•  
  •  
 

Coal Geology & Exploration

Abstract

Background Using directional boreholes, the borehole transient electromagnetic (TEM) method enables near-field excitation and the simultaneous reception of three components within a borehole. This method can effectively avoid interference from ferromagnetic materials in roadways, thereby significantly enhancing the detection accuracy and range. Therefore, this method is widely applied to the detection of underground concealed water hazards in coal mines. However, there is a conflict between the accuracy and efficiency of current inversion methods for borehole TEM data, and existing technologies are insufficient to simultaneously meet the demands for high efficiency and high precision in the detection of concealed water hazards. Objective and Methods To address these issues, this study developed an adaptive sample construction method based on Bayesian optimization and established an artificial intelligence-based inversion framework using a long short-term memory (LSTM). Specifically, the theoretical responses of measured data were reconstructed using the method of trend surface analysis first, aiming to reduce the impacts of factors such as environment on the data and lay the foundation for the analysis of the consistency between the distributions of measured and simulated data. Then, the Bayesian optimization strategy was introduced, and the objective function for data distribution consistency was constructed using maximum mean discrepancy (MMD) and area under the curve (AUC). This objective function allows for the quantitative evaluation of the similarity between the distributions of simulated sample data and measured data, thereby contributing to the determination of the optimal resistivity range through continuous optimization. Furthermore, an algorithm for the one-dimensional (1D) forward modeling of TEM data was developed based on graphics processing unit (GPU) parallel computing. This algorithm was employed to construct a high-quality training sample database based on the optimal resistivity range. The basic framework of the inversion model incorporated the Seq2Seq architecture established using a LSTM while also integrating the attention mechanism to fully capture the temporal dynamic characteristics of electromagnetic responses. Based on 1D inversion, the quadrants of the anomalous response characteristics of the horizontal components of borehole TEM data were determined using the K-means clustering algorithm. Based on both the derived relationship between the depth coefficient and resistivity and the acquired information on toolface angles, the 3D resistivity imaging of the inversion results of borehole TEM data was achieved. Results and Conclusions Numerical simulation experiments reveal that the ATT-LSTM inversion yielded average relative root mean square errors (RRMSEs) of 5% or less, exhibiting higher accuracy compared to the Occam's inversion and the recurrent neural network (RNN)-based inversion. Noise resistance experiments indicate that the ATT-LSTM inversion method maintained high stability and robustness under noise interference at certain levels. Physical simulation experiments were conducted using a water tank, with a copper plate utilized as a substitute for a low-resistivity anomaly. The experiment results indicate that the constructed high-quality sample database and the ATT-LSTM inversion framework jointly allow for the accurate inversion of the stratigraphic models and the characterization of the low-resistivity anomaly. The engineering practice in a coal mine in Xinjiang demonstrates that the ATT-LSTM inversion method can effectively identify underground low-resistivity anomaly zones, with the 3D imaging result highly consistent with known geological data. Overall, the results of this study will provide reliable technical support for the detection of concealed water hazards in coal mining areas, thereby effectively ensuring efficient and rapid roadway excavation.

Keywords

borehole transient electromagnetic (TEM) method, deep learning, Bayesian optimization, long short-term memory (LSTM)

DOI

10.12363/issn.1001-1986.26.05.0301

Reference

[1] 康红普,王国法,王双明,等. 煤炭行业高质量发展研究[J]. 中国工程科学,2021,23(5):130−138 KANG Hongpu,WANG Guofa,WANG Shuangming,et al. High–quality development of China’s coal industry[J]. Strategic Study of CAE,2021,23(5):130−138

[2] 王国法. 煤矿智能化最新技术进展与问题探讨[J]. 煤炭科学技术,2022,50(1):1−27 WANG Guofa. New technological progress of coal mine intelligence and its problems[J]. Coal Science and Technology,2022,50(1):1−27

[3] 董书宁,刘再斌,程建远,等. 煤炭智能开采地质保障技术及展望[J]. 煤田地质与勘探,2021,49(1):21−31 DONG Shuning,LIU Zaibin,CHENG Jianyuan,et al. Technologies and prospect of geological guarantee for intelligent coal mining[J]. Coal Geology & Exploration,2021,49(1):21−31

[4] 王国法,张建中,薛国华,等. 煤矿回采工作面智能地质保障技术进展与思考[J]. 煤田地质与勘探,2023,51(2):12−26 WANG Guofa,ZHANG Jianzhong,XUE Guohua,et al. Progress and reflection of intelligent geological guarantee technology in coal mining face[J]. Coal Geology & Exploration,2023,51(2):12−26

