Stream-flow forecasting using extreme learning machines

A case study in a semi-arid region in Iraq

Zaher Mundher Yaseen, Othman Jaafar, Ravinesh C. Deo, Ozgur Kisi, Jan Adamowski, John Quilty, Ahmed El-Shafie

Research output: Contribution to journalArticle

72 Citations (Scopus)

Abstract

Monthly stream-flow forecasting can yield important information for hydrological applications including sustainable design of rural and urban water management systems, optimization of water resource allocations, water use, pricing and water quality assessment, and agriculture and irrigation operations. The motivation for exploring and developing expert predictive models is an ongoing endeavor for hydrological applications. In this study, the potential of a relatively new data-driven method, namely the extreme learning machine (ELM) method, was explored for forecasting monthly stream-flow discharge rates in the Tigris River, Iraq. The ELM algorithm is a single-layer feedforward neural network (SLFNs) which randomly selects the input weights, hidden layer biases and analytically determines the output weights of the SLFNs. Based on the partial autocorrelation functions of historical stream-flow data, a set of five input combinations with lagged stream-flow values are employed to establish the best forecasting model. A comparative investigation is conducted to evaluate the performance of the ELM compared to other data-driven models: support vector regression (SVR) and generalized regression neural network (GRNN). The forecasting metrics defined as the correlation coefficient (r), Nash-Sutcliffe efficiency (ENS), Willmott's Index (WI), root-mean-square error (RMSE) and mean absolute error (MAE) computed between the observed and forecasted stream-flow data are employed to assess the ELM model's effectiveness. The results revealed that the ELM model outperformed the SVR and the GRNN models across a number of statistical measures. In quantitative terms, superiority of ELM over SVR and GRNN models was exhibited by ENS = 0.578, 0.378 and 0.144, r = 0.799, 0.761 and 0.468 and WI = 0.853, 0.802 and 0.689, respectively and the ELM model attained lower RMSE value by approximately 21.3% (relative to SVR) and by approximately 44.7% (relative to GRNN). Based on the findings of this study, several recommendations were suggested for further exploration of the ELM model in hydrological forecasting problems.

Original languageEnglish
Pages (from-to)603-614
Number of pages12
JournalJournal of Hydrology
Volume542
DOIs
Publication statusPublished - 1 Nov 2016

Fingerprint

semiarid region
streamflow
machine learning
resource allocation
autocorrelation
water use
water management
water resource
irrigation
agriculture
water quality
river

Keywords

  • Extreme learning machine
  • Generalized regression neural network
  • Iraq
  • Semi-arid
  • Stream-flow forecasting
  • Support vector regression

ASJC Scopus subject areas

  • Water Science and Technology

Cite this

Stream-flow forecasting using extreme learning machines : A case study in a semi-arid region in Iraq. / Yaseen, Zaher Mundher; Jaafar, Othman; Deo, Ravinesh C.; Kisi, Ozgur; Adamowski, Jan; Quilty, John; El-Shafie, Ahmed.

In: Journal of Hydrology, Vol. 542, 01.11.2016, p. 603-614.

Research output: Contribution to journalArticle

Yaseen, Zaher Mundher ; Jaafar, Othman ; Deo, Ravinesh C. ; Kisi, Ozgur ; Adamowski, Jan ; Quilty, John ; El-Shafie, Ahmed. / Stream-flow forecasting using extreme learning machines : A case study in a semi-arid region in Iraq. In: Journal of Hydrology. 2016 ; Vol. 542. pp. 603-614.
@article{32adf8482f244176a23cedc86442cb81,
title = "Stream-flow forecasting using extreme learning machines: A case study in a semi-arid region in Iraq",
abstract = "Monthly stream-flow forecasting can yield important information for hydrological applications including sustainable design of rural and urban water management systems, optimization of water resource allocations, water use, pricing and water quality assessment, and agriculture and irrigation operations. The motivation for exploring and developing expert predictive models is an ongoing endeavor for hydrological applications. In this study, the potential of a relatively new data-driven method, namely the extreme learning machine (ELM) method, was explored for forecasting monthly stream-flow discharge rates in the Tigris River, Iraq. The ELM algorithm is a single-layer feedforward neural network (SLFNs) which randomly selects the input weights, hidden layer biases and analytically determines the output weights of the SLFNs. Based on the partial autocorrelation functions of historical stream-flow data, a set of five input combinations with lagged stream-flow values are employed to establish the best forecasting model. A comparative investigation is conducted to evaluate the performance of the ELM compared to other data-driven models: support vector regression (SVR) and generalized regression neural network (GRNN). The forecasting metrics defined as the correlation coefficient (r), Nash-Sutcliffe efficiency (ENS), Willmott's Index (WI), root-mean-square error (RMSE) and mean absolute error (MAE) computed between the observed and forecasted stream-flow data are employed to assess the ELM model's effectiveness. The results revealed that the ELM model outperformed the SVR and the GRNN models across a number of statistical measures. In quantitative terms, superiority of ELM over SVR and GRNN models was exhibited by ENS = 0.578, 0.378 and 0.144, r = 0.799, 0.761 and 0.468 and WI = 0.853, 0.802 and 0.689, respectively and the ELM model attained lower RMSE value by approximately 21.3{\%} (relative to SVR) and by approximately 44.7{\%} (relative to GRNN). Based on the findings of this study, several recommendations were suggested for further exploration of the ELM model in hydrological forecasting problems.",
keywords = "Extreme learning machine, Generalized regression neural network, Iraq, Semi-arid, Stream-flow forecasting, Support vector regression",
author = "Yaseen, {Zaher Mundher} and Othman Jaafar and Deo, {Ravinesh C.} and Ozgur Kisi and Jan Adamowski and John Quilty and Ahmed El-Shafie",
year = "2016",
month = "11",
day = "1",
doi = "10.1016/j.jhydrol.2016.09.035",
language = "English",
volume = "542",
pages = "603--614",
journal = "Journal of Hydrology",
issn = "0022-1694",
publisher = "Elsevier",

