Combing random forest and least square support vector regression for improving extreme rainfall downscaling

Quoc Bao Pham, Tao Chang Yang, Chen Min Kuo, Hung Wei Tseng, Pao Shan Yu

研究成果: Article

2 引文 (Scopus)

摘要

A statistical downscaling approach for improving extreme rainfall simulation was proposed to predict the daily rainfalls at Shih-Men Reservoir catchment in northern Taiwan. The structure of the proposed downscaling approach is composed of two parts: the rainfall-state classification and the regression for rainfall-amount prediction. Predictors of classification and regression methods were selected from the large-scale climate variables of the NCEP reanalysis data based on statistical tests. The data during 1964-1999 and 2000-2013 were used for calibration and validation, respectively. Three classification methods, including linear discriminant analysis (LDA), random forest (RF), and support vector classification (SVC), were adopted for rainfall-state classification and their performances were compared. After rainfall-state classification, the least square support vector regression (LS-SVR) was used for rainfall-amount prediction for different rainfall states. Two rainfall states (i.e., dry day and wet day) and three rainfall states (dry day, non-extreme-rainfall day, and extreme-rainfall day) were defined and compared for judging their downscaling performances. The results show that RF outperforms LDA and SVC for rainfall-state classification. Using RF for three-rainfall-states classification and LS-SVR for rainfall-amount prediction can improve the extreme rainfall downscaling.

原文English
文章編號451
期刊Water (Switzerland)
11
發行號3
DOIs
出版狀態Published - 2019 三月 1

指紋

downscaling
Least-Squares Analysis
Rain
least squares
rain
regression
rainfall
discriminant analysis
Discriminant Analysis
Forests
Discriminant analysis
statistical test
prediction
Climate
Taiwan
Calibration
performance
climate
rainfall simulation
Statistical tests

All Science Journal Classification (ASJC) codes

  • Biochemistry
  • Geography, Planning and Development
  • Aquatic Science
  • Water Science and Technology

引用此文

@article{f006ccce472347d781a135fc67a95888,
title = "Combing random forest and least square support vector regression for improving extreme rainfall downscaling",
abstract = "A statistical downscaling approach for improving extreme rainfall simulation was proposed to predict the daily rainfalls at Shih-Men Reservoir catchment in northern Taiwan. The structure of the proposed downscaling approach is composed of two parts: the rainfall-state classification and the regression for rainfall-amount prediction. Predictors of classification and regression methods were selected from the large-scale climate variables of the NCEP reanalysis data based on statistical tests. The data during 1964-1999 and 2000-2013 were used for calibration and validation, respectively. Three classification methods, including linear discriminant analysis (LDA), random forest (RF), and support vector classification (SVC), were adopted for rainfall-state classification and their performances were compared. After rainfall-state classification, the least square support vector regression (LS-SVR) was used for rainfall-amount prediction for different rainfall states. Two rainfall states (i.e., dry day and wet day) and three rainfall states (dry day, non-extreme-rainfall day, and extreme-rainfall day) were defined and compared for judging their downscaling performances. The results show that RF outperforms LDA and SVC for rainfall-state classification. Using RF for three-rainfall-states classification and LS-SVR for rainfall-amount prediction can improve the extreme rainfall downscaling.",
author = "Pham, {Quoc Bao} and Yang, {Tao Chang} and Kuo, {Chen Min} and Tseng, {Hung Wei} and Yu, {Pao Shan}",
year = "2019",
month = "3",
day = "1",
doi = "10.3390/w11030451",
language = "English",
volume = "11",
journal = "Water (Switzerland)",
issn = "2073-4441",
publisher = "Multidisciplinary Digital Publishing Institute (MDPI)",
number = "3",

}

Combing random forest and least square support vector regression for improving extreme rainfall downscaling. / Pham, Quoc Bao; Yang, Tao Chang; Kuo, Chen Min; Tseng, Hung Wei; Yu, Pao Shan.

於: Water (Switzerland), 卷 11, 編號 3, 451, 01.03.2019.

研究成果: Article

TY - JOUR

T1 - Combing random forest and least square support vector regression for improving extreme rainfall downscaling

AU - Pham, Quoc Bao

AU - Yang, Tao Chang

AU - Kuo, Chen Min

AU - Tseng, Hung Wei

AU - Yu, Pao Shan

PY - 2019/3/1

Y1 - 2019/3/1

N2 - A statistical downscaling approach for improving extreme rainfall simulation was proposed to predict the daily rainfalls at Shih-Men Reservoir catchment in northern Taiwan. The structure of the proposed downscaling approach is composed of two parts: the rainfall-state classification and the regression for rainfall-amount prediction. Predictors of classification and regression methods were selected from the large-scale climate variables of the NCEP reanalysis data based on statistical tests. The data during 1964-1999 and 2000-2013 were used for calibration and validation, respectively. Three classification methods, including linear discriminant analysis (LDA), random forest (RF), and support vector classification (SVC), were adopted for rainfall-state classification and their performances were compared. After rainfall-state classification, the least square support vector regression (LS-SVR) was used for rainfall-amount prediction for different rainfall states. Two rainfall states (i.e., dry day and wet day) and three rainfall states (dry day, non-extreme-rainfall day, and extreme-rainfall day) were defined and compared for judging their downscaling performances. The results show that RF outperforms LDA and SVC for rainfall-state classification. Using RF for three-rainfall-states classification and LS-SVR for rainfall-amount prediction can improve the extreme rainfall downscaling.

AB - A statistical downscaling approach for improving extreme rainfall simulation was proposed to predict the daily rainfalls at Shih-Men Reservoir catchment in northern Taiwan. The structure of the proposed downscaling approach is composed of two parts: the rainfall-state classification and the regression for rainfall-amount prediction. Predictors of classification and regression methods were selected from the large-scale climate variables of the NCEP reanalysis data based on statistical tests. The data during 1964-1999 and 2000-2013 were used for calibration and validation, respectively. Three classification methods, including linear discriminant analysis (LDA), random forest (RF), and support vector classification (SVC), were adopted for rainfall-state classification and their performances were compared. After rainfall-state classification, the least square support vector regression (LS-SVR) was used for rainfall-amount prediction for different rainfall states. Two rainfall states (i.e., dry day and wet day) and three rainfall states (dry day, non-extreme-rainfall day, and extreme-rainfall day) were defined and compared for judging their downscaling performances. The results show that RF outperforms LDA and SVC for rainfall-state classification. Using RF for three-rainfall-states classification and LS-SVR for rainfall-amount prediction can improve the extreme rainfall downscaling.

UR - http://www.scopus.com/inward/record.url?scp=85064892072&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85064892072&partnerID=8YFLogxK

U2 - 10.3390/w11030451

DO - 10.3390/w11030451

M3 - Article

AN - SCOPUS:85064892072

VL - 11

JO - Water (Switzerland)

JF - Water (Switzerland)

SN - 2073-4441

IS - 3

M1 - 451

ER -