Articles | Volume 23, issue 1
Research article
27 Jan 2016
Research article |  | 27 Jan 2016

Artificial neural networks and multiple linear regression model using principal components to estimate rainfall over South America

T. Soares dos Santos, D. Mendes, and R. Rodrigues Torres

Abstract. Several studies have been devoted to dynamic and statistical downscaling for analysis of both climate variability and climate change. This paper introduces an application of artificial neural networks (ANNs) and multiple linear regression (MLR) by principal components to estimate rainfall in South America. This method is proposed for downscaling monthly precipitation time series over South America for three regions: the Amazon; northeastern Brazil; and the La Plata Basin, which is one of the regions of the planet that will be most affected by the climate change projected for the end of the 21st century. The downscaling models were developed and validated using CMIP5 model output and observed monthly precipitation. We used general circulation model (GCM) experiments for the 20th century (RCP historical; 1970–1999) and two scenarios (RCP 2.6 and 8.5; 2070–2100). The model test results indicate that the ANNs significantly outperform the MLR downscaling of monthly precipitation variability.

Short summary
Statistical downscaling is widely used in large operational centers around the world, using exclusively linear relations (MLR); this study uses a statistical downscaling methodology using a nonlinear technique known as ANNs with CMIP5 project data. The artificial neural network can perform tasks that a linear program cannot. The main advantages of this are its temporal processing ability and its ability to incorporate several preceding predictor values as input without any additional effort.