Determination of compound channel apparent shear stress: Application of novel data mining models

Zohreh Sheikh Khozani, Khabat Khosravi, Binh Thai Pham, Bjørn Kløve, Wan Hanna Melini Wan Mohtar, Zaher Mundher Yaseen

Research output: Contribution to journalArticle

8 Citations (Scopus)

Abstract

Momentum exchange in the mixing region between the floodplain and the main channel is an essential hydraulic process, particularly for the estimation of discharge. The current study investigated various data mining models to estimate apparent shear stress in a symmetric compound channel with smooth and rough floodplains. The applied predictive models include random forest (RF), random tree (RT), reduced error pruning tree (REPT), M5P, and the distinguished hybrid bagging-M5P model. The models are constructed based on several correlated physical channel characteristic variables to predict the apparent shear stress. A sensitivity analysis is applied to select the best function tuning parameters for each model. Results showed that input with six variables exhibited the best prediction results for RF model while input with four variables produced the best performance for other models. Based on the optimised input variables for each model, the efficiency of five predictive models discussed here was evaluated. It was found that the M5P and hybrid bagging-M5P models with the coefficient of determination (R2) equal to 0.905 and 0.92, respectively, in the testing stage are superior in estimating apparent shear stress in compound channels than other RF, RT and REPT models.

Original languageEnglish
Pages (from-to)798-811
Number of pages14
JournalJournal of Hydroinformatics
Volume21
Issue number5
DOIs
Publication statusPublished - 1 Sep 2019

Fingerprint

data mining
shear stress
Data mining
Shear stress
pruning
floodplain
Discharge (fluid mechanics)
Sensitivity analysis
sensitivity analysis
momentum
Momentum
Tuning
Hydraulics
hydraulics

Keywords

  • Apparent shear stress
  • Compound channel
  • Data mining
  • Prediction

ASJC Scopus subject areas

  • Civil and Structural Engineering
  • Water Science and Technology
  • Geotechnical Engineering and Engineering Geology
  • Atmospheric Science

Cite this

Determination of compound channel apparent shear stress : Application of novel data mining models. / Khozani, Zohreh Sheikh; Khosravi, Khabat; Pham, Binh Thai; Kløve, Bjørn; Mohtar, Wan Hanna Melini Wan; Yaseen, Zaher Mundher.

In: Journal of Hydroinformatics, Vol. 21, No. 5, 01.09.2019, p. 798-811.

Research output: Contribution to journalArticle

Khozani, Zohreh Sheikh ; Khosravi, Khabat ; Pham, Binh Thai ; Kløve, Bjørn ; Mohtar, Wan Hanna Melini Wan ; Yaseen, Zaher Mundher. / Determination of compound channel apparent shear stress : Application of novel data mining models. In: Journal of Hydroinformatics. 2019 ; Vol. 21, No. 5. pp. 798-811.
@article{fe93a9021fcd441e810d677c9ab347c7,
title = "Determination of compound channel apparent shear stress: Application of novel data mining models",
abstract = "Momentum exchange in the mixing region between the floodplain and the main channel is an essential hydraulic process, particularly for the estimation of discharge. The current study investigated various data mining models to estimate apparent shear stress in a symmetric compound channel with smooth and rough floodplains. The applied predictive models include random forest (RF), random tree (RT), reduced error pruning tree (REPT), M5P, and the distinguished hybrid bagging-M5P model. The models are constructed based on several correlated physical channel characteristic variables to predict the apparent shear stress. A sensitivity analysis is applied to select the best function tuning parameters for each model. Results showed that input with six variables exhibited the best prediction results for RF model while input with four variables produced the best performance for other models. Based on the optimised input variables for each model, the efficiency of five predictive models discussed here was evaluated. It was found that the M5P and hybrid bagging-M5P models with the coefficient of determination (R2) equal to 0.905 and 0.92, respectively, in the testing stage are superior in estimating apparent shear stress in compound channels than other RF, RT and REPT models.",
keywords = "Apparent shear stress, Compound channel, Data mining, Prediction",
author = "Khozani, {Zohreh Sheikh} and Khabat Khosravi and Pham, {Binh Thai} and Bj{\o}rn Kl{\o}ve and Mohtar, {Wan Hanna Melini Wan} and Yaseen, {Zaher Mundher}",
year = "2019",
month = "9",
day = "1",
doi = "10.2166/hydro.2019.037",
language = "English",
volume = "21",
pages = "798--811",
journal = "Journal of Hydroinformatics",
issn = "1464-7141",
publisher = "IWA Publishing",
number = "5",

}

TY - JOUR

T1 - Determination of compound channel apparent shear stress

T2 - Application of novel data mining models

AU - Khozani, Zohreh Sheikh

AU - Khosravi, Khabat

AU - Pham, Binh Thai

AU - Kløve, Bjørn

AU - Mohtar, Wan Hanna Melini Wan

AU - Yaseen, Zaher Mundher

PY - 2019/9/1

Y1 - 2019/9/1

N2 - Momentum exchange in the mixing region between the floodplain and the main channel is an essential hydraulic process, particularly for the estimation of discharge. The current study investigated various data mining models to estimate apparent shear stress in a symmetric compound channel with smooth and rough floodplains. The applied predictive models include random forest (RF), random tree (RT), reduced error pruning tree (REPT), M5P, and the distinguished hybrid bagging-M5P model. The models are constructed based on several correlated physical channel characteristic variables to predict the apparent shear stress. A sensitivity analysis is applied to select the best function tuning parameters for each model. Results showed that input with six variables exhibited the best prediction results for RF model while input with four variables produced the best performance for other models. Based on the optimised input variables for each model, the efficiency of five predictive models discussed here was evaluated. It was found that the M5P and hybrid bagging-M5P models with the coefficient of determination (R2) equal to 0.905 and 0.92, respectively, in the testing stage are superior in estimating apparent shear stress in compound channels than other RF, RT and REPT models.

AB - Momentum exchange in the mixing region between the floodplain and the main channel is an essential hydraulic process, particularly for the estimation of discharge. The current study investigated various data mining models to estimate apparent shear stress in a symmetric compound channel with smooth and rough floodplains. The applied predictive models include random forest (RF), random tree (RT), reduced error pruning tree (REPT), M5P, and the distinguished hybrid bagging-M5P model. The models are constructed based on several correlated physical channel characteristic variables to predict the apparent shear stress. A sensitivity analysis is applied to select the best function tuning parameters for each model. Results showed that input with six variables exhibited the best prediction results for RF model while input with four variables produced the best performance for other models. Based on the optimised input variables for each model, the efficiency of five predictive models discussed here was evaluated. It was found that the M5P and hybrid bagging-M5P models with the coefficient of determination (R2) equal to 0.905 and 0.92, respectively, in the testing stage are superior in estimating apparent shear stress in compound channels than other RF, RT and REPT models.

KW - Apparent shear stress

KW - Compound channel

KW - Data mining

KW - Prediction

UR - http://www.scopus.com/inward/record.url?scp=85072394094&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85072394094&partnerID=8YFLogxK

U2 - 10.2166/hydro.2019.037

DO - 10.2166/hydro.2019.037

M3 - Article

AN - SCOPUS:85072394094

VL - 21

SP - 798

EP - 811

JO - Journal of Hydroinformatics

JF - Journal of Hydroinformatics

SN - 1464-7141

IS - 5

ER -