Statistical Downscaling of Temperature with the Random Forest Model

Advances in Meteorology - Tập 2017 - Trang 1-11 - 2017
Bo Pang1,2, Jiajia Yue1,2, Gang Zhao1,2, Zongxue Xu1,2
1Beijing Key Laboratory of Urban Hydrological Cycle and Sponge City Technology, Beijing 100875, China
2College of Water Sciences, Beijing Normal University, Beijing 100875, China

Tóm tắt

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.

Từ khóa


Tài liệu tham khảo

2007

2004

10.1007/s00704-009-0129-6

10.1016/s0022-1694(99)00136-5

10.1002/joc.2286

10.3354/cr013091

10.1016/S0921-8181(02)00206-0

10.1175/JHM409.1

10.1002/joc.1719

10.1002/joc.655

10.1007/s00704-006-0269-x

10.1007/s00704-014-1253-5

10.1002/joc.1811

10.1175/JCLI3424.1

10.1175/2008JCLI2150.1

10.1016/j.envsoft.2007.10.004

10.1002/joc.2211

10.1007/s00704-016-1956-x

10.3354/cr025015

10.1002/joc.1499

10.1061/(ASCE)HE.1943-5584.0000300

10.1016/S0022-1694(00)00346-2

10.1023/A:1010933404324

10.1016/j.eswa.2015.02.001

10.1016/j.jhydrol.2013.07.009

10.1016/j.compag.2015.05.001

10.1016/j.jhydrol.2015.06.008

10.1016/j.patrec.2005.08.011

10.1080/01431160412331269698

10.1016/j.rse.2011.12.003

10.1016/j.isprsjprs.2011.11.002

10.1021/ci034160g

10.5194/npg-14-211-2007

1991, 1

10.1007/s00704-008-0095-4

2007, Física de la Tierra, 19, 219

10.5194/nhess-12-651-2012

10.1016/j.quaint.2010.12.001

10.1016/j.foodchem.2013.08.013

10.3354/cr007085

2003, Climate Dynamics, 20, 807, 10.1007/s00382-002-0298-9

10.1007/s00704-014-1152-9

10.1016/j.agrformet.2011.03.011

Thông tin
Thông tin xuất bản

Advances in Meteorology

Tập 2017

1-11

Thông tin tác giả