Selection of variables for regional frequency analysis of annual maximum precipitation using multivariate techniques

Woosung Nam, Ju Young Shin, Hongjoon Shin, Jun Haeng Heo

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

The regional frequency analysis is useful to estimate more accurate precipitation quantiles than the at-site frequency analysis, especially in case of regions with short record length like South Korea. In this study, the regionalization of annual maximum precipitation in South Korea was considered. The identification of homogeneous regions has a significant effect on quantile estimation in the regional frequency analysis. Various variables related to precipitation can be used to form regions. Since the type and number of variables may lead to improve the efficiency of partitioning, it is important to select those precipitation related variables, which represent most of the information from all candidate variables. Multivariate analysis techniques such as principal component analysis, factor analysis, and Procrustes analysis were used for this purpose. Finally, 33 variables were selected from the 42 candidate variables using multivariate techniques. A big loss of information due to dimension reduction was not found. Therefore, dimension reduction can promote the efficiency of cluster analysis. The selected variables can be successfully used to form regions for regional frequency analysis of annual maximum precipitation in South Korea.

Original languageEnglish
Title of host publicationRestoring Our Natural Habitat - Proceedings of the 2007 World Environmental and Water Resources Congress
Publication statusPublished - 2007 Dec 1
Event2007 World Environmental and Water Resources Congress: Restoring Our Natural Habitat - Tampa, FL, United States
Duration: 2007 May 152007 May 19

Publication series

NameRestoring Our Natural Habitat - Proceedings of the 2007 World Environmental and Water Resources Congress

Other

Other2007 World Environmental and Water Resources Congress: Restoring Our Natural Habitat
CountryUnited States
CityTampa, FL
Period07/5/1507/5/19

Fingerprint

frequency analysis
Cluster analysis
Factor analysis
Principal component analysis
regionalization
multivariate analysis
factor analysis
cluster analysis
principal component analysis
partitioning
Multivariate Analysis

All Science Journal Classification (ASJC) codes

  • Environmental Engineering
  • Water Science and Technology

Cite this

Nam, W., Shin, J. Y., Shin, H., & Heo, J. H. (2007). Selection of variables for regional frequency analysis of annual maximum precipitation using multivariate techniques. In Restoring Our Natural Habitat - Proceedings of the 2007 World Environmental and Water Resources Congress (Restoring Our Natural Habitat - Proceedings of the 2007 World Environmental and Water Resources Congress).
Nam, Woosung ; Shin, Ju Young ; Shin, Hongjoon ; Heo, Jun Haeng. / Selection of variables for regional frequency analysis of annual maximum precipitation using multivariate techniques. Restoring Our Natural Habitat - Proceedings of the 2007 World Environmental and Water Resources Congress. 2007. (Restoring Our Natural Habitat - Proceedings of the 2007 World Environmental and Water Resources Congress).
@inproceedings{01d72f9e204e45569e25f344a2aed27f,
title = "Selection of variables for regional frequency analysis of annual maximum precipitation using multivariate techniques",
abstract = "The regional frequency analysis is useful to estimate more accurate precipitation quantiles than the at-site frequency analysis, especially in case of regions with short record length like South Korea. In this study, the regionalization of annual maximum precipitation in South Korea was considered. The identification of homogeneous regions has a significant effect on quantile estimation in the regional frequency analysis. Various variables related to precipitation can be used to form regions. Since the type and number of variables may lead to improve the efficiency of partitioning, it is important to select those precipitation related variables, which represent most of the information from all candidate variables. Multivariate analysis techniques such as principal component analysis, factor analysis, and Procrustes analysis were used for this purpose. Finally, 33 variables were selected from the 42 candidate variables using multivariate techniques. A big loss of information due to dimension reduction was not found. Therefore, dimension reduction can promote the efficiency of cluster analysis. The selected variables can be successfully used to form regions for regional frequency analysis of annual maximum precipitation in South Korea.",
author = "Woosung Nam and Shin, {Ju Young} and Hongjoon Shin and Heo, {Jun Haeng}",
year = "2007",
month = "12",
day = "1",
language = "English",
isbn = "9780784409275",
series = "Restoring Our Natural Habitat - Proceedings of the 2007 World Environmental and Water Resources Congress",
booktitle = "Restoring Our Natural Habitat - Proceedings of the 2007 World Environmental and Water Resources Congress",

