Application of novel data mining algorithms in prediction of discharge and end depth in trapezoidal sections

Payam Khosravinia; Mohammad Reza Nikpour; Ozgur Kisi; Zaher Mundher Yaseen

doi:10.1016/j.compag.2020.105283

Application of novel data mining algorithms in prediction of discharge and end depth in trapezoidal sections

Payam Khosravinia, Mohammad Reza Nikpour^*, Ozgur Kisi, Zaher Mundher Yaseen

^*Corresponding author for this work

Research output: Contribution to journal › Article › peer-review

15 Scopus citations

Abstract

Flow measurement in irrigation and drainage networks and water conveyance channels have particular importance. Direct methods of flow measurement are costly, time-consuming and are generally associated with losses of energy in flow. In this study, estimation of discharge and end depth of free overfall flows in trapezoidal channels section were investigated. For this purpose, data-driven techniques including dynamic evolving neural-fuzzy inference system (DENFIS), multivariate adaptive regression spline (MARS) and M5 model tree (M5Tree) were developed. 189 laboratory data experiments, six different scenarios based on geometric variables including side slope (m), bed width (B), bed slope (S₀), and hydraulic variables including critical depth (Y_c), critical slope (S_c) and end depth (Y_E) or discharge (Q) were applied. The model's performance was evaluated thorough several statistical indicators and graphical presentations. The accuracy of all three models were apparent in estimation of the discharge and the end depth for most of the scenarios. The results showed that the DENFIS model for the input combination of all variables (Y_c, Y_E, B, S₀, m, S_c) with the maximum values of R² and Nash-Sutcliffe efficiency coefficient (NSE) that were equal to 0.976 and 0.975, respectively, and the minimum values of RMSE, MAE, PBIAS and RSR, that were equal to 0.0015, 0.0989, −1.5906, and 0.1574, respectively, showed the highest estimation accuracy. Regarding the end depth estimation, DENFIS model for the input combination including the variables Y_c, Q, S_c, m, B with the highest values of R² and NSE equal to 0.993 and 0.992 respectively, and the lowest values of RMSE, MAE, PBIAS and RSR equal to 0.0028, 0.1628, 0.7383 and 0.0883, respectively, had a better performance compared to other MARS and M5Tree. The results of this study suggest DENFIS as a suitable and powerful model for estimation of discharge in irrigation and drainage networks.

Original language	English
Article number	105283
Journal	Computers and Electronics in Agriculture
Volume	170
DOIs	https://doi.org/10.1016/j.compag.2020.105283
State	Published - Mar 2020
Externally published	Yes

Bibliographical note

Publisher Copyright:
© 2020 Elsevier B.V.

Keywords

DENFIS
Discharge
Free overfall flow
M5 tree model
MARS

ASJC Scopus subject areas

Forestry
Agronomy and Crop Science
Computer Science Applications
Horticulture

Access to Document

10.1016/j.compag.2020.105283

Cite this

@article{d83245b5334d48edbb6d7820090c4bf4,

title = "Application of novel data mining algorithms in prediction of discharge and end depth in trapezoidal sections",

abstract = "Flow measurement in irrigation and drainage networks and water conveyance channels have particular importance. Direct methods of flow measurement are costly, time-consuming and are generally associated with losses of energy in flow. In this study, estimation of discharge and end depth of free overfall flows in trapezoidal channels section were investigated. For this purpose, data-driven techniques including dynamic evolving neural-fuzzy inference system (DENFIS), multivariate adaptive regression spline (MARS) and M5 model tree (M5Tree) were developed. 189 laboratory data experiments, six different scenarios based on geometric variables including side slope (m), bed width (B), bed slope (S0), and hydraulic variables including critical depth (Yc), critical slope (Sc) and end depth (YE) or discharge (Q) were applied. The model's performance was evaluated thorough several statistical indicators and graphical presentations. The accuracy of all three models were apparent in estimation of the discharge and the end depth for most of the scenarios. The results showed that the DENFIS model for the input combination of all variables (Yc, YE, B, S0, m, Sc) with the maximum values of R2 and Nash-Sutcliffe efficiency coefficient (NSE) that were equal to 0.976 and 0.975, respectively, and the minimum values of RMSE, MAE, PBIAS and RSR, that were equal to 0.0015, 0.0989, −1.5906, and 0.1574, respectively, showed the highest estimation accuracy. Regarding the end depth estimation, DENFIS model for the input combination including the variables Yc, Q, Sc, m, B with the highest values of R2 and NSE equal to 0.993 and 0.992 respectively, and the lowest values of RMSE, MAE, PBIAS and RSR equal to 0.0028, 0.1628, 0.7383 and 0.0883, respectively, had a better performance compared to other MARS and M5Tree. The results of this study suggest DENFIS as a suitable and powerful model for estimation of discharge in irrigation and drainage networks.",

keywords = "DENFIS, Discharge, Free overfall flow, M5 tree model, MARS",

author = "Payam Khosravinia and Nikpour, \{Mohammad Reza\} and Ozgur Kisi and Yaseen, \{Zaher Mundher\}",

note = "Publisher Copyright: {\textcopyright} 2020 Elsevier B.V.",

year = "2020",

month = mar,

doi = "10.1016/j.compag.2020.105283",

language = "English",

volume = "170",

journal = "Computers and Electronics in Agriculture",

issn = "0168-1699",

publisher = "Elsevier B.V.",

}

TY - JOUR

T1 - Application of novel data mining algorithms in prediction of discharge and end depth in trapezoidal sections

