Many impact studies require climate change information at a finer resolution than that provided by Global Circulation Models (GCMs). This paper investigates the impact of climate change on maximum and minimum temperatures (i.e., predictands) of 14 meteorological stations in the Upper Thames River Basin (UTRB), Ontario, Canada. The data used for evaluation were large-scale predictor variables, extracted from NCEP/NCAR reanalysis data set and the simulations from third-generation Canadian Coupled Global Climate model (CGCM3). Data for four grid points covering the study region were used for developing the downscaling model. A downscaling method based on neural network was applied to project predictands generated from GCM using three scenarios (A1B, A2 and B1). The potential of the downscaling models in simulating predictands was evaluated and downscaling results reveal that the proposed downscaling model can reproduce local daily predictands from large-scale weather variables. Trends of projected maximum and minimum temperatures were studied for historical as well as downscaled values using GCM and scenario uncertainty. There is most likely an increasing trend for Tmax and Tmin for A2 scenario whereas no trend has been observed for B1 scenarios during 2081-2100.