Temporal downscaling: a comparison between artificial neural network and autocorrelation techniques over the Amazon Basin in present and future climate change scenarios

Several studies have been devoted to dynamic and statistical downscaling for both climate variability and climate change. This paper introduces an application of temporal neural networks for downscaling global climate model output and autocorrelation functions. This method is proposed for downscaling daily precipitation time series for a region in the Amazon Basin. The downscaling models were developed and validated using IPCC AR4 model output and observed daily precipitation. In this paper, five AOGCMs for the twentieth century (20C3M; 1970–1999) and three SRES scenarios (A2, A1B, and B1) were used. The performance in downscaling of the temporal neural network was compared to that of an autocorrelation statistical downscaling model with emphasis on its ability to reproduce the observed climate variability and tendency for the period 1970–1999. The model test results indicate that the neural network model significantly outperforms the statistical models for the downscaling of daily precipitation variability.

[1]  Alexei G. Sankovski,et al.  Special report on emissions scenarios , 2000 .

[2]  Yves Chauvin,et al.  Backpropagation: the basic theory , 1995 .

[3]  G. Hegerl,et al.  Detection of human influence on twentieth-century precipitation trends , 2007, Nature.

[4]  C. Thompson,et al.  A Comparison of Statistical and Model-Based Downscaling Techniques for Estimating Local Climate Variations. , 1998 .

[5]  Eric P. Salathe,et al.  Comparison of various precipitation downscaling methods for the simulation of streamflow in a rainshadow river basin , 2003 .

[6]  G. Bürger,et al.  Linear versus nonlinear techniques in downscaling , 1998 .

[7]  B. Hewitson,et al.  Large‐scale atmospheric controls on local precipitation in tropical Mexico , 1992 .

[8]  M. Rummukainen,et al.  Evaluating the performance and utility of regional climate models: the PRUDENCE project , 2007 .

[9]  Tereza Cavazos.  Large-scale circulation anomalies conducive to extreme precipitation events and derivation of daily rainfall in northeastern Mexico and southeastern Texas , 1999 .

[10]  J. Boulanger,et al.  Projection of future climate change conditions using IPCC simulations, neural networks and Bayesian statistics. Part 1: Temperature mean state and seasonal cycle in South America , 2006 .

[11]  J. Boulanger,et al.  Projection of future climate change conditions using IPCC simulations, neural networks and Bayesian statistics. Part 2: Precipitation mean state and seasonal cycle in South America , 2007 .

[12]  S. Solman,et al.  Local estimates of global climate change: a statistical downscaling approach , 1999 .

[13]  J. Pal,et al.  Mean, interannual variability and trends in a regional climate change experiment over Europe. I. Present-day climate (1961–1990) , 2004 .

[14]  Paulin Coulibaly,et al.  Temporal neural networks for downscaling climate variability and extremes , 2005, Proceedings. 2005 IEEE International Joint Conference on Neural Networks, 2005..

[15]  J. Marengo,et al.  Use of regional climate models in impacts assessments and adaptations studies from continental to regional and local scales , 2006 .

[16]  J. Pal,et al.  Projected changes in mean and extreme precipitation over the Mediterranean region from a high resolution double nested RCM simulation , 2006 .

[17]  John F. B. Mitchell,et al.  THE WCRP CMIP3 Multimodel Dataset: A New Era in Climate Change Research , 2007 .

[18]  F. Giorgi.  Simulation of Regional Climate Using a Limited Area Model Nested in a General Circulation Model , 1990 .

[19]  C. Bretherton,et al.  Statistical Precipitation Downscaling over the Northwestern United States Using Numerically Simulated Precipitation as a Predictor , 2003 .