}

TY - JOUR

T1 - Stream-flow forecasting using extreme learning machines

T2 - A case study in a semi-arid region in Iraq

AU - Yaseen, Zaher Mundher

AU - Jaafar, Othman

AU - Deo, Ravinesh C.

AU - Kisi, Ozgur

AU - Adamowski, Jan

AU - Quilty, John

AU - El-Shafie, Ahmed

PY - 2016/11/1

Y1 - 2016/11/1

N2 - Monthly stream-flow forecasting can yield important information for hydrological applications including sustainable design of rural and urban water management systems, optimization of water resource allocations, water use, pricing and water quality assessment, and agriculture and irrigation operations. The motivation for exploring and developing expert predictive models is an ongoing endeavor for hydrological applications. In this study, the potential of a relatively new data-driven method, namely the extreme learning machine (ELM) method, was explored for forecasting monthly stream-flow discharge rates in the Tigris River, Iraq. The ELM algorithm is a single-layer feedforward neural network (SLFNs) which randomly selects the input weights, hidden layer biases and analytically determines the output weights of the SLFNs. Based on the partial autocorrelation functions of historical stream-flow data, a set of five input combinations with lagged stream-flow values are employed to establish the best forecasting model. A comparative investigation is conducted to evaluate the performance of the ELM compared to other data-driven models: support vector regression (SVR) and generalized regression neural network (GRNN). The forecasting metrics defined as the correlation coefficient (r), Nash-Sutcliffe efficiency (ENS), Willmott's Index (WI), root-mean-square error (RMSE) and mean absolute error (MAE) computed between the observed and forecasted stream-flow data are employed to assess the ELM model's effectiveness. The results revealed that the ELM model outperformed the SVR and the GRNN models across a number of statistical measures. In quantitative terms, superiority of ELM over SVR and GRNN models was exhibited by ENS = 0.578, 0.378 and 0.144, r = 0.799, 0.761 and 0.468 and WI = 0.853, 0.802 and 0.689, respectively and the ELM model attained lower RMSE value by approximately 21.3% (relative to SVR) and by approximately 44.7% (relative to GRNN). Based on the findings of this study, several recommendations were suggested for further exploration of the ELM model in hydrological forecasting problems.

AB - Monthly stream-flow forecasting can yield important information for hydrological applications including sustainable design of rural and urban water management systems, optimization of water resource allocations, water use, pricing and water quality assessment, and agriculture and irrigation operations. The motivation for exploring and developing expert predictive models is an ongoing endeavor for hydrological applications. In this study, the potential of a relatively new data-driven method, namely the extreme learning machine (ELM) method, was explored for forecasting monthly stream-flow discharge rates in the Tigris River, Iraq. The ELM algorithm is a single-layer feedforward neural network (SLFNs) which randomly selects the input weights, hidden layer biases and analytically determines the output weights of the SLFNs. Based on the partial autocorrelation functions of historical stream-flow data, a set of five input combinations with lagged stream-flow values are employed to establish the best forecasting model. A comparative investigation is conducted to evaluate the performance of the ELM compared to other data-driven models: support vector regression (SVR) and generalized regression neural network (GRNN). The forecasting metrics defined as the correlation coefficient (r), Nash-Sutcliffe efficiency (ENS), Willmott's Index (WI), root-mean-square error (RMSE) and mean absolute error (MAE) computed between the observed and forecasted stream-flow data are employed to assess the ELM model's effectiveness. The results revealed that the ELM model outperformed the SVR and the GRNN models across a number of statistical measures. In quantitative terms, superiority of ELM over SVR and GRNN models was exhibited by ENS = 0.578, 0.378 and 0.144, r = 0.799, 0.761 and 0.468 and WI = 0.853, 0.802 and 0.689, respectively and the ELM model attained lower RMSE value by approximately 21.3% (relative to SVR) and by approximately 44.7% (relative to GRNN). Based on the findings of this study, several recommendations were suggested for further exploration of the ELM model in hydrological forecasting problems.

KW - Extreme learning machine

KW - Generalized regression neural network

KW - Iraq

KW - Semi-arid

KW - Stream-flow forecasting

KW - Support vector regression

UR - http://www.scopus.com/inward/record.url?scp=84994591754&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84994591754&partnerID=8YFLogxK

U2 - 10.1016/j.jhydrol.2016.09.035

DO - 10.1016/j.jhydrol.2016.09.035

M3 - Article

VL - 542

SP - 603

EP - 614

JO - Journal of Hydrology

JF - Journal of Hydrology

SN - 0022-1694

ER -