Temporal neural networks for downscaling climate variability and extremes

This paper presents an application of temporal neural networks for downscaling global climate models (GCMs) output. Because of computational constraints, GCMs are usually run at coarse grid resolution (in the order of 100s of kilometres) and as a result they are inherently unable to present local sub-grid scale features and dynamics. Consequently, outputs from these models cannot be used directly in many climate change impact studies. This research explored the issues of 'downscaling' the outputs of GCMs using a temporal neural network (TNN) approach. The method is proposed for downscaling daily precipitation and temperature series for a region in northern Quebec, Canada. The downscaling models are developed and validated using large-scale predictor variables derived from the National Center for Environmental Prediction (NCEP) reanalysis data set. The performance of the temporal neural network downscaling model is also compared to a regression-based statistical downscaling model with emphasis on their ability in reproducing the observed climate variability and extremes. The downscaling results for the base period (1961-2000) suggest that the TNN is an efficient method for downscaling both daily precipitation as well as daily maximum and minimum temperature series. Furthermore, the different model test results indicate that the TNN model mostly outperforms the statistical models for the downscaling of daily precipitation extremes and variability.