An important issue in application of fuzzy inference systems (FISs) to a class of systems identification problems such as forecasting problems is to extract the structure and type of fuzzy if-then rules from an input-output data set available. Given a FIS whose number and structure of fuzzy rules are known, artificial neural networks (ANNs) may be used to tune the shape of membership functions of fuzzy variables or other parameters of the fuzzy rule base. Adaptive-Network-Based Fuzzy Inference System (ANFIS) is an example of models in which the shape parameters of the membership functions of fuzzy premise variables as well as the linear parameters of the consequent part of fuzzy rules in a Takagi-Sugeno (TKS) FIS are tuned using ANNs. Genetic algorithms (GAs) may also be used for optimizing the parameter values of the subtractive clustering method by which the number and structure of an initial FIS is determined before it is tuned by ANNs. In this paper, a hybrid Genetic Algorithm-ANFIS (GA-ANFIS) model has been developed in which both clustering and rule base parameters are simultaneously optimized using GAs and ANNs. The model has been applied in prediction of wave parameters (wave significant height and peak spectral period) in Lake Michigan. The data set of year 2001 was used as training set and that of year 2004 as testing data. The results obtained by the hybrid GA-ANFIS model proposed are presented and analyzed.