Toggle Main Menu Toggle Search

Open Access padlockePrints

Advancing water quality research: K-nearest neighbor coupled with the improved grey wolf optimizer algorithm model unveils new possibilities for dry residue prediction

Lookup NU author(s): Dr Jie ZhangORCiD

Downloads


Licence

This work is licensed under a Creative Commons Attribution 4.0 International License (CC BY 4.0).


Abstract

Monitoring stations have been established to combat water pollution, improve the ecosystem,promote human health, and facilitate drinking water production. However, continuous andextensive monitoring of water is costly and time-consuming, resulting in limited datasets and hinderingwater management research. This study focuses on developing an optimized K-nearest neighbor(KNN) model using the improved grey wolf optimization (I-GWO) algorithm to predict dry residuequantities. The model incorporates 20 physical and chemical parameters derived from a dataset of400 samples. Cross-validation is employed to assess model performance, optimize parameters, andmitigate the risk of overfitting. Four folds are created, and each fold is optimized using 11 distancemetrics and their corresponding weighting functions to determine the best model configuration.Among the evaluated models, the Jaccard distance metric with inverse squared weighting functionconsistently demonstrates the best performance in terms of statistical errors and coefficients for eachfold. By averaging predictions from the models in the four folds, an estimation of the overall modelperformance is obtained. The resulting model exhibits high efficiency, with remarkably low errorsreflected in the values of R, R2, R2ADJ, RMSE, and EPM, which are reported as 0.9979, 0.9958, 0.9956,41.2639, and 3.1061, respectively. This study reveals a compelling non-linear correlation betweenphysico-chemical water attributes and the content of dry tailings, indicating the ability to accuratelypredict dry tailing quantities. By employing the proposed methodology to enhance water qualitymodels, it becomes possible to overcome limitations in water quality management and significantlyimprove the precision of predictions regarding critical water parameters.


Publication metadata

Author(s): Tahraoui H, Toumi S, Hassein-Bey AH, Bousselma A, Sid ANEH, Belhadj AE, Triki Z, Kebir M, Amrane A, Zhang J, Assadi AA, Derradji C, Bouguettoucha A, Mouni L

Publication type: Article

Publication status: Published

Journal: Water

Year: 2023

Volume: 15

Issue: 14

Online publication date: 20/07/2023

Acceptance date: 18/07/2023

Date deposited: 10/08/2023

ISSN (electronic): 2073-4441

Publisher: MDPI

URL: https://doi.org/10.3390/w15142631

DOI: 10.3390/w15142631


Altmetrics

Altmetrics provided by Altmetric


Share