A mixture-density-network based approach for finding rating curves

Facing multi-modality and unbalanced data distribution

Chulsang Yoo, Jooyoung Park

Research output: Contribution to journalArticle

4 Citations (Scopus)

Abstract

In this paper, the use of MDNs (Mixture Density Networks) is proposed for deciding rating curves. This method is beneficial especially when a single curve is developed when the relation between stage and discharge exhibits hysteresis. The computational analyses performed for the Han River and Mokkye stations showed that the MDN-based method yields more meaningful results than the conventional least squares approach. Of particular significance was the possible identification of the bi-modal characteristics of rating curves under the proposed method.

Original languageEnglish
Pages (from-to)243-250
Number of pages8
JournalKSCE Journal of Civil Engineering
Volume14
Issue number2
DOIs
Publication statusPublished - 2010 Mar 1

Fingerprint

Hysteresis
Rivers

Keywords

  • Hysteresis
  • Mixture density networks
  • Multi-layer perceptrons
  • Multi-modality
  • Neural networks
  • Rating curves
  • Scaled conjugate gradients algorithms

ASJC Scopus subject areas

  • Civil and Structural Engineering

Cite this

A mixture-density-network based approach for finding rating curves : Facing multi-modality and unbalanced data distribution. / Yoo, Chulsang; Park, Jooyoung.

In: KSCE Journal of Civil Engineering, Vol. 14, No. 2, 01.03.2010, p. 243-250.

Research output: Contribution to journalArticle

@article{a661a92e829b4817b64979fe91b44007,
title = "A mixture-density-network based approach for finding rating curves: Facing multi-modality and unbalanced data distribution",
abstract = "In this paper, the use of MDNs (Mixture Density Networks) is proposed for deciding rating curves. This method is beneficial especially when a single curve is developed when the relation between stage and discharge exhibits hysteresis. The computational analyses performed for the Han River and Mokkye stations showed that the MDN-based method yields more meaningful results than the conventional least squares approach. Of particular significance was the possible identification of the bi-modal characteristics of rating curves under the proposed method.",
keywords = "Hysteresis, Mixture density networks, Multi-layer perceptrons, Multi-modality, Neural networks, Rating curves, Scaled conjugate gradients algorithms",
author = "Chulsang Yoo and Jooyoung Park",
year = "2010",
month = "3",
day = "1",
doi = "10.1007/s12205-010-0243-0",
language = "English",
volume = "14",
pages = "243--250",
journal = "KSCE Journal of Civil Engineering",
issn = "1226-7988",
publisher = "Korean Society of Civil Engineers",
number = "2",

}

TY - JOUR

T1 - A mixture-density-network based approach for finding rating curves

T2 - Facing multi-modality and unbalanced data distribution

AU - Yoo, Chulsang

AU - Park, Jooyoung

PY - 2010/3/1

Y1 - 2010/3/1

N2 - In this paper, the use of MDNs (Mixture Density Networks) is proposed for deciding rating curves. This method is beneficial especially when a single curve is developed when the relation between stage and discharge exhibits hysteresis. The computational analyses performed for the Han River and Mokkye stations showed that the MDN-based method yields more meaningful results than the conventional least squares approach. Of particular significance was the possible identification of the bi-modal characteristics of rating curves under the proposed method.

AB - In this paper, the use of MDNs (Mixture Density Networks) is proposed for deciding rating curves. This method is beneficial especially when a single curve is developed when the relation between stage and discharge exhibits hysteresis. The computational analyses performed for the Han River and Mokkye stations showed that the MDN-based method yields more meaningful results than the conventional least squares approach. Of particular significance was the possible identification of the bi-modal characteristics of rating curves under the proposed method.

KW - Hysteresis

KW - Mixture density networks

KW - Multi-layer perceptrons

KW - Multi-modality

KW - Neural networks

KW - Rating curves

KW - Scaled conjugate gradients algorithms

UR - http://www.scopus.com/inward/record.url?scp=77649207385&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=77649207385&partnerID=8YFLogxK

U2 - 10.1007/s12205-010-0243-0

DO - 10.1007/s12205-010-0243-0

M3 - Article

VL - 14

SP - 243

EP - 250

JO - KSCE Journal of Civil Engineering

JF - KSCE Journal of Civil Engineering

SN - 1226-7988

IS - 2

ER -