Loading…

Evolutionary computational intelligence algorithm coupled with self-tuning predictive model for water quality index determination

•A new hybrid intelligent models are developed for water quality index (WQI).•Non-linear input selection with non-tuned learning model is built for modeling WQI.•Kinta River is selected as case study which is located in tropical environment.•The stand-alone modeling schema is validated with the prop...

Full description

Saved in:
Bibliographic Details
Published in:Journal of hydrology (Amsterdam) 2020-08, Vol.587, p.124974, Article 124974
Main Authors: Abba, S.I., Hadi, Sinan Jasim, Sammen, Saad Sh, Salih, Sinan Q., Abdulkadir, R.A., Pham, Quoc Bao, Yaseen, Zaher Mundher
Format: Article
Language:English
Subjects:
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
cited_by cdi_FETCH-LOGICAL-c356t-5ead71da51fa1359d8c9874563696b61b79e46a09ed8e6db65762777ef2c287a3
cites cdi_FETCH-LOGICAL-c356t-5ead71da51fa1359d8c9874563696b61b79e46a09ed8e6db65762777ef2c287a3
container_end_page
container_issue
container_start_page 124974
container_title Journal of hydrology (Amsterdam)
container_volume 587
creator Abba, S.I.
Hadi, Sinan Jasim
Sammen, Saad Sh
Salih, Sinan Q.
Abdulkadir, R.A.
Pham, Quoc Bao
Yaseen, Zaher Mundher
description •A new hybrid intelligent models are developed for water quality index (WQI).•Non-linear input selection with non-tuned learning model is built for modeling WQI.•Kinta River is selected as case study which is located in tropical environment.•The stand-alone modeling schema is validated with the proposed hybrid models.•The proposed models indicated a superior prediction capacity for WQI. Anthropogenic activities affect the water bodies and result in a drastic reduction of river water quality (WQ). The development of a reliable intelligent model for evaluating the suitability of water remains a challenging task facing hydro-environmental engineers. The current study is investigated the applicability of Extreme Gradient Boosting (XGB) and Genetic Programming (GP) in obtaining feature importance, and then abstracted input variables were imposed into the predictive model (the Extreme Learning Machine (ELM)) for the prediction of water quality index (WQI). The stand-alone modeling schema is compared with the proposed hybrid models where the optimum variables are supplied into the GP, XGB, linear regression (LR), stepwise linear regression (SWLR) and ELM models. The WQ data is obtained from the Department of Environment (DoE) (Malaysia), and results are evaluated in terms of determination coefficient (R2) and root mean square error (RMSE). The results demonstrated that the hybrid GPELM and XGBELM models outperformed the standalone GP, XGB, and ELM models for the prediction of WQI at Kinta River basin. A comparison of the hybrid models showed that the predictive skill of GPELM (RMSE = 3.441 training and RMSE = 3.484 testing) over XGBELM improving the accuracy by decreasing the values of RMSE by 5% and 9% for training and testing, respectively with regards to XGBELM (RMSE = 3.606 training and RMSE = 3.816 testing). Although regressions are often proposed as reference models (LR and SWLR), when combined with computational intelligence, they still provide satisfactory results in this study. The proposed hybrid GPELM and XGBELM models have improved the prediction accuracy with minimum number of input variables and can therefore serve as reliable predictive tools for WQI at Kinta River basin.
