Coal Geology & Exploration


Predicting mine water inflow plays an important role in ensuring mine safety, optimizing resource allocation, and improving work efficiency. This study aims to improve the accuracy and stability of the predicted mine water inflow. Given their strong correlations with water inflow, borehole water level and microseismic energy were chosen as multifactor characteristic variables. Using these variables, this study developed the SSA-CG-Attention multifactor prediction model for mine water inflow along mining faces. The new model extracted effective nonlinear local features of data utilizing a new network structure, which was formed by integrating a convolutional neural network (CNN) based on the time sequence features extracted with a gated recurrent unit (GRU). Furthermore, this model introduced the attention mechanism to focus on input elements during prediction, thus improving the prediction accuracy. Finally, the sparrow search algorithm (SSA) was employed to optimize the model parameters and avoid the occurrence of locally optimal solutions. The new model was compared with traditional single-factor prediction models, including BP neural network, LSTM, and GRU, and multifactor prediction models, consisting of MLP, SLP, SVR, LSTM, GRU, SSA-LSTM, and SSA-GRU. The results indicate that the SSA algorithm allowed for quick optimization within the fewest iterations, thus ruling out the possibility of locally optimal solutions. The new model yielded an absolute error (EMA), a root mean square error (ERMS), and a mean absolute percentage error (EMAP) of 5.24 m3/h, 7.25 m3/h, and 6%, respectively, with a variance sum of 8.9. Furthermore, this model exhibited higher prediction accuracy than other prediction models, and the multifactor prediction models yielded more stable predicted results compared to the single-factor ones. The results of this study provide a new philosophy and methodology for the prediction of mine water inflow along mining faces and serve as a reference and guide for its prediction, prevention, and control, holding theoretical and practical significance.


prediction of mine water inflow, Convolutional Neural Network (CNN), Gated Recurrent Unit (GRU), Attention mechanism, multifactor prediction, microseismic energy




[1] 徐智敏,陈天赐,陈歌,等. 煤层采动顶板水文地质参数演化与矿井涌水量动态计算方法[J]. 煤炭学报,2023,48(2):833−845

XU Zhimin,CHEN Tianci,CHEN Ge,et al. Hydrogeological parameter evolution of coal seam roof and dynamic calculation method of mine water inflow[J]. Journal of China Coal Society,2023,48(2):833−845

[2] 王丹丹. 煤层底板突水危险源动态辨识及危险性动态评价[D]. 徐州:中国矿业大学,2021.

WANG Dandan. Dynamic hazard identification and risk assessment of mine water inrush from coal seam floor[D]. Xuzhou:China University of Mining and Technology,2021.

[3] 余国锋,袁亮,任波,等. 底板突水灾害大数据预测预警平台[J]. 煤炭学报,2021,46(11):3502−3514

YU Guofeng,YUAN Liang,REN Bo,et al. Big data prediction and early warning platform for floor water inrush disaster[J]. Journal of China Coal Society,2021,46(11):3502−3514

[4] LI BO,WU Huang,LIU Pu,et al. Construction and application of mine water inflow prediction model based on multi–factor weighted regression:Wulunshan Coal Mine case[J]. Earth Science Informatics,2023,16(2):1879−1890.

[5] 刘慧,刘桂芹,宁殿艳,等. 基于VMD–DBN的矿井涌水量预测方法[J]. 煤田地质与勘探,2023,51(6):13−21

LIU Hui,LIU Guiqin,NING Dianyan,et al. Mine water inrush prediction method based on VMD–DBN model[J]. Coal Geology & Exploration,2023,51(6):13−21

[6] 熊鹏,谢永生,韩冬,等. 基于Visual Modflow的刚果(金)迪兹瓦露天矿地下涌水量预测[J]. 科学技术与工程,2022,22(28):12324−12330

XIONG Peng,XIE Yongsheng,HAN Dong,et al. Prediction of underground water inflow in Deziwa Open–pit Mine in the Democratic Republic of Congo (DRC) based on Visual Modflow[J]. Science Technology and Engineering,2022,22(28):12324−12330

[7] 樊发旺,郭爱江,芦震,等. 基于生产因素相关性分析的矿井涌水量预测[J]. 陕西煤炭,2024,43(2):82−85

FAN Fawang,GUO Aijiang,LU Zhen,et al. Prediction of mine water inflow based on correlation analysis of production factors[J]. Shaanxi Coal,2024,43(2):82−85

[8] YANG Yanna,ZHANG Qiang,XU Mo. Numerical simulation method utilization in water gushing yield forecasting of Paoziling Tunnel in Hunan Province,China[J]. Applied Mechanics and Materials,2014,580–583:1392–1397.

