Comparison between response surface models and artificial neural networks in hydrologic forecasting

Developing an efficient and accurate hydrologic forecasting model is crucial to managing water resources and flooding issues. In this study, response surface (RS) models including multiple linear regression (MLR), quadratic response surface (QRS), and nonlinear response surface (NRS) were applied to...

Full description

Saved in:
Bibliographic Details
Main Authors: Yu, Jianjun, Qin, Xiaosheng, Larsen, Ole, Chua, Lloyd Hock Chye
Other Authors: School of Civil and Environmental Engineering
Format: Article
Language:English
Published: 2014
Subjects:
Online Access:https://hdl.handle.net/10356/79536
http://hdl.handle.net/10220/19646
Tags: Add Tag
No Tags, Be the first to tag this record!
Institution: Nanyang Technological University
Language: English
id sg-ntu-dr.10356-79536
record_format dspace
spelling sg-ntu-dr.10356-795362020-03-07T11:43:29Z Comparison between response surface models and artificial neural networks in hydrologic forecasting Yu, Jianjun Qin, Xiaosheng Larsen, Ole Chua, Lloyd Hock Chye School of Civil and Environmental Engineering DHI Water & Environment Earth Observatory of Singapore DRNTU::Engineering::Civil engineering::Water resources Developing an efficient and accurate hydrologic forecasting model is crucial to managing water resources and flooding issues. In this study, response surface (RS) models including multiple linear regression (MLR), quadratic response surface (QRS), and nonlinear response surface (NRS) were applied to daily runoff (e.g., discharge and water level) prediction. Two catchments, one in southeast China and the other in western Canada, were used to demonstrate the applicability of the proposed models. Their performances were compared with artificial neural network (ANN) models, trained with the learning algorithms of the gradient descent with adaptive learning rate (ANN-GDA) and Levenberg-Marquardt (ANN-LM). The performances of both RS and ANN in relation to the lags used in the input data, the length of the training samples, long-term (monthly and yearly) predictions, and peak value predictions were also analyzed. The results indicate that the QRS and NRS were able to obtain equally good performance in runoff prediction, as compared with ANN-GDA and ANN-LM, but require lower computational efforts. The RS models bring practical benefits in their application to hydrologic forecasting, particularly in the cases of short-term flood forecasting (e.g., hourly) due to fast training capability, and could be considered as an alternative to ANN. MOE (Min. of Education, S’pore) Accepted version 2014-06-11T02:37:32Z 2019-12-06T13:27:45Z 2014-06-11T02:37:32Z 2019-12-06T13:27:45Z 2014 2014 Journal Article Yu, J., Qin, X., Larsen, O., & Chua, L. H. C. (2014). Comparison between Response Surface Models and Artificial Neural Networks in Hydrologic Forecasting. Journal of Hydrologic Engineering, 19(3), 473-481. 1084-0699 https://hdl.handle.net/10356/79536 http://hdl.handle.net/10220/19646 10.1061/(ASCE)HE.1943-5584.0000827 en Journal of hydrologic engineering © 2014 American Society of Civil Engineers. This is the author created version of a work that has been peer reviewed and accepted for publication by Journal of Hydrologic Engineering, American Society of Civil Engineers. It incorporates referee’s comments but changes resulting from the publishing process, such as copyediting, structural formatting, may not be reflected in this document. The published version is available at: [DOI:http://dx.doi.org/10.1061/(ASCE)HE.1943-5584.0000827]. 31 p. + 6 p. (Figures) application/pdf application/pdf application/pdf application/pdf application/pdf application/pdf application/pdf
institution Nanyang Technological University
building NTU Library
country Singapore
collection DR-NTU
language English
topic DRNTU::Engineering::Civil engineering::Water resources
spellingShingle DRNTU::Engineering::Civil engineering::Water resources
Yu, Jianjun
Qin, Xiaosheng
Larsen, Ole
Chua, Lloyd Hock Chye
Comparison between response surface models and artificial neural networks in hydrologic forecasting
description Developing an efficient and accurate hydrologic forecasting model is crucial to managing water resources and flooding issues. In this study, response surface (RS) models including multiple linear regression (MLR), quadratic response surface (QRS), and nonlinear response surface (NRS) were applied to daily runoff (e.g., discharge and water level) prediction. Two catchments, one in southeast China and the other in western Canada, were used to demonstrate the applicability of the proposed models. Their performances were compared with artificial neural network (ANN) models, trained with the learning algorithms of the gradient descent with adaptive learning rate (ANN-GDA) and Levenberg-Marquardt (ANN-LM). The performances of both RS and ANN in relation to the lags used in the input data, the length of the training samples, long-term (monthly and yearly) predictions, and peak value predictions were also analyzed. The results indicate that the QRS and NRS were able to obtain equally good performance in runoff prediction, as compared with ANN-GDA and ANN-LM, but require lower computational efforts. The RS models bring practical benefits in their application to hydrologic forecasting, particularly in the cases of short-term flood forecasting (e.g., hourly) due to fast training capability, and could be considered as an alternative to ANN.
author2 School of Civil and Environmental Engineering
author_facet School of Civil and Environmental Engineering
Yu, Jianjun
Qin, Xiaosheng
Larsen, Ole
Chua, Lloyd Hock Chye
format Article
author Yu, Jianjun
Qin, Xiaosheng
Larsen, Ole
Chua, Lloyd Hock Chye
author_sort Yu, Jianjun
title Comparison between response surface models and artificial neural networks in hydrologic forecasting
title_short Comparison between response surface models and artificial neural networks in hydrologic forecasting
title_full Comparison between response surface models and artificial neural networks in hydrologic forecasting
title_fullStr Comparison between response surface models and artificial neural networks in hydrologic forecasting
title_full_unstemmed Comparison between response surface models and artificial neural networks in hydrologic forecasting
title_sort comparison between response surface models and artificial neural networks in hydrologic forecasting
publishDate 2014
url https://hdl.handle.net/10356/79536
http://hdl.handle.net/10220/19646
_version_ 1681036312816123904