The hydrogeological conditions of karst tunnel is statistically studied and comprehensively analyzed; and the main factors for the risk evaluation of water inrush of karst tunnel, i.e. geology, ground lithology, groundwater level, topography, strata inclination and surrounding rock fracture, are selected, so as to evaluate the water inrush risk of karst tunnel precisely and further reduce the water inrush risk. Due to the great difference among influencing factors under different hydrogeological conditions, the risk prediction of water inrush of karst tunnels based on BP neural network is adopted. The application results of abovementioned risk prediction method coincide with the actual situation. The abovementioned method is rational and can be used for reference.