A back analysis model based on radial basis function networks is proposed for permanent deformation parameters of earth-rock dams. The model makes good use of the nonlinear mapping capability of the radial basis function networks. It can back-analyze the permanent deformation parameters of earth-rock dams with just a small amount of sample designs

and long computational time for inversion is not needed. Meanwhile

based on the sensitivity analysis of permanent deformation parameters

an objective function for network training is established by considering parameter sensitivity

which improves the inversion accuracy further. The model is illustrated on Zipingpu concrete-faced rockfill dam (CFRD). Three-dimensional finite element method is adopted for static and dynamic analysis

and the earthquake-induced permanent deformation is calculated with improved Shen Zhujiang model. The results show that the earthquake-induced permanent deformations calculated by inversion parameters are very close to the actual values. The proposed model is efficient in back-analysis of earthquake-induced permanent deformation parameters of earth-rock dams.