The study investigates the ability of FG (fuzzy genetic) approach in modeling solar radiation of seven cities from Mediterranean region of Anatolia, Turkey. Latitude, longitude, altitude and month of the year data from the Adana, K. Maras, Mersin, Antalya, Isparta, Burdur and Antakya cities are used as inputs to the FG model to estimate one month ahead solar radiation. FG model is compared with ANNs (artificial neural networks) and ANFIS (adaptive neruro fuzzzy inference system) models with respect to RMSE (root mean square errors), MAE (mean absolute errors) and determination coefficient (R-2) statistics. Comparison results indicate that the FG model performs better than the ANN and ANFIS models. It is found that the FG model can be successfully used for estimating solar radiation by using latitude, longitude, altitude and month of the year information. FG model with RMSE = 6.29 MJ/m(2), MAE = 4.69 MJ/m(2) and R-2 = 0.905 in the test stage was found to be superior to the optimal ANN model with RMSE = 7.17 MJ/m(2), MAE = 5.29 MJ/m(2) and R-2 = 0.876 and ANFIS model with RMSE = 6.75 MJ/m(2), MAE = 5.10 MJ/m(2) and R-2 = 0.892 in estimating solar radiation. (C) 2013 Elsevier Ltd. All rights reserved.