Information about the parameters defining water resources availability is a key factor in their management which improves the operation policies for water resources systems. One of the most important parameters in this area is river streamflow. In this research, two different strategy of data fusion were tested for daily inflow simulation of Taleghan reservoir. Four artificial neural network models beside two Hammerstein-Wiener models were used as individual simulation models. The results showed that the data fusion method has the capacity to improve substantially the results of individual simulation models. The individual models also tested in combination with a weather generator model which was used to generate 100-year of daily temperature and precipitation data. The results demonstrated that although some models performed well in calibration and validation phases, but in combination with a weather generator, they could result in eccentric outcomes. This research also showed that the data fusion method can combine the results of single simulation models to improve the final estimate and to decrease the bandwidth of errors.