Mine water hazards in coal mining have currently become the second major “killer” in China’s coal mining. Accurately grasping the variation law of mine water inrush and precisely predicting the mine water inrush volume are of great significance for the allocation of mine resources and safe production. In order to construct a mine water inflow prediction model applicable to the impact of the massive and thick sandstone water hazard in western China, taking the Binchang mining area, which is most severely threatened by this water hazard, as the research object, based on the water inflow data of the 3407 working face of Gaojiabao certain mine. A water inflow prediction model for mine working faces based on VMD (variational mode decomposition)-LSTM(transformer-long short-term memory)-SVM(support vector machine) was proposed. The original water inflow time series data were first decomposed into sub-sequences of each mode through VMD. Features were then extracted for each modal component using the self-attention mechanism of the Transformer architecture. Finally, these features were fed into the LSTM-SVM combined model to complete the subsequent prediction of water inflow. The model prediction results show that the VMD-Transformer-LSTM-SVM coupling model has the smallest error compared with the other models: EMAE、EMAPE and ERMSE are 47.76 m3/h, 3.33% and 57.34 m3/h respectively, with a maximum R2 of 0.96. Moreover, compared with the prediction results of each model that have not undergone VMD, they also show higher robustness and accuracy. The research finds that the VMD-Transformer-LSTM-SVM coupling model shows relatively obvious advantages in the prediction of water inflow in the working face of this mine. This model not only enriches the prediction methods of water inflow in western mines, but also provides a new method for predicting mine water inflow for mines with geological conditions similar to the study mine. The research results have certain practical significance for the prediction of mine water inflow in mining areas and the prevention and control of mine water hazards.
LIU Xuan, JI Ya-dong, ZHU Kai-peng, ZHAO Chun-hu, LI Kai, LI Pan-pan, YUAN Chen-han, MU Rong-long, YAN Peng-zhen.
Construction and Application of VMD-Transformer-LSTM-SVM Time Series Prediction Model for Water Inflow in Coal Seam Roofs[J].
Science Technology and Engineering, 2026, 26(18): 7747-7758 DOI:10.12404/j.issn.1671-1815.2504573
WangShuangming, ShenYanjun, SongShijie, et al. Change of coal energy status and green and low-carbon development under the “dual carbon” goal[J]. Journal of China Coal Society, 2023, 48(7): 2599-2612.
WuQiang, GaoJunlian, ZengYifan, et al. Life-cycle protection and utilization of coal mine water in China[J]. Strategic Study of CAE, 2025, 27(2): 184-204.
LianHuiqing, YanTao, YinShangxian, et al. Research on early warning of roof water inrush in working faces based on a transparent hydrogeological model[J]. Coal Science and Technology, 2025, 53(1): 259-271.
ShiShouqiao, WuFuzhu, BianKai. Height prediction and three-dimensional development characteristics of the soft water-conductive fracture zone in weakly cemented overlay[J]. Journal of Mining & Safety Engineering, 2022, 39(6): 1154-1160.
XuDongjing, DouXuan, LiYe, et al. Predictive modeling of the development height of water-conducting fissure zones in mines in Shandong miningarea[J]. Journal of Mining Science and Technology, 2025, 10(1): 86-94.
DongXufeng, GaoWeifu, ZhuHaifeng, et al. Research on develo-pment law of repeated mining overburden fractures in close inclined multiple coal seams[J]. Safety in Coal Mines, 2025, 56(6): 1-8.
[13]
SunK, FanL M, XiaY C, et al. Impact of coal mining on groundwater of Luohe Formation in Binchang mining area[J]. Internatio-nal Journal of Coal Science & Technology, 2021, 8: 88-102.
ZhouQuanchao, LiuLing, LiJisheng, et al. Solving hydrogeological parameters of thick sandstone based on various analytical and numerical methods[J]. Coal Science and Technology, 2024, 52(S1): 174-182.
GuoXiaoming, LiuYingfeng, GuZhanxing. Detection and calculation of the height of water flowing fractured zone of coalroof in Binchang mining area[J]. Journal of Control Engineering, Mining and Strata, 2023, 5(5): 91-100.
LiuHui, LiuGuiqin, NingDianyan, et al. Mine water inrush prediction method based on VMD-DBN model[J]. Coal Geology & Exploration, 2023, 51(6): 13-21.
[20]
LiB, WuH, LiuP, 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: 1879-1890.
LiuXuan, JiYadong, ZhuKaipeng, et al. Construction and application of a TCN-LSTM-SVM-based time series prediction model for water inflow in coal seam roofs[J]. Coal Geology & Exploration, 2025, 53(6): 201-211.
