Application of the Hybrid Artificial Neural Network Coupled with Rolling Mechanism and Grey Model Algorithms for Streamflow Forecasting Over Multiple Time Horizons

Zaher Mundher Yaseen, Minglei Fu, Chen Wang, Wan Hanna Melini Wan Mohtar, Ravinesh C. Deo, Ahmed El-shafie

Research output: Contribution to journalArticle

20 Citations (Scopus)

Abstract

Streamflow forecasting is paramount process in water and flood management, determination of river water flow potentials, environmental flow analysis, agricultural practices and hydro-power generation. However, the dynamicity, stochasticity and inherent complexities present in the temporal evolution of streamflow could hinder the accurate and reliable forecasting of this important hydrological parameter. In this study, the uncertainty and nonstationary characteristics of streamflow data has been treated using a set of coupled data pre-processing methods before being considered as input for an artificial neural network algorithm namely; rolling mechanism (RM) and grey models (GM). The rolling mechanism method is applied to smooth out the dataset based on the antecedent values of the model inputs before being applied to the GM algorithm. The optimization of the input datasets selection was performed using auto-correlation (ACF) and partial auto-correlation (PACF) functions. The pre-processed data was then integrated with two artificial neural network models, the back propagation (RMGM-BP) and Elman Recurrent Neural Network (RMGM-ERNN). The development, training, testing and evaluation of the proposed hybrid models were undertaken using streamflow data for two tropical hydrological basins (Johor and Kelantan Rivers). The hybrid RMGM-ERNN was found to provide better results than the hybrid RMGM-BP model. Relatively good performance of the proposed hybrid models with a data pre-processing approach provides a successful alternative to achieve better accuracy in streamflow forecasting compared to the traditional artificial neural network approach without a data pre-processing scheme.

Original languageEnglish
Pages (from-to)1883-1899
Number of pages17
JournalWater Resources Management
Volume32
Issue number5
DOIs
Publication statusPublished - 1 Mar 2018

Fingerprint

artificial neural network
streamflow
Neural networks
Recurrent neural networks
Autocorrelation
autocorrelation
Processing
Rivers
back propagation
Potential flow
stochasticity
temporal evolution
agricultural practice
Backpropagation
power generation
river flow
Catchments
Power generation
river water
Water

Keywords

  • Artificial neural network
  • Grey model
  • Multiple time scales
  • Rolling mechanism
  • Streamflow
  • Tropical environment

ASJC Scopus subject areas

  • Civil and Structural Engineering
  • Water Science and Technology

Cite this

Application of the Hybrid Artificial Neural Network Coupled with Rolling Mechanism and Grey Model Algorithms for Streamflow Forecasting Over Multiple Time Horizons. / Yaseen, Zaher Mundher; Fu, Minglei; Wang, Chen; Wan Mohtar, Wan Hanna Melini; Deo, Ravinesh C.; El-shafie, Ahmed.

In: Water Resources Management, Vol. 32, No. 5, 01.03.2018, p. 1883-1899.

Research output: Contribution to journalArticle

@article{6a71f20870b34781ac4d6aedaf288397,
title = "Application of the Hybrid Artificial Neural Network Coupled with Rolling Mechanism and Grey Model Algorithms for Streamflow Forecasting Over Multiple Time Horizons",
abstract = "Streamflow forecasting is paramount process in water and flood management, determination of river water flow potentials, environmental flow analysis, agricultural practices and hydro-power generation. However, the dynamicity, stochasticity and inherent complexities present in the temporal evolution of streamflow could hinder the accurate and reliable forecasting of this important hydrological parameter. In this study, the uncertainty and nonstationary characteristics of streamflow data has been treated using a set of coupled data pre-processing methods before being considered as input for an artificial neural network algorithm namely; rolling mechanism (RM) and grey models (GM). The rolling mechanism method is applied to smooth out the dataset based on the antecedent values of the model inputs before being applied to the GM algorithm. The optimization of the input datasets selection was performed using auto-correlation (ACF) and partial auto-correlation (PACF) functions. The pre-processed data was then integrated with two artificial neural network models, the back propagation (RMGM-BP) and Elman Recurrent Neural Network (RMGM-ERNN). The development, training, testing and evaluation of the proposed hybrid models were undertaken using streamflow data for two tropical hydrological basins (Johor and Kelantan Rivers). The hybrid RMGM-ERNN was found to provide better results than the hybrid RMGM-BP model. Relatively good performance of the proposed hybrid models with a data pre-processing approach provides a successful alternative to achieve better accuracy in streamflow forecasting compared to the traditional artificial neural network approach without a data pre-processing scheme.",
keywords = "Artificial neural network, Grey model, Multiple time scales, Rolling mechanism, Streamflow, Tropical environment",
author = "Yaseen, {Zaher Mundher} and Minglei Fu and Chen Wang and {Wan Mohtar}, {Wan Hanna Melini} and Deo, {Ravinesh C.} and Ahmed El-shafie",
year = "2018",
month = "3",
day = "1",
doi = "10.1007/s11269-018-1909-5",
language = "English",
volume = "32",
pages = "1883--1899",
journal = "Water Resources Management",
issn = "0920-4741",
publisher = "Springer Netherlands",
number = "5",