[9] 张宪峰,魏久传,张延飞,等. 基于主成分分析与BP神经网络的矿井涌水量预测研究[J]. 煤炭技术,2018,37(6):201−203

ZHANG Xianfeng,WEI Jiuchuan,ZHANG Yanfei,et al. Principal component analysis and BP neural network of mine water inflow prediction research[J]. Coal Technology,2018,37(6):201−203

[10] 王档良,房亚飞,邓国伟,等. 基于改进多元回归模型与GIS的陕北凉水井矿井工作面涌水量预测[J]. 煤炭科技,2022,43(4):85−92

WANG Dangliang,FANG Yafei,DENG Guowei,et al. Prediction of water inflow of Liangshuijing mine face in northern Shaanxi based on improved multiple regression model and GIS[J]. Coal Science & Technology Magazine,2022,43(4):85−92

[11] 侯恩科,席慧琴,文强,等. 基于GMS的隐伏火烧区下煤层开采工作面涌水量预测[J]. 安全与环境学报,2022,22(5):2482−2492

HOU Enke,XI Huiqin,WEN Qiang,et al. Prediction of water inflow volume in the coal mining workforce below the concealed fire area based on GMS[J]. Journal of Safety and Environment,2022,22(5):2482−2492

[12] 张润畦,商芷萱,蒋知廷,等. 基于灰色系统理论与ARIMA模型对涌水量预测研究[J]. 华北科技学院学报,2022,19(1):13−20

ZHANG Runqi,SHANG Zhixuan,JIANG Zhiting,et al. Research on water in flow prediction methods based on grey system theory and ARIMA model[J]. Journal of North China Institute of Science and Technology,2022,19(1):13−20

[13] 吴卫忠,邓忠,陈余道,等. 广西盘龙铅锌矿涌水量时间序列变化特征分析及ARIMA预测[J]. 桂林理工大学学报,2023,43(3):406−413

WU Weizhong,DENG Zhong,CHEN Yudao,et al. Characteristic analysis of time series change and ARIMA prediction of water inflow for Panlong lead–zinc deposit in Guangxi[J]. Journal of Guilin University of Technology,2023,43(3):406−413

[14] 王晓蕾. 煤矿开采矿井涌水量预测方法现状及发展趋势[J]. 科学技术与工程,2020,20(30):12255−12267

WANG Xiaolei. Present situation and development trend of coal mine discharge forecast method[J]. Science Technology and Engineering,2020,20(30):12255−12267

[15] 程婷婷,梅欢,余子先,等. 微震监测技术在煤矿工业场区高边坡稳定性监测中的应用[J]. 中国煤炭,2023,49(3):55−61

CHENG Tingting,MEI Huan,YU Zixian,et al. Application of micro–seismic monitoring technology in stability monitoring of high slope of coal mine industrial site[J]. China Coal,2023,49(3):55−61

[16] 连会青,杨艺,杨松霖,等. 基于微震监测技术的煤矿顶板水害预测[J]. 煤矿安全,2023,54(5):49−55

LIAN Huiqing,YANG Yi,YANG Songlin,et al. Prediction of coal mine roof water damage based on micro–seismic monitoring technology[J]. Safety in Coal Mines,2023,54(5):49−55

[17] 周然然. 多重扰动煤体冲击地压影响因素及防治技术研究[D]. 廊坊:华北科技学院,2023.

ZHOU Ranran. Study on the influence factors and prevention technology of rockburst in coal mass with multiple disturbances[D]. Langfang:North China Institute of Science and Technology,2023.

[18] 杨艺. 亭南煤矿水害风险预警指标和预警方法研究[D]. 廊坊:华北科技学院,2022.

