A dynamic modeling approach to predict water inflow during tunnel excavation in relatively uniform rock masses

Karst landforms are widely distributed all over the world. With the continuous improvement of infrastructure construction, tunnelling in mountainous karst areas is inevitable. Due to the complex hydrogeological conditions in karst areas, groundwater inflow during tunnelling is usually difficult to predict and can cause huge economic losses and casualties. Therefore, finding better ways to improve the prediction of tunnel water inflow is of great significance to ensure the safety of tunnelling. In this study, three commonly used modules (CHD, DRAIN and CFPM1) in MODFLOW are selected and compared to predict the water inflow of tunnels. We find that the CFPM1 module performs better in terms of considering both tunnel size and actual water inflow dynamics during tunnel excavation, which is a continuous process rather than an instantaneous process. Secondly, we build a hypothetical case and predict the tunnel water inflows using above three different modules. We find that the CHD module yields the largest initial and stable water inflow, followed by the DRAIN module, and the CFPM1 yields the least. Besides, as the most sensitive factor in the CFPM1 module, the influence of tunnel diameter on water inflow is discussed. Finally, taking the Shizishan Tunnel as an actual field example, we compare the simulation results of different modules with the measured tunnel inflow. In general, the prediction of the CFPM1 module is the closest to the measured value, and the prediction accuracy is the highest during the conventional tunnel construction process. However, when water-saturated karst features such as underground rivers, caves or faults are exposed during tunnelling, the water level may change instantaneously, which is more consistent with the principle of CHD module. In summary, this study provides theoretical and numerical support for the safe construction of relatively uniform rock mass tunnels in karst areas.