A time series forecasting model integrating spatial features for inter-borehole resistivity and its application

Authors

WANG Jianghong, Ordos Huaxing Energy Co., Ltd., Ordos 010300, ChinaFollow
LIU Shuo, CCTEG Xi’an Research Institute (Group) Co., Ltd., Xi’an 710077, ChinaFollow
WANG Gang, Ordos Huaxing Energy Co., Ltd., Ordos 010300, China
XUE Wuqiang, Ordos Huaxing Energy Co., Ltd., Ordos 010300, China
LI Bofan, CCTEG Xi’an Research Institute (Group) Co., Ltd., Xi’an 710077, China

Abstract

Background Mine resistivity prediction serves as a core technique for water hazards monitoring in coal mines. However, due to sparse monitoring points and insufficient spatial resolution, conventional prediction approaches fail to capture dynamic resistivity variations under complex geological conditions.Objective and Methods To address this challenge, this study developed a deep learning-based time series forecasting model integrating spatial features for inter-borehole resistivity. Using a prediction framework constructed based on long short-term memory (LSTM) and critical spatial monitoring points selected through Pearson correlation analysis, this model (also referred to as the LSTM model) enabled high-precision prediction of resistivity in unknown areas. Specifically, the electrical connectivity between monitoring points was quantified using spatial correlation heatmaps. The optimal number of neighboring points was determined at five to reduce data redundancy and enhance the generalization capability of the LSTM model. The model architecture captured temporal dependencies in resistivity data using the gating mechanisms of LSTM and incorporated spatial information from multiple monitoring points, reducing the sensitivity of conventional models to vanishing gradients associated with long sequences. Against the engineering background of mining face 61304 in the Tangjiahui coal mine, Ordos City, this study compared the prediction performance of the LSTM model and the recurrent neural network (RNN) model based on the monitoring data from directional boreholes in the coal seam floor.Results and Conclusions The results indicate that the LSTM model outperformed the RNN model in terms of mean absolute error (E_MA = 0.0582), root mean square error (E_MS = 0.005 2), and coefficient of determination (R² = 0.937 7). Under 10% noise interference, the R² value of the LSTM model decreased by merely 0.02, demonstrating strong robustness. The LSTM model was applied to the dynamic monitoring during the early, middle, and late grouting stages. A high-density spatiotemporal resistivity dataset was obtained by supplementing sparse measured data with predicted data. The inversion imaging results based on this dataset confirm that the LSTM model can restore the continuity of geological structures that is ignored in low-density monitoring while successfully identifying weak anomaly areas that cannot be reflected in the inversion results derived using low-density data. The LSTM model can effectively overcome the limitations of low spatial resolutions in traditional monitoring, offering a robust technical approach for the dynamic monitoring and accurate early warning of water hazards under complex geological conditions.

Keywords

mine resistivity prediction, spatiotemporal modeling, long short-term memory (LSTM), deep learning, water hazard monitoring

DOI

10.12363/issn.1001-1986.24.10.0665

Recommended Citation

WANG Jianghong, LIU Shuo, WANG Gang, et al. (2025) "A time series forecasting model integrating spatial features for inter-borehole resistivity and its application," Coal Geology & Exploration: Vol. 53: Iss. 8, Article 19.
DOI: 10.12363/issn.1001-1986.24.10.0665
Available at: https://cge.researchcommons.org/journal/vol53/iss8/19

Reference

[1] 岳建华，杨海燕，冉华赓. 矿井电法勘探研究现状与发展趋势[J]. 煤田地质与勘探，2023，51(1)：259−276.

YUE Jianhua，YANG Haiyan，RAN Huageng. Research status and development trend of mine electrical prospecting[J]. Coal Geology & Exploration，2023，51(1)：259−276.

[2] 张继锋，孙乃泉，刘最亮，等. 电磁法在煤矿水害隐患探测方面的综述[J]. 煤田地质与勘探，2023，51(2)：301−316.

ZHANG Jifeng，SUN Naiquan，LIU Zuiliang，et al. Electromagnetic methods in the detection of water hazards in coal mines：A review[J]. Coal Geology & Exploration，2023，51(2)：301−316.

[3] 岳建华，刘树才. 矿井直流电法勘探[M]. 徐州：中国矿业大学出版社，2000.

[4] 鲁晶津，吴小平. 巷道直流电阻率法超前探测三维数值模拟[J]. 煤田地质与勘探，2013，41(6)：83−86.

LU Jingjin，WU Xiaoping. 3D numerical modeling of tunnel DC resistivity for in–advance detection[J]. Coal Geology & Exploration，2013，41(6)：83−86.

