A Mixture-Density-Network Based Approach for Finding Rating Curves: Facing Multi-Modality and Unbalanced Data Distribution

Citations

WEB OF SCIENCE

5
Citations

SCOPUS

6

초록

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.

키워드

rating curvesneural networksmixture density networksmulti-layer perceptronsscaled conjugate gradients algorithmsmulti-modalityhysteresisNEURAL-NETWORKSTAGEHYSTERESIS
제목
A Mixture-Density-Network Based Approach for Finding Rating Curves: Facing Multi-Modality and Unbalanced Data Distribution
저자
Yoo, ChulsangPark, Jooyoung
DOI
10.1007/s12205-010-0243-0
발행일
2010-03
유형
Article
저널명
KSCE Journal of Civil Engineering
14
2
페이지
245 ~ 252