Statistical Downscaling of Temperature with the Random Forest Model

Bo Pang,Gang Zhao,Zongxue Xu,Jiajia Yue

doi:10.1155/2017/7265178

Abstract

The issues with downscaling the outputs of a global climate model (GCM) to a regional scale that are appropriate to hydrological impact studies are investigated using the random forest (RF) model, which has been shown to be superior for large dataset analysis and variable importance evaluation. The RF is proposed for downscaling daily mean temperature in the Pearl River basin in southern China. Four downscaling models were developed and validated by using the observed temperature series from 61 national stations and large-scale predictor variables derived from the National Center for Environmental Prediction–National Center for Atmospheric Research reanalysis dataset. The proposed RF downscaling model was compared to multiple linear regression, artificial neural network, and support vector machine models. Principal component analysis (PCA) and partial correlation analysis (PAR) were used in the predictor selection for the other models for a comprehensive study. It was shown that the model efficiency of the RF model was higher than that of the other models according to five selected criteria. By evaluating the predictor importance, the RF could choose the best predictor combination without using PCA and PAR. The results indicate that the RF is a feasible tool for the statistical downscaling of temperature.

Highlights

Global climate models (GCMs) are considered the most credible tools for the projection of future global climate change [1]
Duhan and Pandey [12] compared multiple linear regression (MLR), artificial neural networks (ANN), and the least square support vector machine (LS-support vector machines (SVM)) models to downscale the temperature of the Tons River basin in India and demonstrated that LS-SVM models perform better than ANN and MLR models
A statistical model based on the random forest method was proposed and applied to the Pearl River basin

Summary

Introduction

Global climate models (GCMs) are considered the most credible tools for the projection of future global climate change [1]. Various techniques have been developed to downscale GCM outputs to finer scales These methods are widely divided into dynamic (physical) and statistical (empirical) downscaling [2, 3]. Duhan and Pandey [12] compared MLR, ANN, and the least square support vector machine (LS-SVM) models to downscale the temperature of the Tons River basin in India and demonstrated that LS-SVM models perform better than ANN and MLR models. These comparison studies indicate that none of the aforementioned methods can assure an accurate estimate of temperature under different situations

Objectives

Methods

Findings

Conclusion