[5] 刘再斌,范涛,李萍,等. 煤矿远距离综合物探及透明地质保障系统研发与应用[J]. 智能矿山,2025,6(2):7−12

[6] 刘峰,郭林峰,赵路正. 双碳背景下煤炭安全区间与绿色低碳技术路径[J]. 煤炭学报,2022,47(1):1−15 LIU Feng,GUO Linfeng,ZHAO Luzheng. Research on coal safety range and green low–carbon technology path under the dual–carbon background[J]. Journal of China Coal Society,2022,47(1):1−15

[7] 袁亮,张通,王玥晗,等. 深部煤炭资源安全高效开采科学问题及关键技术[J]. 煤炭学报,2025,50(1):1−12 YUAN Liang,ZHANG Tong,WANG Yuehan,et al. Scientific problems and key technologies for safe and efficient mining of deep coal resources[J]. Journal of China Coal Society,2025,50(1):1−12

[8] 张平松,欧元超,李圣林. 我国矿井物探技术及装备的发展现状与思考[J]. 煤炭科学技术,2021,49(7):1−15 ZHANG Pingsong,OU Yuanchao,LI Shenglin. Development quo–status and thinking of mine geophysical prospecting technology and equipment in China[J]. Coal Science and Technology,2021,49(7):1−15

[9] 郭文达,朱希安. 烟圈反演和视纵向电导解释方法对比[J]. 煤田地质与勘探,2014,42(6):93−96 GUO Wenda,ZHU Xi’an. Comparison between the smoke loop inversion and apparent longitudinal conductivity interpretation method[J]. Coal Geology & Exploration,2014,42(6):93−96

[10] 李锋平,杨海燕,邓居智,等. 地面瞬变电磁法一维烟圈反演技术研究[J]. 地球物理学进展,2016,31(2):688−694 LI Fengping,YANG Haiyan,DENG Juzhi,et al. One–dimensional smoke ring inversion technology of ground transient electromagnetic method[J]. Progress in Geophysics,2016,31(2):688−694

[11] 杨海燕,李锋平,岳建华,等. 基于“烟圈”理论的圆锥型场源瞬变电磁优化反演[J]. 中国矿业大学学报,2016,45(6):1230−1237 YANG Haiyan,LI Fengping,YUE Jianhua,et al. Optimal transient electromagnetic inversion of conical field source based on smoke ring theory[J]. Journal of China University of Mining & Technology,2016,45(6):1230−1237

[12] 孙怀凤,张诺亚,柳尚斌,等. 基于L1范数的瞬变电磁非线性反演[J]. 地球物理学报,2019,62(12):4860−4873 SUN Huaifeng,ZHANG Nuoya,LIU Shangbin,et al. L1–norm based nonlinear inversion of transient electromagnetic data[J]. Chinese Journal of Geophysics,2019,62(12):4860−4873

[13] XUE Guoqiang,LI Hai,HE Yiming,et al. Development of the inversion method for transient electromagnetic data[J]. IEEE Access,2020,8:146172−146181.

[14] ZHOU Zhiyong,HE Ke,KANG Shihai,et al. Sparse regularization inversion method for transient electromagnetic data and high–resolution prospection of subsurface targets[J]. Scientific Reports,2025,15:31208.

[15] 程久龙，焦俊俊，陈志，等. 钻孔瞬变电磁法扫描探测RCQPSO–LMO组合算法2. 5D反演[J]. 地球物理学报，2024，67(2)：781–792. CHENG Jiulong，JIAO Junjun，CHEN Zhi，et al. 2. 5D inversion of borehole transient electromagnetic method with scanning detection based on RCQPSO–LMO combined algorithm[J]. Chinese Journal of Geophysics，2024，67(2)：781–792.

[16] 王书明,底青云,夏彤,等. 瞬变电磁数据L–PSO反演方法[J]. 地球物理学报,2022,65(4):1482−1493 WANG Shuming,DI Qingyun,XIA Tong,et al. Transient electromagnetic method inversion based on Lévy flight–particle swarm optimization[J]. Chinese Journal of Geophysics,2022,65(4):1482−1493

[17] 李明星. 矿井瞬变电磁PSO–DLS组合算法反演研究[J]. 煤炭科学技术,2019,47(9):268−272 LI Mingxing. Study on mine transient electromagnetic method inversion based on PSO–DLS combination algorithm[J]. Coal Science and Technology,2019,47(9):268−272

[18] LI Ruiyou,ZHANG Huaiqing,YU Nian,et al. A fast approximation for 1–D inversion of transient electromagnetic data by using a back propagation neural network and improved particle swarm optimization[J]. Nonlinear Processes in Geophysics,2019,26(4):445−456.

[19] LI Ruiyou,ZHANG Huaiqing,ZHUANG Qiong,et al. BP neural network and improved differential evolution for transient electromagnetic inversion[J]. Computers & Geosciences,2020,137:104434.

