of Coal Geology, 21(1-2): 1-30. doi: 10.1016/0166-5162(92)90033-s
    [46] MOORE T A, 2012. Coalbed methane: a review[J]. International Journal of Coal Geology, 101: 36-81. doi: 10.1016/j.coal.2012.05.011
    [47] MOTT R A, SPOONER C E, 1940. The calorific value of carbon in coal: the Dulong relationship[J]. Fuel, 19: 226-231, 242-251.
    [48] O'BRIEN G, JENKINS B, ESTERLE J, et al., 2003. Coal characterisation by automated coal petrography[J]. Fuel, 82(9): 1067-1073. doi: 10.1016/s0016-2361(02)00428-3
    [49] O'BRIEN G, JENKINS B, OFORI P, et al., 2007. Semi-automated petrographic assessment of coal by coal grain analysis[J]. Minerals Engineering, 20(5): 428-434. doi: 10.1016/j.mineng.2006.11.006
    [50] O'KEEFE J M K, BECHTEL A, CHRISTANIS K, et al., 2013. On the fundamental difference between coal rank and coal type[J]. International Journal of Coal Geology, 118: 58-87. doi: 10.1016/j.coal.2013.08.007
    [51] ONIFADE M, LAWAL A I, ABDULSALAM J, et al., 2021. Development of multiple soft computing models for estimating organic and inorganic constituents in coal[J]. International Journal of Mining Science and Technology, 31(3): 483-494. doi: 10.1016/j.ijmst.2021.02.003
    [52] PARIKH J, CHANNIWALA S A, GHOSAL G K, 2005. A correlation for calculating HHV from proximate analysis of solid fuels[J]. Fuel, 84(5): 487-494. doi: 10.1016/j.fuel.2004.10.010
    [53] PES B, 2020. Ensemble feature selection for high-dimensional data: a stability analysis across multiple domains[J]. Neural Computing and Applications, 32(10): 5951-5973. doi: 10.1007/s00521-019-04082-3
    [54] QIN Y, YUAN L, CHENG Y P, et al., 2013. Scenario predication for the mid-term and long-term coalbed methane production scale of surface drilling wells in China[J]. Acta Petrolei Sinica, 34(3): 489-495. (in Chinese with English abstract)
    [55] REN D Y, ZHAO F H, DAI S F, et al. , 2006. Geochemistry of trace elements in coal[M]. Beijing: Science Press. (in Chinese)
    [56] RICHARDS A P, HAYCOCK D, FRANDSEN J, et al., 2021. A review of coal heating value correlations with application to coal char, tar, and other fuels[J]. Fuel, 283: 118942. doi: 10.1016/j.fuel.2020.118942
    [57] SANTOS R B M, AUGUSTO K S, IGLESIAS J C Á, et al., 2022. A deep learning system for collotelinite segmentation and coal reflectance determination[J]. International Journal of Coal Geology, 263: 104111. doi: 10.1016/j.coal.2022.104111
    [58] SEREDIN V V, DAI S F, 2012. Coal deposits as potential alternative sources for lanthanides and yttrium[J]. International Journal of Coal Geology, 94: 67-93. doi: 10.1016/j.coal.2011.11.001
    [59] SHARMA TIMILSINA M S, SEN S, UPRETY B, et al., 2024. Prediction of HHV of fuel by machine learning algorithm: interpretability analysis using Shapley additive explanations (SHAP)[J]. Fuel, 357: 129573. doi: 10.1016/j.fuel.2023.129573
    [60] SHIRAZI A R, BÖRTIN O, EKLUND L, et al., 1995. The impact of mineral matter in coal on its combustion, and a new approach to the determination of the calorific value of coal[J]. Fuel, 74(2): 247-251. doi: 10.1016/0016-2361(95)92661-O
    [61] SONG H Q, DU S Y, YANG J S, et al., 2024. Forecasting and influencing factor analysis of coalbed methane productivity utilizing intelligent algorithms[J]. Chinese Journal of Engineering, 46(4): 614-626. (in Chinese with English abstract)
    [62] STACH E, 1927. Der Kohlenreliefschliff, ein neues Hilfsmittel für die angewandte Kohlenpetrographie[J]. Mitteilungen der Abteilung für Gesteins-, Erz-, Kohle- und Salzuntersuchungen, 2: 75-94.