WangHaibin, JiaChuanwei, ZhangSihua, et al. Analysis and prediction of the correlation between mine water inflow and mining parameters in Binchang Mining Area[J]. Journal of Mining & Safety Engineering, 2025, 42(1): 73-84.
WangDangliang, FangYafei, DengGuowei, 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.
[27]
LiuW T, LiQ, ZhaoJ Y, et al. Assessment of water inrush risk using the principal component logistic regression model in the Pandao coal mine, China[J]. Arabian Journal of Geosciences, 2018, 11(16). DOI: 10.1007/s12517-018-3815-9.
[28]
LiB, ZhangH L, LuoY L, et al. Mine inflow prediction model based on unbiased Grey-Markov theory and its application[J]. Earth Science Informatics, 2022, 15: 855-862.
[29]
LiuJ H, ZhaoY L, TanT, et al. Evolution and modeling of mine water inflow and hazard characteristics in southern coalfields of China: a case of Meitanba mine[J]. International Journal of Mining Science and Technology, 2022, 32: 513-524.
ZhouQuanchao, ZhengJieming, FuYaojun, et al. Application of“water release cross section flow”method inmine water inflow prediction: taking Hetaoyu Coal mine in the southern margin of Ordos Basin as an example[J]. Coal Science and Technology, 2023, 51(S1): 310-317.
XuZhimin, ChenTianci, ChenGe, et al. Hydrogeological para-meter evolution of coal seam roof and dynamic calculation method of mine water inflow[J]. Journal of China Coal Society, 2023, 48(2): 833-845.
LiJunqiang, WangXiaoshan, CongYu, et al. Prediction of water inflow in deep mining of large water mine based on Visual MODFLOW[J]. Metal Mine, 2024(10): 257-264.
HuBing, LiuHuiyue, LiYuan, et al. Influence of key parameter values in Modflow on mine water inflow prediction[J]. Coal Engineering, 2024, 56(10): 247-253.
[38]
ZhaiH T, WangJ C, LuY C, et al. Prediction of the mine water inflow of coal-bearing rock series based on well group pumping[J]. Water, 2023, 15: 3680.
XiongPeng, XieYongsheng, HanDong, 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.
ZhouQuanchao, WangDandan, DangZhiwei, et al. Research and comparative analysis of mine water inflowprediction method: a case study of Donggou Coal Mine in Xinjiang[J]. Coal Science and Technology, 2024, 52(S1): 211-220.
YuBo. Permeability evolution and water inflow dynamic prediction of stratified miningin extra-thick coal seam[D]. Beijing: China Coal Research Institute, 2022.
LiChaofeng. Prediction theory and method ofwater inflow from roof thick layeredaquifer of coal mining face[D]. Beijing: China Coal Research Institute, 2019.
HouEnke, XiaBingbing, WuZhangtao, et al. Mine water inflow prediction based on CEEMDAN-BO-BiGRU[J]. Science Techno-logy and Engineering, 2023, 23(28): 12012-12019.
[49]
ShiJ W, WangS Q, QuP F, et al. Time series prediction model using LSTM-Transformer neural network for mine water inflow[J]. Scientific Reports, 2024, 14: 18284.
[50]
DingY Y, YinS X, DaiZ X, et al. Multi-factor prediction of water inflow from the working face based on an improved SSA-RG-MHA model[J]. Water, 2024, 16: 3390.
[51]
YangS L, LianH Q, MohamadR S, et al. Hybrid approach for early warning of mine water: energy density-based identification of water-conducting channels combined with water inflow prediction by SA-LSTM[J]. IEEE Transactions on Geoscience and Remote Sensing, 2024, 62: 1-12.
ZhaoYuxing, LiXiangwen. Predicted water yield of open-pit metal mines based on a Bi-RNN and GMS coupling model[J]. Coal Geology & Exploration, 2024, 52(12): 155-169.
WangFei, RongTongrui, HouEnke, et al. Research on time series prediction method of mine water inflow based on VMD-BiLSTM combined model[J]. Mining Research and Development, 2024, 44(3): 143-151.
DingYingying, YinShangxian, LianHuiqing, et al. Research on water inflow prediction of working face based on CEEMDAN and improved hybrid time series model[J]. Journal of Safety Science and Technology, 2024, 20(3): 110-117.
[58]
DragomiretskiyK, ZossoD. Variational mode decomposition[J]. IEEE Transactions on Signal Processing, 2014, 62(3): 531-544.