An ensemble decomposition-based artificial intelligence approach for daily streamflow prediction

Mohammad Rezaie-Balf, Sajad Fani Nowbandegani, S. Zahra Samadi, Hossein Fallah, Sina Alaghmand

Research output: Contribution to journalArticleResearchpeer-review

1 Citation (Scopus)

Abstract

Accurate prediction of daily streamflow plays an essential role in various applications of water resources engineering, such as flood mitigation and urban and agricultural planning. This study investigated a hybrid ensemble decomposition technique based on ensemble empirical mode decomposition (EEMD) and variational mode decomposition (VMD) with gene expression programming (GEP) and random forest regression (RFR) algorithms for daily streamflow simulation across three mountainous stations, Siira, Bilghan, and Gachsar, in Karaj, Iran. To determine the appropriate corresponding input variables with optimal lag time the partial auto-correlation function (PACF) and auto-correlation function (ACF) were used for streamflow prediction purpose. Calibration and validation datasets were separately decomposed by EEMD that eventually improved standalone predictive models. Further, the component of highest pass (IMF1) was decomposed by the VMD approach to breakdown the distinctive characteristic of the variables. Results suggested that the EEMD-VMD algorithm significantly enhanced model calibration. Moreover, the EEMD-VMD-RFR algorithm as a hybrid ensemble model outperformed better than other techniques (EEMD-VMD-GEP, RFR and GEP) for daily streamflow prediction of the selected gauging stations. Overall, the proposed methodology indicated the superiority of hybrid ensemble models compare to standalone in predicting streamflow time series particularly in case of high fluctuations and different patterns in datasets.

Original languageEnglish
Article number709
Number of pages30
JournalWater
Volume11
Issue number4
DOIs
Publication statusPublished - 6 Apr 2019

Keywords

  • Artificial intelligence (AI) approach
  • Ensemble empirical mode decomposition (EEMD)
  • Mountainous watershed
  • Streamflow
  • Variational mode decomposition (VMD)

Cite this

Rezaie-Balf, Mohammad ; Nowbandegani, Sajad Fani ; Samadi, S. Zahra ; Fallah, Hossein ; Alaghmand, Sina. / An ensemble decomposition-based artificial intelligence approach for daily streamflow prediction. In: Water. 2019 ; Vol. 11, No. 4.
@article{0184e37a13d74186abbc711e555d3ab6,
title = "An ensemble decomposition-based artificial intelligence approach for daily streamflow prediction",
abstract = "Accurate prediction of daily streamflow plays an essential role in various applications of water resources engineering, such as flood mitigation and urban and agricultural planning. This study investigated a hybrid ensemble decomposition technique based on ensemble empirical mode decomposition (EEMD) and variational mode decomposition (VMD) with gene expression programming (GEP) and random forest regression (RFR) algorithms for daily streamflow simulation across three mountainous stations, Siira, Bilghan, and Gachsar, in Karaj, Iran. To determine the appropriate corresponding input variables with optimal lag time the partial auto-correlation function (PACF) and auto-correlation function (ACF) were used for streamflow prediction purpose. Calibration and validation datasets were separately decomposed by EEMD that eventually improved standalone predictive models. Further, the component of highest pass (IMF1) was decomposed by the VMD approach to breakdown the distinctive characteristic of the variables. Results suggested that the EEMD-VMD algorithm significantly enhanced model calibration. Moreover, the EEMD-VMD-RFR algorithm as a hybrid ensemble model outperformed better than other techniques (EEMD-VMD-GEP, RFR and GEP) for daily streamflow prediction of the selected gauging stations. Overall, the proposed methodology indicated the superiority of hybrid ensemble models compare to standalone in predicting streamflow time series particularly in case of high fluctuations and different patterns in datasets.",
keywords = "Artificial intelligence (AI) approach, Ensemble empirical mode decomposition (EEMD), Mountainous watershed, Streamflow, Variational mode decomposition (VMD)",
author = "Mohammad Rezaie-Balf and Nowbandegani, {Sajad Fani} and Samadi, {S. Zahra} and Hossein Fallah and Sina Alaghmand",
year = "2019",
month = "4",
day = "6",
doi = "10.3390/w11040709",
language = "English",
volume = "11",
journal = "Water",
issn = "2073-4441",
publisher = "MDPI AG",
number = "4",

}

An ensemble decomposition-based artificial intelligence approach for daily streamflow prediction. / Rezaie-Balf, Mohammad; Nowbandegani, Sajad Fani; Samadi, S. Zahra; Fallah, Hossein; Alaghmand, Sina.