    [63] STACH E, MACKOWSKY M T, TEICHMÜLLER M, et al. , 1975. Stach's textbook of coal petrology[M]. 2nd ed. Berlin, Stuttgart: Gebrüder Borntraeger.
    [64] STEUER W, 1926. General formulas for calculating the heating value of fossil fuels from their elementary analyses[J]. Brennstoff-Chemie, 7: 344-347.
    [65] TAGGART R K, HOWER J C, DWYER G S, et al. , 2016. Trends in the rare earth element content of U. S. -based coal combustion fly ashes[J]. Environmental Science & Technology, 50(11): 5919-5926.
    [66] TAN P, ZHANG C, XIA J, et al., 2015. Estimation of higher heating value of coal based on proximate analysis using support vector regression[J]. Fuel Processing Technology, 138: 298-304. doi: 10.1016/j.fuproc.2015.06.013
    [67] TAYLOR G H, TEICHMULLER M, DAVIS A, et al. , 1998. Organic petrology: a new handbook incorporating some revised parts of Stach's Textbook of coal petrology; with 70 tables in the text[M]. Berlin: Borntraeger.
    [68] TEICHMÜLLER M, 1974. Über neue Macerale der Liptinit-Gruppe und die Entstehung von Micrinit[J]. Fortschritte in der Geologie von Rheinland und Westfalen, 24: 37-64.
    [69] THOMAS L, 2002. Coal geology[M]. Chichester: Wiley.
    [70] TING F T C, 1978. Petrographic techniques in coal analysis[M]//KARR C JR. Analytical methods for coal and coal products. New York: Academic Press: 3-26.
    [71] TIWARY A K, GHOSH S, SINGH R, et al., 2020. Automated coal petrography using random forest[J]. International Journal of Coal Geology, 232: 103629. doi: 10.1016/j.coal.2020.103629
    [72] UNSWORTH J F, GOUGH H, 1989. Characterization of coals by automated optical image analysis 1. Vitrinite reflectance[J]. Journal of Microscopy, 156(3): 313-326. doi: 10.1111/j.1365-2818.1989.tb02933.x
    [73] VENKOBA RAO B, GOPALAKRISHNA S J, 2009. Hardgrove grindability index prediction using support vector regression[J]. International Journal of Mineral Processing, 91(1-2): 55-59. doi: 10.1016/j.minpro.2008.12.003
    [74] VUTHALURU H B, BROOKE R J, ZHANG D K, et al., 2003. Effects of moisture and coal blending on Hardgrove Grindability Index of Western Australian coal[J]. Fuel Processing Technology, 81(1): 67-76. doi: 10.1016/S0378-3820(03)00044-4
    [75] WANG H D, LEI M, CHEN Y L, et al., 2019a. Intelligent identification of maceral components of coal based on image segmentation and classification[J]. Applied Sciences, 9(15): 3245. doi: 10.3390/app9163245
    [76] WANG H D, LEI M, LI M, et al., 2019b. Intelligent estimation of vitrinite reflectance of coal from photomicrographs based on machine learning[J]. Energies, 12(20): 3855. doi: 10.3390/en12203855
    [77] WANG H Y, WANG Q Q, HUANG L, et al., 2023. Intelligent decision-making system for integrated geological and engineering of deep coalbed methane development[J]. Energy & Fuels, 37(18): 13976-13984. doi: 10.1021/acs.energyfuels.3c02642
    [78] WANG T, LIN Q H, 2021. Hybrid predictive models: when an interpretable model collaborates with a black-box model[J]. The Journal of Machine Learning Research, 22(1): 137.
