Artificial neural network modeling of the rainfall-runoff process

Hsu Kuo-Lin Hsu, Hoshin Vijai Gupta, S. Sorooshian

Research output: Contribution to journalArticle

954 Citations (Scopus)

Abstract

This study presents a new procedure (entitled linear least squares simplex) for identifying the structure and parameters of three-layer feed forward artificial neural network (ANN) models and demonstrates the potential of such models for simulating the nonlinear hydrologic behaviour of watersheds. The nonlinear ANN model approach is shown to provide a better representation of the rainfall-runoff relationships of the medium-size Leaf River basin near Collins, Mississippi, than the linear ARMAX (autorergressive moving average with exogenous inputs) time series approach or the conceptual SAC-SMA (Sacramento soil moisture accounting) model. The ANN approach does provide a viable and effective alternative to the ARMAX time series approach for developing input-output simulation and forecasting models in situations that do not require modeling of the internal structure of the watershed. -from Authors

Original languageEnglish (US)
Pages (from-to)2517-2530
Number of pages14
JournalWater Resources Research
Volume31
Issue number10
DOIs
StatePublished - 1995
Externally publishedYes

Fingerprint

Runoff
artificial neural network
neural networks
Rain
runoff
Neural networks
rain
rainfall
modeling
Sacramento Soil Moisture Accounting Model
time series analysis
Watersheds
Time series
watershed
time series
nonlinear models
Soil moisture
least squares
Catchments
river basin

ASJC Scopus subject areas

  • Aquatic Science
  • Environmental Science(all)
  • Environmental Chemistry
  • Water Science and Technology

Cite this

Artificial neural network modeling of the rainfall-runoff process. / Kuo-Lin Hsu, Hsu; Gupta, Hoshin Vijai; Sorooshian, S.

In: Water Resources Research, Vol. 31, No. 10, 1995, p. 2517-2530.

Research output: Contribution to journalArticle

Kuo-Lin Hsu, Hsu ; Gupta, Hoshin Vijai ; Sorooshian, S. / Artificial neural network modeling of the rainfall-runoff process. In: Water Resources Research. 1995 ; Vol. 31, No. 10. pp. 2517-2530.
@article{1e1d0f678e404a5594f02b6c9582a867,
title = "Artificial neural network modeling of the rainfall-runoff process",
abstract = "This study presents a new procedure (entitled linear least squares simplex) for identifying the structure and parameters of three-layer feed forward artificial neural network (ANN) models and demonstrates the potential of such models for simulating the nonlinear hydrologic behaviour of watersheds. The nonlinear ANN model approach is shown to provide a better representation of the rainfall-runoff relationships of the medium-size Leaf River basin near Collins, Mississippi, than the linear ARMAX (autorergressive moving average with exogenous inputs) time series approach or the conceptual SAC-SMA (Sacramento soil moisture accounting) model. The ANN approach does provide a viable and effective alternative to the ARMAX time series approach for developing input-output simulation and forecasting models in situations that do not require modeling of the internal structure of the watershed. -from Authors",
author = "{Kuo-Lin Hsu}, Hsu and Gupta, {Hoshin Vijai} and S. Sorooshian",
year = "1995",
doi = "10.1029/95WR01955",
language = "English (US)",
volume = "31",
pages = "2517--2530",
journal = "Water Resources Research",
issn = "0043-1397",
publisher = "American Geophysical Union",
number = "10",

}

TY - JOUR

T1 - Artificial neural network modeling of the rainfall-runoff process

AU - Kuo-Lin Hsu, Hsu

AU - Gupta, Hoshin Vijai

AU - Sorooshian, S.

PY - 1995

Y1 - 1995

N2 - This study presents a new procedure (entitled linear least squares simplex) for identifying the structure and parameters of three-layer feed forward artificial neural network (ANN) models and demonstrates the potential of such models for simulating the nonlinear hydrologic behaviour of watersheds. The nonlinear ANN model approach is shown to provide a better representation of the rainfall-runoff relationships of the medium-size Leaf River basin near Collins, Mississippi, than the linear ARMAX (autorergressive moving average with exogenous inputs) time series approach or the conceptual SAC-SMA (Sacramento soil moisture accounting) model. The ANN approach does provide a viable and effective alternative to the ARMAX time series approach for developing input-output simulation and forecasting models in situations that do not require modeling of the internal structure of the watershed. -from Authors

AB - This study presents a new procedure (entitled linear least squares simplex) for identifying the structure and parameters of three-layer feed forward artificial neural network (ANN) models and demonstrates the potential of such models for simulating the nonlinear hydrologic behaviour of watersheds. The nonlinear ANN model approach is shown to provide a better representation of the rainfall-runoff relationships of the medium-size Leaf River basin near Collins, Mississippi, than the linear ARMAX (autorergressive moving average with exogenous inputs) time series approach or the conceptual SAC-SMA (Sacramento soil moisture accounting) model. The ANN approach does provide a viable and effective alternative to the ARMAX time series approach for developing input-output simulation and forecasting models in situations that do not require modeling of the internal structure of the watershed. -from Authors

UR - http://www.scopus.com/inward/record.url?scp=0029413797&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0029413797&partnerID=8YFLogxK

U2 - 10.1029/95WR01955

DO - 10.1029/95WR01955

M3 - Article

AN - SCOPUS:0029413797

VL - 31

SP - 2517

EP - 2530

JO - Water Resources Research

JF - Water Resources Research

SN - 0043-1397

IS - 10

ER -