doi_str_mv 10.1016/j.jhydrol.2020.124974
format article
fullrecord <record><control><sourceid>elsevier_cross</sourceid><recordid>TN_cdi_crossref_primary_10_1016_j_jhydrol_2020_124974</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><els_id>S0022169420304340</els_id><sourcerecordid>S0022169420304340</sourcerecordid><originalsourceid>FETCH-LOGICAL-c356t-5ead71da51fa1359d8c9874563696b61b79e46a09ed8e6db65762777ef2c287a3</originalsourceid><addsrcrecordid>eNqFkM9OwzAMxiMEEmPwCEh5gY4kbZP2hNA0_kiTuMA5yhJ3S5U2I003duTNyTbu-GL5k_3Z_iF0T8mMEsof2lm7OZjg3YwRljRW1KK4QBNaiTpjgohLNCGEsYzyurhGN8PQkhR5XkzQz2Ln3Rit71U4YO277RjVqXTY9hGcs2voNWDl1j7YuOlS07h1YPA-VXgA12Rx7G2_xtsAxupod4A7b8Dhxge8VxEC_hqVs_GQLA18YwNJ62x_WnSLrhrlBrj7y1P0-bz4mL9my_eXt_nTMtN5yWNWgjKCGlXSRtG8rE2l60oUJc95zVecrkQNBVekBlMBNyteCs6EENAwzSqh8ikqz746-GEI0MhtsF36WlIijxxlK_84yiNHeeaY5h7Pc5CO21kIctD2iMTYADpK4-0_Dr-hvoNs</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype></control><display><type>article</type><title>Evolutionary computational intelligence algorithm coupled with self-tuning predictive model for water quality index determination</title><source>ScienceDirect Journals</source><creator>Abba, S.I. ; Hadi, Sinan Jasim ; Sammen, Saad Sh ; Salih, Sinan Q. ; Abdulkadir, R.A. ; Pham, Quoc Bao ; Yaseen, Zaher Mundher</creator><creatorcontrib>Abba, S.I. ; Hadi, Sinan Jasim ; Sammen, Saad Sh ; Salih, Sinan Q. ; Abdulkadir, R.A. ; Pham, Quoc Bao ; Yaseen, Zaher Mundher</creatorcontrib><description>•A new hybrid intelligent models are developed for water quality index (WQI).•Non-linear input selection with non-tuned learning model is built for modeling WQI.•Kinta River is selected as case study which is located in tropical environment.•The stand-alone modeling schema is validated with the proposed hybrid models.•The proposed models indicated a superior prediction capacity for WQI. Anthropogenic activities affect the water bodies and result in a drastic reduction of river water quality (WQ). The development of a reliable intelligent model for evaluating the suitability of water remains a challenging task facing hydro-environmental engineers. The current study is investigated the applicability of Extreme Gradient Boosting (XGB) and Genetic Programming (GP) in obtaining feature importance, and then abstracted input variables were imposed into the predictive model (the Extreme Learning Machine (ELM)) for the prediction of water quality index (WQI). The stand-alone modeling schema is compared with the proposed hybrid models where the optimum variables are supplied into the GP, XGB, linear regression (LR), stepwise linear regression (SWLR) and ELM models. The WQ data is obtained from the Department of Environment (DoE) (Malaysia), and results are evaluated in terms of determination coefficient (R2) and root mean square error (RMSE). The results demonstrated that the hybrid GPELM and XGBELM models outperformed the standalone GP, XGB, and ELM models for the prediction of WQI at Kinta River basin. A comparison of the hybrid models showed that the predictive skill of GPELM (RMSE = 3.441 training and RMSE = 3.484 testing) over XGBELM improving the accuracy by decreasing the values of RMSE by 5% and 9% for training and testing, respectively with regards to XGBELM (RMSE = 3.606 training and RMSE = 3.816 testing). Although regressions are often proposed as reference models (LR and SWLR), when combined with computational intelligence, they still provide satisfactory results in this study. The proposed hybrid GPELM and XGBELM models have improved the prediction accuracy with minimum number of input variables and can therefore serve as reliable predictive tools for WQI at Kinta River basin.