}

Nam, W, Shin, JY, Shin, H & Heo, JH 2007, Selection of variables for regional frequency analysis of annual maximum precipitation using multivariate techniques. in Restoring Our Natural Habitat - Proceedings of the 2007 World Environmental and Water Resources Congress. Restoring Our Natural Habitat - Proceedings of the 2007 World Environmental and Water Resources Congress, 2007 World Environmental and Water Resources Congress: Restoring Our Natural Habitat, Tampa, FL, United States, 07/5/15.

Selection of variables for regional frequency analysis of annual maximum precipitation using multivariate techniques. / Nam, Woosung; Shin, Ju Young; Shin, Hongjoon; Heo, Jun Haeng.

Restoring Our Natural Habitat - Proceedings of the 2007 World Environmental and Water Resources Congress. 2007. (Restoring Our Natural Habitat - Proceedings of the 2007 World Environmental and Water Resources Congress).

Research output: Chapter in Book/Report/Conference proceedingConference contribution

TY - GEN

T1 - Selection of variables for regional frequency analysis of annual maximum precipitation using multivariate techniques

AU - Nam, Woosung

AU - Shin, Ju Young

AU - Shin, Hongjoon

AU - Heo, Jun Haeng

PY - 2007/12/1

Y1 - 2007/12/1

N2 - The regional frequency analysis is useful to estimate more accurate precipitation quantiles than the at-site frequency analysis, especially in case of regions with short record length like South Korea. In this study, the regionalization of annual maximum precipitation in South Korea was considered. The identification of homogeneous regions has a significant effect on quantile estimation in the regional frequency analysis. Various variables related to precipitation can be used to form regions. Since the type and number of variables may lead to improve the efficiency of partitioning, it is important to select those precipitation related variables, which represent most of the information from all candidate variables. Multivariate analysis techniques such as principal component analysis, factor analysis, and Procrustes analysis were used for this purpose. Finally, 33 variables were selected from the 42 candidate variables using multivariate techniques. A big loss of information due to dimension reduction was not found. Therefore, dimension reduction can promote the efficiency of cluster analysis. The selected variables can be successfully used to form regions for regional frequency analysis of annual maximum precipitation in South Korea.

AB - The regional frequency analysis is useful to estimate more accurate precipitation quantiles than the at-site frequency analysis, especially in case of regions with short record length like South Korea. In this study, the regionalization of annual maximum precipitation in South Korea was considered. The identification of homogeneous regions has a significant effect on quantile estimation in the regional frequency analysis. Various variables related to precipitation can be used to form regions. Since the type and number of variables may lead to improve the efficiency of partitioning, it is important to select those precipitation related variables, which represent most of the information from all candidate variables. Multivariate analysis techniques such as principal component analysis, factor analysis, and Procrustes analysis were used for this purpose. Finally, 33 variables were selected from the 42 candidate variables using multivariate techniques. A big loss of information due to dimension reduction was not found. Therefore, dimension reduction can promote the efficiency of cluster analysis. The selected variables can be successfully used to form regions for regional frequency analysis of annual maximum precipitation in South Korea.

UR - http://www.scopus.com/inward/record.url?scp=80051616760&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=80051616760&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:80051616760

SN - 9780784409275

T3 - Restoring Our Natural Habitat - Proceedings of the 2007 World Environmental and Water Resources Congress

BT - Restoring Our Natural Habitat - Proceedings of the 2007 World Environmental and Water Resources Congress

ER -

Nam W, Shin JY, Shin H, Heo JH. Selection of variables for regional frequency analysis of annual maximum precipitation using multivariate techniques. In Restoring Our Natural Habitat - Proceedings of the 2007 World Environmental and Water Resources Congress. 2007. (Restoring Our Natural Habitat - Proceedings of the 2007 World Environmental and Water Resources Congress).