Simulation of river flow in order to understand the river yield in the future is one of the important and
practical issues in water resource management. In this study, monthly discharge of Taleghan river in Glinak
stations at one step proceeding were forecasted using Artificial Intelligent (Artificial Neural Network MLP,
ANFIS with Grid Partition and Subtractive Clustering) and time series methods. Two inputs including raw
discharge data and de-seasonalised discharge data were used for different models. For time series models,
ARIMA (3,0,0)(0,1,1) were selected as suitable model. The optimum structure in Artificial Intelligence
method after pre-processing was determined using input and output data based on trial and error, and then,
using the optimum structure, the streamflow discharge was forecasted. After the output of each single
model was obtained, the structure of hybrid models were determined. The results showed hybrid methods
3 and 2 have the best application and time series model has better results than Artificial Intelligent methods.