AU - Khosravinia, Payam

AU - Nikpour, Mohammad Reza

AU - Kisi, Ozgur

AU - Yaseen, Zaher Mundher

PY - 2020/3

Y1 - 2020/3

N2 - Flow measurement in irrigation and drainage networks and water conveyance channels have particular importance. Direct methods of flow measurement are costly, time-consuming and are generally associated with losses of energy in flow. In this study, estimation of discharge and end depth of free overfall flows in trapezoidal channels section were investigated. For this purpose, data-driven techniques including dynamic evolving neural-fuzzy inference system (DENFIS), multivariate adaptive regression spline (MARS) and M5 model tree (M5Tree) were developed. 189 laboratory data experiments, six different scenarios based on geometric variables including side slope (m), bed width (B), bed slope (S0), and hydraulic variables including critical depth (Yc), critical slope (Sc) and end depth (YE) or discharge (Q) were applied. The model's performance was evaluated thorough several statistical indicators and graphical presentations. The accuracy of all three models were apparent in estimation of the discharge and the end depth for most of the scenarios. The results showed that the DENFIS model for the input combination of all variables (Yc, YE, B, S0, m, Sc) with the maximum values of R2 and Nash-Sutcliffe efficiency coefficient (NSE) that were equal to 0.976 and 0.975, respectively, and the minimum values of RMSE, MAE, PBIAS and RSR, that were equal to 0.0015, 0.0989, −1.5906, and 0.1574, respectively, showed the highest estimation accuracy. Regarding the end depth estimation, DENFIS model for the input combination including the variables Yc, Q, Sc, m, B with the highest values of R2 and NSE equal to 0.993 and 0.992 respectively, and the lowest values of RMSE, MAE, PBIAS and RSR equal to 0.0028, 0.1628, 0.7383 and 0.0883, respectively, had a better performance compared to other MARS and M5Tree. The results of this study suggest DENFIS as a suitable and powerful model for estimation of discharge in irrigation and drainage networks.

AB - Flow measurement in irrigation and drainage networks and water conveyance channels have particular importance. Direct methods of flow measurement are costly, time-consuming and are generally associated with losses of energy in flow. In this study, estimation of discharge and end depth of free overfall flows in trapezoidal channels section were investigated. For this purpose, data-driven techniques including dynamic evolving neural-fuzzy inference system (DENFIS), multivariate adaptive regression spline (MARS) and M5 model tree (M5Tree) were developed. 189 laboratory data experiments, six different scenarios based on geometric variables including side slope (m), bed width (B), bed slope (S0), and hydraulic variables including critical depth (Yc), critical slope (Sc) and end depth (YE) or discharge (Q) were applied. The model's performance was evaluated thorough several statistical indicators and graphical presentations. The accuracy of all three models were apparent in estimation of the discharge and the end depth for most of the scenarios. The results showed that the DENFIS model for the input combination of all variables (Yc, YE, B, S0, m, Sc) with the maximum values of R2 and Nash-Sutcliffe efficiency coefficient (NSE) that were equal to 0.976 and 0.975, respectively, and the minimum values of RMSE, MAE, PBIAS and RSR, that were equal to 0.0015, 0.0989, −1.5906, and 0.1574, respectively, showed the highest estimation accuracy. Regarding the end depth estimation, DENFIS model for the input combination including the variables Yc, Q, Sc, m, B with the highest values of R2 and NSE equal to 0.993 and 0.992 respectively, and the lowest values of RMSE, MAE, PBIAS and RSR equal to 0.0028, 0.1628, 0.7383 and 0.0883, respectively, had a better performance compared to other MARS and M5Tree. The results of this study suggest DENFIS as a suitable and powerful model for estimation of discharge in irrigation and drainage networks.

KW - DENFIS

KW - Discharge

KW - Free overfall flow

KW - M5 tree model

KW - MARS

UR - https://www.scopus.com/pages/publications/85079340238

U2 - 10.1016/j.compag.2020.105283

DO - 10.1016/j.compag.2020.105283

M3 - Article

AN - SCOPUS:85079340238

SN - 0168-1699

VL - 170

JO - Computers and Electronics in Agriculture

JF - Computers and Electronics in Agriculture

M1 - 105283

ER -

Application of novel data mining algorithms in prediction of discharge and end depth in trapezoidal sections

Abstract

Bibliographical note

Keywords

ASJC Scopus subject areas

Access to Document

Fingerprint

Cite this