[20] LIU Wei,XI Zhenzhu,WANG He,et al. Two–dimensional deep learning inversion of magnetotelluric sounding data[J]. Journal of Geophysics and Engineering,2021,18(5):627−641.

[21] COLOMBO D,TURKOGLU E,LI Weichang,et al. Physics–driven deep–learning inversion with application to transient electromagnetics[J]. Geophysics,2021,86(3):E209−E224.

[22] 范涛,薛国强,李萍,等. 瞬变电磁长短时记忆网络深度学习实时反演方法[J]. 地球物理学报,2022,65(9):3650−3663 FAN Tao,XUE Guoqiang,LI Ping,et al. TEM real–time inversion based on long–short term memory network[J]. Chinese Journal of Geophysics,2022,65(9):3650−3663

[23] LIU Wei,WANG He,XI Zhenzhu,et al. Physics–driven deep learning inversion with application to magnetotelluric[J]. Remote Sensing,2022,14(13):3218.

[24] LI Ruiyou,ZHANG Yong,JU Jiayi,et al. Physics–embedded deep learning inversion for transient electromagnetic method survey data[J]. Computers & Geosciences,2025,204:106000.

[25] PUZYREV V. Deep learning electromagnetic inversion with convolutional neural networks[J]. Geophysical Journal International,2019,218(2):817−832.

[26] WU Sihong,HUANG Qinghua,ZHAO Li. Convolutional neural network inversion of airborne transient electromagnetic data[J]. Geophysical Prospecting,2021,69(8/9):1761−1772.

[27] LI Ziteng,LI Hai,LI Keying. A novel self–supervised deep learning inversion method incorporating a fast forward network for transient electromagnetic data[J]. Journal of Geophysical Research:Machine Learning and Computation,2025,2(4):e2025JH000811.

[28] MCMILLAN M，PETERS B，GREIF O，et al. Inverting airborne electromagnetic data with machine learning[C]//NSG 2024 5th Conference on Geophysics for Mineral Exploration and Mining. Helsinki：European Association of Geoscientists & Engineers，2024：1–5.

[29] LIANG Hao,GAO Ruoyun,YIN Changchun,et al. Physics–driven deep–learning for marine CSEM data inversion[J]. Journal of Applied Geophysics,2024,229:105474.

[30] PUZYREV V,SALLES T,SURMA G,et al. Geophysical model generation with generative adversarial networks[J]. Geoscience Letters,2022,9:32.

[31] SHIN Y. Domain adaptation from drilling to geophysical data for mineral exploration[J]. Geosciences,2024,14(7):183.

[32] 范涛,赵兆,吴海,等. 矿井瞬变电磁多匝回线电感影响消除及曲线偏移研究[J]. 煤炭学报,2014,39(5):932−940 FAN Tao,ZHAO Zhao,WU Hai,et al. Research on inductance effect removing and curve offset for mine TEM with multi small loops[J]. Journal of China Coal Society,2014,39(5):932−940

[33] 范涛,郝跃,李萍,等. 煤矿井下孔中瞬变电磁矢量合成超前探测方法[J]. 煤田地质与勘探,2025,53(11):1−11 FAN Tao,HAO Yue,LI Ping,et al. A method for advance detection of underground concealed water hazards in coal mines based on borehole transient electromagnetic method and vector synthesis[J]. Coal Geology & Exploration,2025,53(11):1−11

[34] DING Tianxuan,LI Zhimei,ZHANG Yaowu. Testing the equality of distributions using integrated maximum mean discrepancy[J]. Journal of Statistical Planning and Inference,2025,236:106246.

[35] GRETTON A,BORGWARDT K M,RASCH M J,et al. A kernel two–sample test[J]. Journal of Machine Learning Research,2012,13:723−773.

[36] FAWCETT T. An introduction to ROC analysis[J]. Pattern Recognition Letters,2006,27(8):861−874.

[37] BRADLEY A P. The use of the area under the ROC curve in the evaluation of machine learning algorithms[J]. Pattern Recognition,1997,30(7):1145−1159.

[38] 范涛,李萍,赵兆,等. 钻孔瞬变电磁方法探测越界开采采空区的应用[J]. 煤田地质与勘探,2022,50(1):20−24 FAN Tao,LI Ping,ZHAO Zhao,et al. Application of borehole transient electromagnetic method in detecting the cross–border mining goaf[J]. Coal Geology & Exploration,2022,50(1):20−24

Download Chinese Version

Share

COinS
 
 

To view the content in your browser, please download Adobe Reader or, alternately,
you may Download the file to your hard drive.

NOTE: The latest versions of Adobe Reader do not support viewing PDF files within Firefox on Mac OS and if you are using a modern (Intel) Mac, there is no official plugin for viewing PDF files within the browser window.