In: Water, Vol. 11, No. 4, 709, 06.04.2019.

Research output: Contribution to journalArticleResearchpeer-review

TY - JOUR

T1 - An ensemble decomposition-based artificial intelligence approach for daily streamflow prediction

AU - Rezaie-Balf, Mohammad

AU - Nowbandegani, Sajad Fani

AU - Samadi, S. Zahra

AU - Fallah, Hossein

AU - Alaghmand, Sina

PY - 2019/4/6

Y1 - 2019/4/6

N2 - Accurate prediction of daily streamflow plays an essential role in various applications of water resources engineering, such as flood mitigation and urban and agricultural planning. This study investigated a hybrid ensemble decomposition technique based on ensemble empirical mode decomposition (EEMD) and variational mode decomposition (VMD) with gene expression programming (GEP) and random forest regression (RFR) algorithms for daily streamflow simulation across three mountainous stations, Siira, Bilghan, and Gachsar, in Karaj, Iran. To determine the appropriate corresponding input variables with optimal lag time the partial auto-correlation function (PACF) and auto-correlation function (ACF) were used for streamflow prediction purpose. Calibration and validation datasets were separately decomposed by EEMD that eventually improved standalone predictive models. Further, the component of highest pass (IMF1) was decomposed by the VMD approach to breakdown the distinctive characteristic of the variables. Results suggested that the EEMD-VMD algorithm significantly enhanced model calibration. Moreover, the EEMD-VMD-RFR algorithm as a hybrid ensemble model outperformed better than other techniques (EEMD-VMD-GEP, RFR and GEP) for daily streamflow prediction of the selected gauging stations. Overall, the proposed methodology indicated the superiority of hybrid ensemble models compare to standalone in predicting streamflow time series particularly in case of high fluctuations and different patterns in datasets.

AB - Accurate prediction of daily streamflow plays an essential role in various applications of water resources engineering, such as flood mitigation and urban and agricultural planning. This study investigated a hybrid ensemble decomposition technique based on ensemble empirical mode decomposition (EEMD) and variational mode decomposition (VMD) with gene expression programming (GEP) and random forest regression (RFR) algorithms for daily streamflow simulation across three mountainous stations, Siira, Bilghan, and Gachsar, in Karaj, Iran. To determine the appropriate corresponding input variables with optimal lag time the partial auto-correlation function (PACF) and auto-correlation function (ACF) were used for streamflow prediction purpose. Calibration and validation datasets were separately decomposed by EEMD that eventually improved standalone predictive models. Further, the component of highest pass (IMF1) was decomposed by the VMD approach to breakdown the distinctive characteristic of the variables. Results suggested that the EEMD-VMD algorithm significantly enhanced model calibration. Moreover, the EEMD-VMD-RFR algorithm as a hybrid ensemble model outperformed better than other techniques (EEMD-VMD-GEP, RFR and GEP) for daily streamflow prediction of the selected gauging stations. Overall, the proposed methodology indicated the superiority of hybrid ensemble models compare to standalone in predicting streamflow time series particularly in case of high fluctuations and different patterns in datasets.

KW - Artificial intelligence (AI) approach

KW - Ensemble empirical mode decomposition (EEMD)

KW - Mountainous watershed

KW - Streamflow

KW - Variational mode decomposition (VMD)

UR - http://www.scopus.com/inward/record.url?scp=85065022773&partnerID=8YFLogxK

U2 - 10.3390/w11040709

DO - 10.3390/w11040709

M3 - Article

VL - 11

JO - Water

JF - Water

SN - 2073-4441

IS - 4

M1 - 709

ER -