    [79] WANG Y, BAI X F, WU L L, et al., 2022. Identification of maceral groups in Chinese bituminous coals based on semantic segmentation models[J]. Fuel, 308: 121844. doi: 10.1016/j.fuel.2021.121844
    [80] WARD C R, 2002. Analysis and significance of mineral matter in coal seams[J]. International Journal of Coal Geology, 50(1-4): 135-168. doi: 10.1016/S0166-5162(02)00117-9
    [81] WARD C R, 2016. Analysis, origin and significance of mineral matter in coal: an updated review[J]. International Journal of Coal Geology, 165: 1-27. doi: 10.1016/j.coal.2016.07.014
    [82] WEI X Y, HUANG W S, LIU L L, et al., 2024. Low-rank coalbed methane production capacity prediction method based on time-series deep learning[J]. Energy, 311: 133247. doi: 10.1016/j.energy.2024.133247
    [83] WEN H, YAN L, JIN Y F, et al., 2023a. Coalbed methane concentration prediction and early-warning in fully mechanized mining face based on deep learning[J]. Energy, 264: 126208. doi: 10.1016/j.energy.2022.126208
    [84] WEN Z P, LIU H T, ZHOU M Q, et al. , 2023b. Explainable machine learning rapid approach to evaluate coal ash content based on X-ray fluorescence[J]. Fuel, 332(Pt 1): 125991.
    [85] WOOD D A, 2019. Transparent open-box learning network provides auditable predictions for coal gross calorific value[J]. Modeling Earth Systems and Environment, 5(2): 395-419. doi: 10.1007/s40808-018-0543-9
    [86] XU N, XU C P, FINKELMAN R B, et al., 2022. Coal elemental (compositional) data analysis with hierarchical clustering algorithms[J]. International Journal of Coal Geology, 249: 103892. doi: 10.1016/j.coal.2021.103892
    [87] XU N, WANG Z W, DAI Y C, et al., 2023a. Prediction of higher heating value of coal based on gradient boosting regression tree model[J]. International Journal of Coal Geology, 274: 104293. doi: 10.1016/j.coal.2023.104293
    [88] XU N, ZHU W, HUANG B, et al., 2023b. Modes of occurrence of elements in high-germanium coals using correlation analysis algorithm[J]. Applied Geochemistry, 152: 105647. doi: 10.1016/j.apgeochem.2023.105647
    [89] XU N, ZHU W, WANG R, et al., 2023c. Application of self-organizing maps to coal elemental data[J]. International Journal of Coal Geology, 277: 104358. doi: 10.1016/j.coal.2023.104358
    [90] XU N, WANG Q F, LI P F, et al., 2025a. Intelligent identification of coal macerals using improved semi-supervised semantic segmentation methods[J]. International Journal of Coal Geology, 300: 104712. doi: 10.1016/j.coal.2025.104712
    [91] XU N, LI F, ZHU W, et al., 2025b. Predicting the concentrations of rare earth elements and yttrium in coal using self-organizing map[J]. Natural Resources Research, 34(3): 1467-1479. doi: 10.1007/s11053-025-10477-y
    [92] XU N, JIAO F Y, HOWER J C, et al. , 2026a. An improved U-net model for the identification of coal macerals[J]. International Journal of Coal Preparation and Utilization, doi: 10.1080/19392699.2026.2613015.
    [93] XU N, LI P F, KONG J P, et al. , 2026b. Predicting the prospect of rare earth elements and yttrium recovery from coal using machine learning[J]. International Journal of Coal Preparation and Utilization, doi: 10.1080/19392699.2026.2613010.