}

TY - JOUR

T1 - Application of the Hybrid Artificial Neural Network Coupled with Rolling Mechanism and Grey Model Algorithms for Streamflow Forecasting Over Multiple Time Horizons

AU - Yaseen, Zaher Mundher

AU - Fu, Minglei

AU - Wang, Chen

AU - Wan Mohtar, Wan Hanna Melini

AU - Deo, Ravinesh C.

AU - El-shafie, Ahmed

PY - 2018/3/1

Y1 - 2018/3/1

N2 - Streamflow forecasting is paramount process in water and flood management, determination of river water flow potentials, environmental flow analysis, agricultural practices and hydro-power generation. However, the dynamicity, stochasticity and inherent complexities present in the temporal evolution of streamflow could hinder the accurate and reliable forecasting of this important hydrological parameter. In this study, the uncertainty and nonstationary characteristics of streamflow data has been treated using a set of coupled data pre-processing methods before being considered as input for an artificial neural network algorithm namely; rolling mechanism (RM) and grey models (GM). The rolling mechanism method is applied to smooth out the dataset based on the antecedent values of the model inputs before being applied to the GM algorithm. The optimization of the input datasets selection was performed using auto-correlation (ACF) and partial auto-correlation (PACF) functions. The pre-processed data was then integrated with two artificial neural network models, the back propagation (RMGM-BP) and Elman Recurrent Neural Network (RMGM-ERNN). The development, training, testing and evaluation of the proposed hybrid models were undertaken using streamflow data for two tropical hydrological basins (Johor and Kelantan Rivers). The hybrid RMGM-ERNN was found to provide better results than the hybrid RMGM-BP model. Relatively good performance of the proposed hybrid models with a data pre-processing approach provides a successful alternative to achieve better accuracy in streamflow forecasting compared to the traditional artificial neural network approach without a data pre-processing scheme.

AB - Streamflow forecasting is paramount process in water and flood management, determination of river water flow potentials, environmental flow analysis, agricultural practices and hydro-power generation. However, the dynamicity, stochasticity and inherent complexities present in the temporal evolution of streamflow could hinder the accurate and reliable forecasting of this important hydrological parameter. In this study, the uncertainty and nonstationary characteristics of streamflow data has been treated using a set of coupled data pre-processing methods before being considered as input for an artificial neural network algorithm namely; rolling mechanism (RM) and grey models (GM). The rolling mechanism method is applied to smooth out the dataset based on the antecedent values of the model inputs before being applied to the GM algorithm. The optimization of the input datasets selection was performed using auto-correlation (ACF) and partial auto-correlation (PACF) functions. The pre-processed data was then integrated with two artificial neural network models, the back propagation (RMGM-BP) and Elman Recurrent Neural Network (RMGM-ERNN). The development, training, testing and evaluation of the proposed hybrid models were undertaken using streamflow data for two tropical hydrological basins (Johor and Kelantan Rivers). The hybrid RMGM-ERNN was found to provide better results than the hybrid RMGM-BP model. Relatively good performance of the proposed hybrid models with a data pre-processing approach provides a successful alternative to achieve better accuracy in streamflow forecasting compared to the traditional artificial neural network approach without a data pre-processing scheme.

KW - Artificial neural network

KW - Grey model

KW - Multiple time scales

KW - Rolling mechanism

KW - Streamflow

KW - Tropical environment

UR - http://www.scopus.com/inward/record.url?scp=85040652083&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85040652083&partnerID=8YFLogxK

U2 - 10.1007/s11269-018-1909-5

DO - 10.1007/s11269-018-1909-5

M3 - Article

VL - 32

SP - 1883

EP - 1899

JO - Water Resources Management

JF - Water Resources Management

SN - 0920-4741

IS - 5

ER -