Comparison of the efficacy of particle swarm optimization and stochastic gradient descent algorithms on multi-layer perceptron model to estimate longitudinal dispersion coefficients in natural streams

Accurate estimation of the longitudinal dispersion coefficient (LDC) is essential for modeling the pollution status in rivers. This research investigates the capabilities of machine-learning methods such as multi-layer perceptron (MLP), multi-layer perceptron trained with particle swarm optimization...

Full description

Bibliographic Details
Published in:Engineering Applications of Computational Fluid Mechanics
Main Author: Hai T.; Li H.; Band S.S.; Shadkani S.; Samadianfard S.; Hashemi S.; Chau K.-W.; Mousavi A.
Format: Article
Language:English
Published: Taylor and Francis Ltd. 2022
Online Access:https://www.scopus.com/inward/record.uri?eid=2-s2.0-85142253156&doi=10.1080%2f19942060.2022.2141896&partnerID=40&md5=45425c497c6bee866ef082e3eb8d5a4a
id 2-s2.0-85142253156
spelling 2-s2.0-85142253156
Hai T.; Li H.; Band S.S.; Shadkani S.; Samadianfard S.; Hashemi S.; Chau K.-W.; Mousavi A.
Comparison of the efficacy of particle swarm optimization and stochastic gradient descent algorithms on multi-layer perceptron model to estimate longitudinal dispersion coefficients in natural streams
2022
Engineering Applications of Computational Fluid Mechanics
16
1
10.1080/19942060.2022.2141896
https://www.scopus.com/inward/record.uri?eid=2-s2.0-85142253156&doi=10.1080%2f19942060.2022.2141896&partnerID=40&md5=45425c497c6bee866ef082e3eb8d5a4a
Accurate estimation of the longitudinal dispersion coefficient (LDC) is essential for modeling the pollution status in rivers. This research investigates the capabilities of machine-learning methods such as multi-layer perceptron (MLP), multi-layer perceptron trained with particle swarm optimization (MLP-PSO), multi-layer perceptron trained with Stochastic gradient descent deep learning (MLP-SGD) and different regressions including linear and non-linear regressions (LR and NLR) methods for determining the LDC of pollution in natural rivers and evaluates the accuracy of these methods in comparison with real measured data. Furthermore, the correlation coefficient (CC), root mean squared error (RMSE) and Willmott’s Index (WI) were implemented to evaluate the accuracies of the mentioned methods. Comparison of the results showed the superiority of the MLP-SGD model with CC of 0.923, RMSE of 281.4 and WI of 0.954, which indicates the undeniable accuracy and quality of the deep-learning model that can be used as a powerful model for LDC simulation. Also due to the acceptable performance of the PSO algorithm in the hybridization of the MLP model, the use of PSO algorithms is recommended to train machine-learning techniques for LDC estimation. © 2022 The Author(s). Published by Informa UK Limited, trading as Taylor & Francis Group.
Taylor and Francis Ltd.
19942060
English
Article
All Open Access; Gold Open Access
author Hai T.; Li H.; Band S.S.; Shadkani S.; Samadianfard S.; Hashemi S.; Chau K.-W.; Mousavi A.
spellingShingle Hai T.; Li H.; Band S.S.; Shadkani S.; Samadianfard S.; Hashemi S.; Chau K.-W.; Mousavi A.
Comparison of the efficacy of particle swarm optimization and stochastic gradient descent algorithms on multi-layer perceptron model to estimate longitudinal dispersion coefficients in natural streams
author_facet Hai T.; Li H.; Band S.S.; Shadkani S.; Samadianfard S.; Hashemi S.; Chau K.-W.; Mousavi A.
author_sort Hai T.; Li H.; Band S.S.; Shadkani S.; Samadianfard S.; Hashemi S.; Chau K.-W.; Mousavi A.
title Comparison of the efficacy of particle swarm optimization and stochastic gradient descent algorithms on multi-layer perceptron model to estimate longitudinal dispersion coefficients in natural streams
title_short Comparison of the efficacy of particle swarm optimization and stochastic gradient descent algorithms on multi-layer perceptron model to estimate longitudinal dispersion coefficients in natural streams
title_full Comparison of the efficacy of particle swarm optimization and stochastic gradient descent algorithms on multi-layer perceptron model to estimate longitudinal dispersion coefficients in natural streams
title_fullStr Comparison of the efficacy of particle swarm optimization and stochastic gradient descent algorithms on multi-layer perceptron model to estimate longitudinal dispersion coefficients in natural streams
title_full_unstemmed Comparison of the efficacy of particle swarm optimization and stochastic gradient descent algorithms on multi-layer perceptron model to estimate longitudinal dispersion coefficients in natural streams
title_sort Comparison of the efficacy of particle swarm optimization and stochastic gradient descent algorithms on multi-layer perceptron model to estimate longitudinal dispersion coefficients in natural streams
publishDate 2022
container_title Engineering Applications of Computational Fluid Mechanics
container_volume 16
container_issue 1
doi_str_mv 10.1080/19942060.2022.2141896
url https://www.scopus.com/inward/record.uri?eid=2-s2.0-85142253156&doi=10.1080%2f19942060.2022.2141896&partnerID=40&md5=45425c497c6bee866ef082e3eb8d5a4a
description Accurate estimation of the longitudinal dispersion coefficient (LDC) is essential for modeling the pollution status in rivers. This research investigates the capabilities of machine-learning methods such as multi-layer perceptron (MLP), multi-layer perceptron trained with particle swarm optimization (MLP-PSO), multi-layer perceptron trained with Stochastic gradient descent deep learning (MLP-SGD) and different regressions including linear and non-linear regressions (LR and NLR) methods for determining the LDC of pollution in natural rivers and evaluates the accuracy of these methods in comparison with real measured data. Furthermore, the correlation coefficient (CC), root mean squared error (RMSE) and Willmott’s Index (WI) were implemented to evaluate the accuracies of the mentioned methods. Comparison of the results showed the superiority of the MLP-SGD model with CC of 0.923, RMSE of 281.4 and WI of 0.954, which indicates the undeniable accuracy and quality of the deep-learning model that can be used as a powerful model for LDC simulation. Also due to the acceptable performance of the PSO algorithm in the hybridization of the MLP model, the use of PSO algorithms is recommended to train machine-learning techniques for LDC estimation. © 2022 The Author(s). Published by Informa UK Limited, trading as Taylor & Francis Group.
publisher Taylor and Francis Ltd.
issn 19942060
language English
format Article
accesstype All Open Access; Gold Open Access
record_format scopus
collection Scopus
_version_ 1809677892320231424