Ensemble learning-driven optimization of coagulant dosing for drinking water treatment plants using a scalable framework for smart and sustainable process control
Environmental Research · 2026-01 · 288 · 123229
DOI: 10.1016/j.envres.2025.123229 ↗Kurz gefasst
Fachartikel in der Zeitschrift Environmental Research, 2026-01. Verfasst von Abderzak Moussouni und 8 weiteren Autor:innen. Beteiligte Einrichtung: Abdelhafid Boussouf University Center Mila, Department of Civil Engineering & Hydraulics, Environmental Engineering and Technology, LEGHYD Laboratory…. Hauptthemen laut MEDLINE: Water Purification, Machine Learning, Drinking Water. Die Arbeit wurde bisher 9-mal zitiert (Crossref) und nennt 42 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
Coagulation and flocculation remain foundational in drinking water treatment plants (DWTPs) worldwide. Determining optimal coagulant dosage remains a persistent challenge due to raw water variability and reliance on conventional jar tests, labor-intensive, time-consuming methods, and being prone to operational inefficiencies. This study introduces a novel machine learning (ML) based framework leveraging tree-based ensemble models to predict coagulant dosing with high precision, offering a transformative alternative to empirical approaches. Seven algorithms, Random Forest (RF), ExtraTree, REPTree, and M5P (M5 Prime) Tree, RF-Extra Tree, RF-REPTree, RF-M5P Tree, were systematically evaluated using real-world operational data, incorporating five key water quality parameters: turbidity (Tb), Electric conductivity (EC), pH, temperature, and dissolved oxygen (DO). The performance of the proposed models was assessed based on Root Mean Square Error (RMSE), Nash-Sutcliffe Efficiency (NSE), Kling-Gupta Efficiency (KGE), Willmott's index of agreement (WI), and the coefficient of determination (R2) values. Among the models, the RF-Extra Tree model exhibited superior predictability (RMSE = 0.515, MAE = 0.329, NSE = 0.9850, WI = 0.996, KGE = 0.969 and R2 = 0.985), significantly outperforming traditional heuristics and other models. The RF algorithm also demonstrated robust results (RMSE = 0.807, MAE = 0.586, NSE = 0.963, WI = 0.99, KGE = 0.899, and R2 = 0.963), highlighting its potential for deployment in dynamic, data-driven treatment environments. This research not only underscores the capacity of ensemble learning to model the complex, non-linear relationships inherent in water treatment but also provides a scalable decision-support tool capable of enhancing treatment consistency, reducing chemical use, and optimizing operational efficiency across diverse geographic and climatic conditions. The proposed methodology holds global relevance for advancing smart water treatment infrastructure, offering both environmental and economic benefits to utilities and stakeholders.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Substanzen
Autor:innen und Institutionen
- Abdelhafid Boussouf University Center Mila, Department of Civil Engineering & Hydraulics, Environmental Engineering and Technology, LEGHYD Laboratory, 43000, Mila, Algeria. Electronic address: a.moussouni@centre-univ-mi…
- Centre de Recherche en Aménagement du Territoire (CRAT), Campus Zouaghi Slimane, Route de Ain el Bey, 25000 Constantine, Algeria. Electronic address: amer.zeghmar@crat.dz.
- University of Mustapha Ben Boulaïd Batna 2, 53 Constantine Road, Fesdis, 05078, Algeria. Electronic address: l.benchaiba@univ-batna2.dz.
- Faculty of Civil Engineering, LEGHYD Laboratory, University of Science and Technology Houari Boumediene, PB 32 El-Alia. 16111, Algiers, Algeria. Electronic address: amaaliou@usthb.dz.
- Biotechnical Faculty, University of Montenegro, Podgorica, 81000, Montenegro; Geo Eco- Eco Agro (GEA), 20 Novaka Miloševa, Podgorica, 81000, Montenegro. Electronic address: velibor.spalevic@gmail.com.
- Machine Minds Academy, 12 Wulfstan Way, Cambridge, CB18QH, United Kingdom; Geo Eco- Eco Agro (GEA), 20 Novaka Miloševa, Podgorica, 81000, Montenegro. Electronic address: lizny96@gmail.com.
Zitieren
APA
Moussouni, A., Zeghmar, A., Benchaiba, L., Maaliou, A., Spalevic, V., Jaufer, L., Ksibi, M., Helfer, F., & Kader, S. (2026). Ensemble learning-driven optimization of coagulant dosing for drinking water treatment plants using a scalable framework for smart and sustainable process control. Environmental Research, 288, 123229. https://doi.org/10.1016/j.envres.2025.123229
Vancouver
Moussouni A, Zeghmar A, Benchaiba L, Maaliou A, Spalevic V, Jaufer L, et al. Ensemble learning-driven optimization of coagulant dosing for drinking water treatment plants using a scalable framework for smart and sustainable process control. Environmental Research. 2026;288:123229. doi:10.1016/j.envres.2025.123229
BibTeX
@article{Moussouni2026,
author = {Moussouni, Abderzak and Zeghmar, Amer and Benchaiba, Leila and Maaliou, Aziz and Spalevic, Velibor and Jaufer, Lizny and Ksibi, Mohamed and Helfer, Fernanda and Kader, Shuraik},
title = {Ensemble learning-driven optimization of coagulant dosing for drinking water treatment plants using a scalable framework for smart and sustainable process control},
journal = {Environmental Research},
year = {2026},
volume = {288},
pages = {123229},
doi = {10.1016/j.envres.2025.123229}
}
EUVIMED