</description><identifier>ISSN: 0022-1694</identifier><identifier>EISSN: 1879-2707</identifier><identifier>DOI: 10.1016/j.jhydrol.2020.124974</identifier><language>eng</language><publisher>Elsevier B.V</publisher><subject>Extreme Gradient Boosting ; Extreme Learning Machine ; Genetic Programming ; Kinta River ; Water quality index ; Watershed management</subject><ispartof>Journal of hydrology (Amsterdam), 2020-08, Vol.587, p.124974, Article 124974</ispartof><rights>2020 Elsevier B.V.</rights><lds50>peer_reviewed</lds50><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed><citedby>FETCH-LOGICAL-c356t-5ead71da51fa1359d8c9874563696b61b79e46a09ed8e6db65762777ef2c287a3</citedby><cites>FETCH-LOGICAL-c356t-5ead71da51fa1359d8c9874563696b61b79e46a09ed8e6db65762777ef2c287a3</cites><orcidid>0000-0001-9356-2798 ; 0000-0001-5580-0644 ; 0000-0002-0468-5962 ; 0000-0003-3647-7137</orcidid></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><link.rule.ids>314,780,784,27924,27925</link.rule.ids></links><search><creatorcontrib>Abba, S.I.</creatorcontrib><creatorcontrib>Hadi, Sinan Jasim</creatorcontrib><creatorcontrib>Sammen, Saad Sh</creatorcontrib><creatorcontrib>Salih, Sinan Q.</creatorcontrib><creatorcontrib>Abdulkadir, R.A.</creatorcontrib><creatorcontrib>Pham, Quoc Bao</creatorcontrib><creatorcontrib>Yaseen, Zaher Mundher</creatorcontrib><title>Evolutionary computational intelligence algorithm coupled with self-tuning predictive model for water quality index determination</title><title>Journal of hydrology (Amsterdam)</title><description>•A new hybrid intelligent models are developed for water quality index (WQI).•Non-linear input selection with non-tuned learning model is built for modeling WQI.•Kinta River is selected as case study which is located in tropical environment.•The stand-alone modeling schema is validated with the proposed hybrid models.•The proposed models indicated a superior prediction capacity for WQI. Anthropogenic activities affect the water bodies and result in a drastic reduction of river water quality (WQ). The development of a reliable intelligent model for evaluating the suitability of water remains a challenging task facing hydro-environmental engineers. The current study is investigated the applicability of Extreme Gradient Boosting (XGB) and Genetic Programming (GP) in obtaining feature importance, and then abstracted input variables were imposed into the predictive model (the Extreme Learning Machine (ELM)) for the prediction of water quality index (WQI). The stand-alone modeling schema is compared with the proposed hybrid models where the optimum variables are supplied into the GP, XGB, linear regression (LR), stepwise linear regression (SWLR) and ELM models. The WQ data is obtained from the Department of Environment (DoE) (Malaysia), and results are evaluated in terms of determination coefficient (R2) and root mean square error (RMSE). The results demonstrated that the hybrid GPELM and XGBELM models outperformed the standalone GP, XGB, and ELM models for the prediction of WQI at Kinta River basin. A comparison of the hybrid models showed that the predictive skill of GPELM (RMSE = 3.441 training and RMSE = 3.484 testing) over XGBELM improving the accuracy by decreasing the values of RMSE by 5% and 9% for training and testing, respectively with regards to XGBELM (RMSE = 3.606 training and RMSE = 3.816 testing). Although regressions are often proposed as reference models (LR and SWLR), when combined with computational intelligence, they still provide satisfactory results in this study. The proposed hybrid GPELM and XGBELM models have improved the prediction accuracy with minimum number of input variables and can therefore serve as reliable predictive tools for WQI at Kinta River basin.</description><subject>Extreme Gradient Boosting</subject><subject>Extreme Learning Machine</subject><subject>Genetic Programming</subject><subject>Kinta River</subject><subject>Water quality index</subject><subject>Watershed management</subject><issn>0022-1694</issn><issn>1879-2707</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2020</creationdate><recordtype>article</recordtype><recordid>eNqFkM9OwzAMxiMEEmPwCEh5gY4kbZP2hNA0_kiTuMA5yhJ3S5U2I003duTNyTbu-GL5k_3Z_iF0T8mMEsof2lm7OZjg3YwRljRW1KK4QBNaiTpjgohLNCGEsYzyurhGN8PQkhR5XkzQz2Ln3Rit71U4YO277RjVqXTY9hGcs2voNWDl1j7YuOlS07h1YPA-VXgA12Rx7G2_xtsAxupod4A7b8Dhxge8VxEC_hqVs_GQLA18YwNJ62x_WnSLrhrlBrj7y1P0-bz4mL9my_eXt_nTMtN5yWNWgjKCGlXSRtG8rE2l60oUJc95zVecrkQNBVekBlMBNyteCs6EENAwzSqh8ikqz746-GEI0MhtsF36WlIijxxlK_84yiNHeeaY5h7Pc5CO21kIctD2iMTYADpK4-0_Dr-hvoNs</recordid><startdate>202008</startdate><enddate>202008</enddate><creator>Abba, S.I.</creator><creator>Hadi, Sinan Jasim</creator><creator>Sammen, Saad Sh</creator><creator>Salih, Sinan Q.</creator><creator>Abdulkadir, R.A.</creator><creator>Pham, Quoc Bao</creator><creator>Yaseen, Zaher Mundher</creator><general>Elsevier B.V</general><scope>AAYXX</scope><scope>CITATION</scope><orcidid>https://orcid.org/0000-0001-9356-2798</orcidid><orcidid>https://orcid.org/0000-0001-5580-0644</orcidid><orcidid>https://orcid.org/0000-0002-0468-5962</orcidid><orcidid>https://orcid.org/0000-0003-3647-7137</orcidid></search><sort><creationdate>202008</creationdate><title>Evolutionary computational intelligence algorithm coupled with self-tuning predictive model for water quality index determination</title><author>Abba, S.I. ; Hadi, Sinan Jasim ; Sammen, Saad Sh ; Salih, Sinan Q. ; Abdulkadir, R.A. ; Pham, Quoc Bao ; Yaseen, Zaher Mundher</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c356t-5ead71da51fa1359d8c9874563696b61b79e46a09ed8e6db65762777ef2c287a3</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2020</creationdate><topic>Extreme Gradient Boosting</topic><topic>Extreme Learning Machine</topic><topic>Genetic Programming</topic><topic>Kinta River</topic><topic>Water quality index</topic><topic>Watershed management</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Abba, S.I.</creatorcontrib><creatorcontrib>Hadi, Sinan Jasim</creatorcontrib><creatorcontrib>Sammen, Saad Sh</creatorcontrib><creatorcontrib>Salih, Sinan Q.</creatorcontrib><creatorcontrib>Abdulkadir, R.A.</creatorcontrib><creatorcontrib>Pham, Quoc Bao</creatorcontrib><creatorcontrib>Yaseen, Zaher Mundher</creatorcontrib><collection>CrossRef</collection><jtitle>Journal of hydrology (Amsterdam)</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Abba, S.I.</au><au>Hadi, Sinan Jasim</au><au>Sammen, Saad Sh</au><au>Salih, Sinan Q.</au><au>Abdulkadir, R.A.</au><au>Pham, Quoc Bao</au><au>Yaseen, Zaher Mundher</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Evolutionary computational intelligence algorithm coupled with self-tuning predictive model for water quality index determination</atitle><jtitle>Journal of hydrology (Amsterdam)</jtitle><date>2020-08</date><risdate>2020</risdate><volume>587</volume><spage>124974</spage><pages>124974-</pages><artnum>124974</artnum><issn>0022-1694</issn><eissn>1879-2707</eissn><abstract>•A new hybrid intelligent models are developed for water quality index (WQI).•Non-linear input selection with non-tuned learning model is built for modeling WQI.•Kinta River is selected as case study which is located in tropical environment.•The stand-alone modeling schema is validated with the proposed hybrid models.