Water inrush poses a serious threat to the safety and sustainability of coal mining operations, particularly in arid–semiarid regions where confined aquifers overlie coal seams. Therefore, an accurate assessment of roof water inrush risk is essential to prevent water hazards on the roof. In this study, a water abundance assessment model was developed for the Zhuanlongwan mining area (ZMA) to identify zones of varying inrush vulnerability. In the model, five key controlling indicators, that is, the roof-sandstone thickness, fault density, unit inflow, hydraulic conductivity, and lithologic coefficient, were determined with the fuzzy analytic hierarchy process (FAHP) and Random Forest (RF) approaches, and the roof aquifer was subsequently classified by using the natural breaks classification method (Jenks). The model performance was validated through metrics of the overall accuracy (A), Cohen′s κ coefficient, and the area under the receiver operating characteristic curve (AUC). Furthermore, the water inrush effect is also affected by the roof geological properties. By considering the relation between roof water abundance and the residual roof layer thickness influenced by the water-conducting fracture zone (WCFZ), a synthetic water inrush risk assessment system was finally organized, classified into four categories: the water-inrush risk zone, potential leakage zone, relative safe zone, and the safe zone. The results demonstrated a high level of agreement between predicted and observed vulnerability patterns, indicating the robustness of the FAHP-RF approach. This study provides a practical and data-driven framework for evaluating the water abundance of roof aquifers and mitigating water inrush hazards in arid–semiarid confined coal seam mining.
扫码关注我们
求助内容:
应助结果提醒方式:
