Abstract. This paper proposes the application of evolutionary fuzzy (EF) approach for prediction of daily suspended sediment concentration (SSC). The EF was improved by the combination of two methods, fuzzy logic and genetic algorithm. The accuracy of EF models is compared with those of the artificial neural network (ANN) and adaptive neuro-fuzzy inference system with fuzzy c-means clustering (ANFIS-FCM). The daily streamflow and suspended sediment data collected from two stations on the Eel River in California, United States are used in the study. Root mean square errors (RMSE), mean absolute errors (MAE) and determination coefficient criteria are used for evaluating the accuracy of the models. The EF is found to be superior to the ANN and ANFIS-FCM in SSC prediction. The relative RMSE and MAE differences between the optimal EF and ANN models were found to be 13–50 % and 15–65 % for the upstream and downstream stations, respectively. Comparison of the optimal EF, ANN and ANFIS-FCM models in estimating peak and total suspended sediments revealed that the EF model provided better accuracy than the ANN and ANFIS-FCM.