    [94] YANG Q, HAN D X, 1979. Coalfield geology of China: volume I[M]. Beijing: China Coal Industry Publishing House. (in Chinese)
    [95] YESENCHAK R, SHARMA S, MAXWELL A E, 2022. Modes of occurrence, elemental relationships, and economic viability of rare earth elements in West Virginia coals: a statistical approach[J]. Minerals, 12(8): 1060. doi: 10.3390/min12081060
    [96] ZHANG H, CAI X L, NI P, et al., 2025a. Prediction of coalbed methane content based on composite logging parameters and PCA-BP neural network[J]. Journal of Applied Geophysics, 236: 105681. doi: 10.1016/j.jappgeo.2025.105681
    [97] ZHANG H Y, LI K W, SHI S H, et al., 2025b. Prediction of coalbed methane production using a modified machine learning methodology[J]. Energies, 18(6): 1341. doi: 10.3390/en18061341
    [98] ZHENG Y, 2015. Methodologies for cross-domain data fusion: an overview[J]. IEEE Transactions on Big Data, 1(1): 16-34. doi: 10.1109/TBDATA.2015.2465959
    [99] ZHU J, ZHAO Y H, HU Q J, et al., 2022. Coalbed methane production model based on random forests optimized by a genetic algorithm[J]. ACS Omega, 7(15): 13083-13094. doi: 10.1021/acsomega.2c00519
    [100] ZHU W, XU N, HOWER J C, 2025a. Unveiling the predictive power of machine learning in coal gross calorific value estimation: an interpretability perspective[J]. Energy, 318: 134781. doi: 10.1016/j.energy.2025.134781
    [101] ZHU W, SHEN L S, XU N, et al., 2025b. Rare earth elements and yttrium in Chinese coals: distribution and economic significance[J]. Renewable and Sustainable Energy Reviews, 212: 115423. doi: 10.1016/j.rser.2025.115423
    [102] ZHU W, LIU W, XU N, et al., 2026. Modes of occurrence of critical elements in coals from the Guanbanwusu mine, Inner Mongolia, China: a novel stratigraphy-constrained sliding-window correlation approach[J]. Applied Geochemistry, 196: 106638. doi: 10.1016/j.apgeochem.2025.106638
    [103] 代世峰, 2025. 煤系关键金属矿产研究: 中美对比[J]. 煤炭学报, 50(1): 506-515. doi: 10.13225/j.cnki.jccs.YG24.1625
    [104] 韩德馨, 杨起, 1980. 中国煤田地质学: 下册[M]. 北京: 煤炭工业出版社.
    [105] 韩德馨, 1996. 中国煤岩学[M]. 徐州: 中国矿业大学出版社.
    [106] 秦勇, 袁亮, 程远平, 等, 2013. 中国煤层气地面井中长期生产规模的情景预测[J]. 石油学报, 34(3): 489-495. doi: 10.7623/syxb201303009
    [107] 任德贻, 赵峰华, 代世峰, 等, 2006. 煤的微量元素地球化学[M]. 北京: 科学出版社.
    [108] 宋洪庆, 都书一, 杨焦生, 等, 2024. 基于机器学习的煤层气产能标定智能算法及影响因素分析[J]. 工程科学学报, 46(4): 614-626. doi: 10.13374/j.issn2095-9389.2023.08.11.002
    [109] 杨起, 韩德馨, 1979. 中国煤田地质学: 上册[M]. 北京: 煤炭工业出版社.
    • 相关文章
    • 被引
  • 资源附件(0)
  • 加载中
图(1) / 表(1)
计量
  • 文章访问数:  135
  • HTML全文浏览量:  11
  • PDF下载量:  45
  • 被引次数: 0
出版历程
  • 收稿日期:  2026-05-21
  • 修回日期:  2026-09-02
  • 录用日期:  2026-09-04
  • 预出版日期:  2026-09-04
  • 刊出日期:  2026-10-28

目录

    /

    返回文章
    返回

    网站版权《地质力学学报》编辑部  京ICP备18031784号  网站总访问量：

    本系统由 北京仁和汇智信息技术有限公司 开发    百度统计