YANG Yi. Study on early warning index and method of water disaster risk monitoring in Tingnan Coal Mine[D]. Langfang:North China Institute of Science and Technology,2022.

[19] 查华胜,张海江,连会青,等. 潘二煤矿A组煤层底板灰岩水害微震监测[J]. 煤炭学报,2022,47(8):3001−3014

ZHA Huasheng,ZHANG Haijiang,LIAN Huiqing,et al. Microseismic monitoring on limestone water inrush at coal seam floor for group A coal layer of Pan’er Coal Mine[J]. Journal of China Coal Society,2022,47(8):3001−3014

[20] AMBADEKAR P K,CHOUDHARI C M. CNN based tool monitoring system to predict life of cutting tool[J]. SN Applied Sciences,2020,2(5):860.

[21] LECUN Y,BOTTOU L,BENGIO Y,et al. Gradient–based learning applied to document recognition[J]. Proceedings of the IEEE,1998,86(11):2278−2324.

[22] 郝晓东,乔星星,王影,等. 基于GRU神经网络多标签多分类的焦炭质量预测模型[J]. 煤炭转化,2023,46(6):90−100

HAO Xiaodong,QIAO Xingxing,WANG Ying,et al. Multi–label multi– classification coke quality prediction model based on GRU neural network[J]. Coal Conversion,2023,46(6):90−100

[23] CHUAH C W,HE Wanxian,HUANG Deshuang. GMean:A semi–supervised GRU and K–mean model for predicting the TF binding site[J]. Scientific Reports,2024,14(1):2539.

[24] 谢谦,董立红,厍向阳. 基于Attention–GRU的短期电价预测[J]. 电力系统保护与控制,2020,48(23):154−160

XIE Qian,DONG Lihong,SHE Xiangyang. Short–term electricity price forecasting based on Attention–GRU[J]. Power System Protection and Control,2020,48(23):154−160

[25] LI Zhanli,GAO Tianyu,GUO Cheng,et al. A gated recurrent unit network model for predicting open channel flow in coal mines based on attention mechanisms[J]. IEEE Access,2020,8:119819−119828.

[26] 邵良杉,毕圣昊,王彦彬,等. 基于ISSA–ELM的煤与瓦斯突出危险等级预测[J]. 中国安全生产科学技术,2023,19(9):76−82

SHAO Liangshan,BI Shenghao,WANG Yanbin,et al. Prediction of coal and gas outburst risk level based on ISSA–ELM[J]. Journal of Safety Science and Technology,2023,19(9):76−82

[27] YAO Zhiyuan,WANG Zhaocai,WANG Dangwei,et al. An ensemble CNN–LSTM and GRU adaptive weighting model based improved sparrow search algorithm for predicting runoff using historical meteorological and runoff data as input[J]. Journal of Hydrology,2023,625:129977.

[28] 王浩,丁峰,吴晓,等. 基于LSTM神经网络的航空公司旅客来电量预测方法[J]. 民航学报,2023,7(5):136−140

WANG Hao,DING Feng,WU Xiao,et al. Prediction method of airline passenger incoming calls based on LSTM neural network[J]. Journal of Civil Aviation,2023,7(5):136−140

[29] 杨艺,孟璐. 亭南煤矿微震监测数据与工作面涌水量关系研究[J]. 华北科技学院学报,2021,18(1):22−29

YANG Yi,MENG Lu. Study on the relationship between microseismic monitoring data and water inflow of working face in Tingnan Coal Mine[J]. Journal of North China Institute of Science and Technology,2021,18(1):22−29

[30] 梁满玉,尹尚先,姚辉,等. 基于DRN–BiLSTM模型的矿井涌水量预测[J]. 煤矿安全,2023,54(5):56−62

LIANG Manyu,YIN Shangxian,YAO Hui,et al. Mine water inflow prediction based on DRN–BiLSTM model[J]. Safety in Coal Mines,2023,54(5):56−62

[31] KAAN Y,FATIH I,EMEL K. Treatability of high–strength real sheep slaughterhouse wastewater using struvite precipitation coupled Fenton’s oxidation:The MAPFOX process[J]. Water Resources and Industry,2023,30:100228.



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.