EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Machine Learning-Based Prediction of Coagulant Dosing in Drinking Water Treatment Plants Using Polynomial Regression with Lasso Regularization

Jusuk An, Joonhong Park, Seungjae Yeon, Changseog Oh, Bokjin Lee, Woosik Jung, Jeongmin Yun, Hyun Je Oh

Processes · 26.11.2025 · 13 (12) · 3829

DOI: 10.3390/pr13123829 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Processes, online erschienen am 26.11.2025. Verfasst von Jusuk An und 7 weiteren Autor:innen. Die Arbeit wurde bisher 9-mal zitiert (Crossref) und nennt 23 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Korea Ministry of Environment, Ministry of Science and ICT.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Coagulation is a critical unit process in drinking water treatment plants (DWTPs), where accurate dosing of coagulants such as polyaluminum chloride (PAC) and polyaluminum hydroxide chloride silicate (PACS) directly determines turbidity removal and operational stability. However, nonlinear interactions among water-quality variables complicate dosage prediction, and jar tests or operator heuristics cannot support real-time control. This study presents a scientifically interpretable and operationally transferable framework based on polynomial multiple linear regression (PMLR) with Lasso regularization, which was specifically developed for full-scale DWTP environments. While conventional PMLR rapidly overfits beyond polynomial degrees of 4–5, the Lasso-regularized model maintained stable generalization even at a degree of 10 by automatically pruning redundant terms and suppressing multicollinearity, thereby minimizing the need for manual hyperparameter tuning. Using 8303 hourly operational records from a full-scale DWTP in Korea, the Lasso-PMLR achieved R2 = 0.951, RMSE = 0.120, and MAPE = 7.02%, outperforming traditional linear regression (R2 = 0.896; MAPE = 8.64%). This proportional stability across increasing polynomial degrees, demonstrated directly using long-term real-world data, is particularly valuable for practical deployment because it ensures robustness without complex model-selection procedures. The transparent coefficient structure enables operators—who typically rely on jar tests—to understand and adjust dosing behavior, offering a field-ready and interpretable alternative to black-box models and supporting more efficient coagulant use, reduced sludge production, and sustainable automation in DWTP operation.

Förderung

  • Korea Ministry of Environment
  • Ministry of Science and ICT

Zitieren

APA

An, J., Park, J., Yeon, S., Oh, C., Lee, B., Jung, W., Yun, J., & Oh, H. J. (2025). Machine Learning-Based Prediction of Coagulant Dosing in Drinking Water Treatment Plants Using Polynomial Regression with Lasso Regularization. Processes, 13(12), 3829. https://doi.org/10.3390/pr13123829

Vancouver

An J, Park J, Yeon S, Oh C, Lee B, Jung W, et al. Machine Learning-Based Prediction of Coagulant Dosing in Drinking Water Treatment Plants Using Polynomial Regression with Lasso Regularization. Processes. 2025;13(12):3829. doi:10.3390/pr13123829

BibTeX
@article{An2025,
  author = {An, Jusuk and Park, Joonhong and Yeon, Seungjae and Oh, Changseog and Lee, Bokjin and Jung, Woosik and Yun, Jeongmin and Oh, Hyun Je},
  title = {Machine Learning-Based Prediction of Coagulant Dosing in Drinking Water Treatment Plants Using Polynomial Regression with Lasso Regularization},
  journal = {Processes},
  year = {2025},
  volume = {13},
  number = {12},
  pages = {3829},
  doi = {10.3390/pr13123829}
}
Kostenlos starten →