Abstract: A back analysis method of viscoelastic rock mass is proposed in this paper,in which,pattern search(PS),genetic algorithm(GA),and neural network(NN) are naturally combined.The method that has been trained by optimal prediction algorithm is used to describe relationship between the rock mass viscoelastic parameters and displacement and expected to improve the precision of back analysis on parameters,short the time of calculation.The practical engineering example shows feasibility and advantages of this method.