Modeling of scour depth and length of a diversion channel flow system with soft computing techniques

This study employed soft computing techniques, namely, support vector machine (SVM) and Gaussian process regression (GPR) techniques, to predict the properties of a scour hole depth (ds) and length (Ls) in a diversion channel flow system. The study considered different geometries of diversion channe...

Full description

Bibliographic Details
Main Authors: Alomari, Nashwan K., Sihag, Parveen, Sami Al-Janabi, Ahmed Mohammed, Yusuf, Badronnisa
Format: Article
Language:English
Published: IWA Publishing 2023
Online Access:http://psasir.upm.edu.my/id/eprint/110300/
http://psasir.upm.edu.my/id/eprint/110300/1/110300.pdf
_version_ 1848865487906144256
author Alomari, Nashwan K.
Sihag, Parveen
Sami Al-Janabi, Ahmed Mohammed
Yusuf, Badronnisa
author_facet Alomari, Nashwan K.
Sihag, Parveen
Sami Al-Janabi, Ahmed Mohammed
Yusuf, Badronnisa
author_sort Alomari, Nashwan K.
building UPM Institutional Repository
collection Online Access
description This study employed soft computing techniques, namely, support vector machine (SVM) and Gaussian process regression (GPR) techniques, to predict the properties of a scour hole depth (ds) and length (Ls) in a diversion channel flow system. The study considered different geometries of diversion channels (angles and bed widths) and different hydraulic conditions. Four kernel function models for each technique (polynomial kernel function, normalized polynomial kernel function, radial basis kernel, and the Pearson VII function kernel) were evaluated in this investigation. Root mean square error (RMSE) values are 8.3949 for training datasets and 11.6922 for testing datasets, confirming that the normalized polynomial kernel function-based GP outperformed other models in predicting Ls. Regarding predicting ds, the polynomial kernel function-based SVM outperforms other models, recording RMSE of 0.5175 for training datasets and 0.6019 for testing datasets. The sensitivity investigation of input parameters shows that the diversion angle had a major influence in predicting Ls and ds.
first_indexed 2025-11-15T14:05:30Z
format Article
id upm-110300
institution Universiti Putra Malaysia
institution_category Local University
language English
last_indexed 2025-11-15T14:05:30Z
publishDate 2023
publisher IWA Publishing
recordtype eprints
repository_type Digital Repository
spelling upm-1103002024-10-07T03:43:39Z http://psasir.upm.edu.my/id/eprint/110300/ Modeling of scour depth and length of a diversion channel flow system with soft computing techniques Alomari, Nashwan K. Sihag, Parveen Sami Al-Janabi, Ahmed Mohammed Yusuf, Badronnisa This study employed soft computing techniques, namely, support vector machine (SVM) and Gaussian process regression (GPR) techniques, to predict the properties of a scour hole depth (ds) and length (Ls) in a diversion channel flow system. The study considered different geometries of diversion channels (angles and bed widths) and different hydraulic conditions. Four kernel function models for each technique (polynomial kernel function, normalized polynomial kernel function, radial basis kernel, and the Pearson VII function kernel) were evaluated in this investigation. Root mean square error (RMSE) values are 8.3949 for training datasets and 11.6922 for testing datasets, confirming that the normalized polynomial kernel function-based GP outperformed other models in predicting Ls. Regarding predicting ds, the polynomial kernel function-based SVM outperforms other models, recording RMSE of 0.5175 for training datasets and 0.6019 for testing datasets. The sensitivity investigation of input parameters shows that the diversion angle had a major influence in predicting Ls and ds. IWA Publishing 2023 Article PeerReviewed text en cc_by_4 http://psasir.upm.edu.my/id/eprint/110300/1/110300.pdf Alomari, Nashwan K. and Sihag, Parveen and Sami Al-Janabi, Ahmed Mohammed and Yusuf, Badronnisa (2023) Modeling of scour depth and length of a diversion channel flow system with soft computing techniques. Water Supply, 23 (3). pp. 1267-1283. ISSN 1606-9749; eISSN: 1607-0798 https://iwaponline.com/ws/article/23/3/1267/93399/Modeling-of-scour-depth-and-length-of-a-diversion 10.2166/ws.2023.026
spellingShingle Alomari, Nashwan K.
Sihag, Parveen
Sami Al-Janabi, Ahmed Mohammed
Yusuf, Badronnisa
Modeling of scour depth and length of a diversion channel flow system with soft computing techniques
title Modeling of scour depth and length of a diversion channel flow system with soft computing techniques
title_full Modeling of scour depth and length of a diversion channel flow system with soft computing techniques
title_fullStr Modeling of scour depth and length of a diversion channel flow system with soft computing techniques
title_full_unstemmed Modeling of scour depth and length of a diversion channel flow system with soft computing techniques
title_short Modeling of scour depth and length of a diversion channel flow system with soft computing techniques
title_sort modeling of scour depth and length of a diversion channel flow system with soft computing techniques
url http://psasir.upm.edu.my/id/eprint/110300/
http://psasir.upm.edu.my/id/eprint/110300/
http://psasir.upm.edu.my/id/eprint/110300/
http://psasir.upm.edu.my/id/eprint/110300/1/110300.pdf