An innovative data-driven quantitative prediction method aiming at base groundwater intrusion risk under extra-thick coal seam mining and its practical application

The coal production process is faced with intricate groundwater intrusion mechanisms and variable groundwater intrusion primary governing factors, and the uncertainties associated with the factors make the prediction of base groundwater intrusion more difficult. This research focuses on the Tangjiahui Coal Mine, which is a representative coalfield in Northwest China. The prediction index system including coal seam base aquifer capacity, aquiclude capacity, and geological structure is selected, with seven prediction factors being considered. Secondly, the analytic hierarchy process (AHP) and entropy weight (EW) method are applied to calculate the subjective and objective weights. On this basis, two models of comprehensive weight based on AHP-EW improved by game theory and improved variable weight of base groundwater intrusion risk based on the foundation of comprehensive weight are constructed. The predicted results are displayed by using the powerful spatial management and information processing functions of GIS, and the performance of the two models is discussed and compared. By comparing the prediction results with the in-situ groundwater intrusion points, it is found that the prediction model has high accuracy. Finally, the prevention strategies of base groundwater intrusion are put forward based on the risk zoning outcomes. The research findings can generate a scientific theoretical foundation for mine groundwater disaster prediction.