[5] 鲁晶津，王冰纯，李德山，等. 矿井电阻率法监测系统在采煤工作面水害防治中的应用[J]. 煤田地质与勘探，2022，50(1)：36−44.

LU Jingjin，WANG Bingchun，LI Deshan，et al. Application of mine–used resistivity monitoring system in working face water disaster control[J]. Coal Geology & Exploration，2022，50(1)：36−44.

[6] 崔伟雄，袁博. 矿井电阻率法监测数据质量评价方法探讨[J]. 煤田地质与勘探，2023，51(4)：143−151.

CUI Weixiong，YUAN Bo. Quality assessment of resistivity monitoring data of coal mines[J]. Coal Geology & Exploration，2023，51(4)：143−151.

[7] 张磊，许博，刘斌，等. 煤矿防治水智能化技术研究现状及展望[J]. 陕西煤炭，2022，41(6)：224−226.

ZHANG Lei，XU Bo，LIU Bin，et al. Research status and prospect of intelligent water prevention and control technology in coal mine[J]. Shaanxi Coal，2022，41(6)：224−226.

[8] 刘树才，刘鑫明，姜志海，等. 煤层底板导水裂隙演化规律的电法探测研究[J]. 岩石力学与工程学报，2009，28(2)：348−356.

LIU Shucai，LIU Xinming，JIANG Zhihai，et al. Research on electrical prediction for evaluating water conducting fracture zones in coal seam floor[J]. Chinese Journal of Rock Mechanics and Engineering，2009，28(2)：348−356.

[9] 刘斌，李术才，李树忱，等. 电阻率层析成像法监测系统在矿井突水模型试验中的应用[J]. 岩石力学与工程学报，2010，29(2)：297−307.

LIU Bin，LI Shucai，LI Shuchen，et al. Application of electrical resistivity tomography monitoring system to mine water inrush model test[J]. Chinese Journal of Rock Mechanics and Engineering，2010，29(2)：297−307.

[10] 刘鑫明，刘树才，姜志海，等. 电阻率法监测煤层底板破碎带数值模拟[J]. 煤矿安全，2013，44(1)：39−42.

LIU Xinming，LIU Shucai，JIANG Zhihai，et al. Numerical simulation on coal seam floor fracture zone based on resistivity method monitoring[J]. Safety in Coal Mines，2013，44(1)：39−42.

[11] 鲁晶津. 煤矿井下含/导水构造三维电阻率反演成像技术[J]. 煤炭学报，2016，41(3)：687−695.

LU Jingjin. 3D electrical resistivity inversion and imaging technology for coal mine water–containing/water–conductive structures[J]. Journal of China Coal Society，2016，41(3)：687−695.

[12] 王智，王程，方思南. 基于非结构化有限元的三维井地电阻率法约束反演[J]. 物探与化探，2022，46(6)：1431−1443.

WANG Zhi，WANG Cheng，FANG Sinan. Constraint inversion of three–dimensional borehole–to–surface resistivity based on unstructured finite element[J]. Geophysical and Geochemical Exploration，2022，46(6)：1431−1443.

[13] 李艳波，苟通，赵永波. 三维并行电法探测矿山煤岩层含水率应用研究[J]. 能源与节能，2024(12)：46−48.

LI Yanbo，GOU Tong，ZHAO Yongbo. Application of three–dimensional parallel electrical method in detecting water content of coal rock layers in coal mine[J]. Energy and Energy Conservation，2024(12)：46−48.

[14] 高明亮，于生宝，郑建波，等. 基于IGA算法的电阻率神经网络反演成像研究[J]. 地球物理学报，2016，59(11)：4372−4382.

GAO Mingliang，YU Shengbao，ZHENG Jianbo，et al. Research of resistivity imaging using neural network based on immune genetic algorithm[J]. Chinese Journal of Geophysics，2016，59(11)：4372−4382.

[15] 李宇腾，程建远，鲁晶津，等. 基于人工神经网络的矿井直流电阻率法超前预测方法[J]. 煤田地质与勘探，2023，51(6)：185−193.

LI Yuteng，CHENG Jianyuan，LU Jingjin，et al. Direct current resistivity method for the advance prediction of water hazards in coal mines based on an artificial neural network[J]. Coal Geology & Exploration，2023，51(6)：185−193.

[16] 王越. 矿井水害电性信息长时监测系统设计[D]. 长春：吉林大学，2023.

WANG Yue. Design of long time monitoring system for mine water damage electrical information[D]. Changchun：Jilin University，2023.

[17] 张磊，于可伟. 深部煤层开采矿井水害成因与防治技术[J]. 陕西煤炭，2024，43(6)：153−156.

