Learning networks in rainfall estimation

Theodore B. Trafalis; Budi Santosa; Michael B. Richman

doi:10.1007/s10287-005-0026-0

Learning networks in rainfall estimation

Theodore B. Trafalis^*, Budi Santosa, Michael B. Richman

^*Corresponding author for this work

Research output: Contribution to journal › Article › peer-review

11 Citations (Scopus)

Abstract

This paper utilizes Artificial Neural Networks (ANNs), standard Support Vector Regression (SVR), Least-Squares Support Vector Regression (LS-SVR), linear regression (LR) and a rain rate (RR) formula that meteorologists use, to estimate rainfall. A unique source of ground truth rainfall data is the Oklahoma Mesonet. With the advent of the WSR-88D network of radars data mining is feasible for this study. The reflectivity measurements from the radar are used as inputs for the techniques tested. LS-SVR generalizes better than ANNs, linear regression and a rain rate formula in rainfall estimation and for rainfall detection, SVR has a better performance than the other techniques.

Original language	English
Pages (from-to)	229-251
Number of pages	23
Journal	Computational Management Science
Volume	2
Issue number	3
DOIs	https://doi.org/10.1007/s10287-005-0026-0
Publication status	Published - Jul 2005
Externally published	Yes

Keywords

Artificial neural networks
Kernel functions
Radar
Rainfall estimation
Support vector machines

Access to Document

10.1007/s10287-005-0026-0

Cite this

@article{6c3de6b7d0b2401aad88ac5336b5479c,

title = "Learning networks in rainfall estimation",

abstract = "This paper utilizes Artificial Neural Networks (ANNs), standard Support Vector Regression (SVR), Least-Squares Support Vector Regression (LS-SVR), linear regression (LR) and a rain rate (RR) formula that meteorologists use, to estimate rainfall. A unique source of ground truth rainfall data is the Oklahoma Mesonet. With the advent of the WSR-88D network of radars data mining is feasible for this study. The reflectivity measurements from the radar are used as inputs for the techniques tested. LS-SVR generalizes better than ANNs, linear regression and a rain rate formula in rainfall estimation and for rainfall detection, SVR has a better performance than the other techniques.",

keywords = "Artificial neural networks, Kernel functions, Radar, Rainfall estimation, Support vector machines",

author = "Trafalis, {Theodore B.} and Budi Santosa and Richman, {Michael B.}",

note = "Funding Information: The present work has been partially supported by the NSF grant EIA-0205628.",

year = "2005",

month = jul,

doi = "10.1007/s10287-005-0026-0",

language = "English",

volume = "2",

pages = "229--251",

journal = "Computational Management Science",

issn = "1619-697X",

publisher = "Springer Verlag",

number = "3",

}

TY - JOUR

T1 - Learning networks in rainfall estimation

AU - Trafalis, Theodore B.

AU - Santosa, Budi

AU - Richman, Michael B.

N1 - Funding Information: The present work has been partially supported by the NSF grant EIA-0205628.

PY - 2005/7

Y1 - 2005/7

N2 - This paper utilizes Artificial Neural Networks (ANNs), standard Support Vector Regression (SVR), Least-Squares Support Vector Regression (LS-SVR), linear regression (LR) and a rain rate (RR) formula that meteorologists use, to estimate rainfall. A unique source of ground truth rainfall data is the Oklahoma Mesonet. With the advent of the WSR-88D network of radars data mining is feasible for this study. The reflectivity measurements from the radar are used as inputs for the techniques tested. LS-SVR generalizes better than ANNs, linear regression and a rain rate formula in rainfall estimation and for rainfall detection, SVR has a better performance than the other techniques.

AB - This paper utilizes Artificial Neural Networks (ANNs), standard Support Vector Regression (SVR), Least-Squares Support Vector Regression (LS-SVR), linear regression (LR) and a rain rate (RR) formula that meteorologists use, to estimate rainfall. A unique source of ground truth rainfall data is the Oklahoma Mesonet. With the advent of the WSR-88D network of radars data mining is feasible for this study. The reflectivity measurements from the radar are used as inputs for the techniques tested. LS-SVR generalizes better than ANNs, linear regression and a rain rate formula in rainfall estimation and for rainfall detection, SVR has a better performance than the other techniques.

KW - Artificial neural networks

KW - Kernel functions

KW - Radar

KW - Rainfall estimation

KW - Support vector machines

UR - http://www.scopus.com/inward/record.url?scp=22944439719&partnerID=8YFLogxK

U2 - 10.1007/s10287-005-0026-0

DO - 10.1007/s10287-005-0026-0

M3 - Article

AN - SCOPUS:22944439719

SN - 1619-697X

VL - 2

SP - 229

EP - 251

JO - Computational Management Science

JF - Computational Management Science

IS - 3

ER -

Learning networks in rainfall estimation

Abstract

Keywords

Access to Document

Other files and links

Fingerprint

Cite this