•The proposed models indicated a superior prediction capacity for WQI. Anthropogenic activities affect the water bodies and result in a drastic reduction of river water quality (WQ). The development of a reliable intelligent model for evaluating the suitability of water remains a challenging task facing hydro-environmental engineers. The current study is investigated the applicability of Extreme Gradient Boosting (XGB) and Genetic Programming (GP) in obtaining feature importance, and then abstracted input variables were imposed into the predictive model (the Extreme Learning Machine (ELM)) for the prediction of water quality index (WQI). The stand-alone modeling schema is compared with the proposed hybrid models where the optimum variables are supplied into the GP, XGB, linear regression (LR), stepwise linear regression (SWLR) and ELM models. The WQ data is obtained from the Department of Environment (DoE) (Malaysia), and results are evaluated in terms of determination coefficient (R2) and root mean square error (RMSE). The results demonstrated that the hybrid GPELM and XGBELM models outperformed the standalone GP, XGB, and ELM models for the prediction of WQI at Kinta River basin. A comparison of the hybrid models showed that the predictive skill of GPELM (RMSE = 3.441 training and RMSE = 3.484 testing) over XGBELM improving the accuracy by decreasing the values of RMSE by 5% and 9% for training and testing, respectively with regards to XGBELM (RMSE = 3.606 training and RMSE = 3.816 testing). Although regressions are often proposed as reference models (LR and SWLR), when combined with computational intelligence, they still provide satisfactory results in this study. The proposed hybrid GPELM and XGBELM models have improved the prediction accuracy with minimum number of input variables and can therefore serve as reliable predictive tools for WQI at Kinta River basin.</abstract><pub>Elsevier B.V</pub><doi>10.1016/j.jhydrol.2020.124974</doi><orcidid>https://orcid.org/0000-0001-9356-2798</orcidid><orcidid>https://orcid.org/0000-0001-5580-0644</orcidid><orcidid>https://orcid.org/0000-0002-0468-5962</orcidid><orcidid>https://orcid.org/0000-0003-3647-7137</orcidid><oa>free_for_read</oa></addata></record>
fulltext fulltext
identifier ISSN: 0022-1694
ispartof Journal of hydrology (Amsterdam), 2020-08, Vol.587, p.124974, Article 124974
issn 0022-1694
1879-2707
language eng
recordid cdi_crossref_primary_10_1016_j_jhydrol_2020_124974
source ScienceDirect Journals
subjects Extreme Gradient Boosting
Extreme Learning Machine
Genetic Programming
Kinta River
Water quality index
Watershed management
title Evolutionary computational intelligence algorithm coupled with self-tuning predictive model for water quality index determination
url http://sfxeu10.hosted.exlibrisgroup.com/loughborough?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2024-12-25T13%3A46%3A14IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-elsevier_cross&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=Evolutionary%20computational%20intelligence%20algorithm%20coupled%20with%20self-tuning%20predictive%20model%20for%20water%20quality%20index%20determination&rft.jtitle=Journal%20of%20hydrology%20(Amsterdam)&rft.au=Abba,%20S.I.&rft.date=2020-08&rft.volume=587&rft.spage=124974&rft.pages=124974-&rft.artnum=124974&rft.issn=0022-1694&rft.eissn=1879-2707&rft_id=info:doi/10.1016/j.jhydrol.2020.124974&rft_dat=%3Celsevier_cross%3ES0022169420304340%3C/elsevier_cross%3E%3Cgrp_id%3Ecdi_FETCH-LOGICAL-c356t-5ead71da51fa1359d8c9874563696b61b79e46a09ed8e6db65762777ef2c287a3%3C/grp_id%3E%3Coa%3E%3C/oa%3E%3Curl%3E%3C/url%3E&rft_id=info:oai/&rft_id=info:pmid/&rfr_iscdi=true