ZHANG Lei，YU Kewei. Mine water hazard genesis and its prevention and control technology for deep coal seam mining mines[J]. Shaanxi Coal，2024，43(6)：153−156.

[18] 张池，孙伟，张奋轩. 井下电法探测煤矿水患致灾因素的应用[J]. 陕西煤炭，2018，37(4)：105−108.

ZHANG Chi，SUN Wei，ZHANG Fenxuan. Application of underground electric prospecting in the prevention of water disaster[J]. Shaanxi Coal，2018，37(4)：105−108.

[19] 李金铭. 电法勘探方法发展概况[J]. 物探与化探，1996，20(4)：250−258.

LI Jinming. A generalized description of the development of electric exploration methods[J]. Geophysical and Geochemical Exploration，1996，20(4)：250−258.

[20] 何继善. 电法勘探的发展和展望[J]. 地球物理学报，1997，40(增刊1)：308−316.

HE Jishan. Development and prospect of electrical prospecting method[J]. Chinese Journal of Geophysics，1997，40(Sup.1)：308−316.

[21] 李博凡，刘磊，范涛，等. 煤矿井下定向钻孔中电阻率探测技术与应用[J]. 煤田地质与勘探，2022，50(1)：52−58.

LI Bofan，LIU Lei，FAN Tao，et al. Resistivity detection and its application in underground coal mine directional boreholes[J]. Coal Geology & Exploration，2022，50(1)：52−58.

[22] 陈星月. 基于深度学习的低阻储层流体识别[D]. 武汉：长江大学，2024.

CHEN Xingyue. Fluid identification of low resistivity reservoir based ondeep learning[D]. Wuhan：Yangtze University，2024.

[23] 吕建立. 基于RNN算法的煤矿井下瓦斯浓度预测研究[J]. 能源与环保，2023，45(9)：84−87.

LYU Jianli. Study on prediction of gas concentration in coal mine underground based on RNN algorithm[J]. China Energy and Environmental Protection，2023，45(9)：84−87.

[24] MADAN R，MANGIPUDI P S. Predicting computer network traffic：A time series forecasting approach using DWT，ARIMA and RNN[C]//2018 Eleventh International Conference on Contemporary Computing (IC3). Noida：IEEE，2018：1–5.

[25] TORRES J F，HADJOUT D，SEBAA A，et al. Deep learning for time series forecasting：A survey[J]. Big Data，2021，9(1)：3−21.

[26] HEWAMALAGE H，BERGMEIR C，BANDARA K. Recurrent neural networks for time series forecasting：Current status and future directions[J]. International Journal of Forecasting，2021，37(1)：388−427.

[27] 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.

[28] SIAMI–NAMINI S，TAVAKOLI N，NAMIN A S. A comparison of ARIMA and LSTM in forecasting time series[C]//2018 17th IEEE International Conference on Machine Learning and Applications (ICMLA). Orlando：IEEE，2018：1394–1401.

[29] 李佳，王维波，盛立，等. 应用双向长短时记忆神经网络的微地震信号降噪方法[J]. 石油地球物理勘探，2023，58(2)：285−294.

LI Jia，WANG Weibo，SHENG Li，et al. Denoising of microseismic signal based on bidirectional long short–term memory neural network[J]. Oil Geophysical Prospecting，2023，58(2)：285−294.

[30] 杨晖. 基于皮尔森相关算法的云存储层次化去冗优化[J]. 吉林大学学报(信息科学版)，2022，40(1)：71−76.

YANG Hui. Hierarchical redundancy elimination optimization of cloud storage based on Pearson correlation algorithm[J]. Journal of Jilin University (Information Science Edition)，2022，40(1)：71−76.

[31] 韩晓，王涛，韦晓广，等. 考虑阵列间时空相关性的超短期光伏出力预测[J]. 电力系统保护与控制，2024，52(14)：82−94.

HAN Xiao，WANG Tao，WEI Xiaoguang，et al. Ultrashort–term photovoltaic output forecasting considering spatiotemporal correlation between arrays[J]. Power System Protection and Control，2024，52(14)：82−94.

[32] 傅晨，王开军. 决定系数与相关系数辅助的LASSO回归[J]. 福建师范大学学报(自然科学版)，2024，40(2)：57−63.

FU Chen，WANG Kaijun. LASSO regression assisted by coefficient of determination and correlation coefficient[J]. Journal of Fujian Normal University (Natural Science Edition)，2024，40(2)：57−63.

[33] SHELATKAR T，TONDALE S，YADAV S，et al. Web traffic time series forecasting using ARIMA and LSTM RNN[J]. ITM Web of Conferences，2020，32：03017.