Abstract: The artificial intelligence modeling of nonstationary rainfall-runoff has some restriction in accuracy of simulation base on complexity and nonlinearity of training patterns. Statistical preprocessing of trainings could determine homogeneity of rainfall-runoff patterns before modeling in artificial intelligence. In this study, the new hybrid model of artificial intelligence in conjunction with statistical clustering is introduced. Statistical pre-processing effects of 360 rainfall-runoff patterns considered before modeling using Radial Basis Function Neural Networks (RBFNNs). In the first step all 360 monthly rainfall-runoff patterns classify by cluster analysis in 4 groups and each class modeled by different RBFNNs topology. Results of 4 cluster base-RBFNNs compare with no action one and the optimized structure of Hybrid Cluster base-RBFNN models of Nazloochaei river flow present. Results show that clustering of rainfall-runoff patterns and modeling of each dataset by different RBFNNs has higher accuracy than no preprocessing of patterns in prediction and modeling of river flow.