Climate change takes a great effect on global hydrology and Welter resources, ecology and environment, and social economic development due to an increasing concentration of greenhouse gases in the atmosphere. Relationship among streamflow and its influences of precipitation and temperature in monthly scale is developed using an artificial neural network model. The model is trained and validated based on inputs of precipitation and temperature data in Bayinbuluke hydrological station within the study catchment and output of streamflow data in the Dashankou hydrological station which controls streamflow of the Kaidu River into the Bosten Lake. The model structure is determined with a trial and error method. Sensitivity analysis of modeling slremflow to temperature rise and precipitation increase demonstrates that influences of temperature rise is more significant than that of precipitatioo in-crefise, and streamflow increase is primarily concentrated in summer season. Based on input of possible future climate scenarios predicted by regional climate models (RCMs), the model prediction presents thal annual streamflow would increase 38.6 percent, 71.8 percent in summer and 11.4 percent in winter.