Modeling and optimization of coagulant dosage in water treatment plants using hybridized random forest model with genetic algorithm optimization

Mohammed Achite (), Saeed Samadianfard (), Nehal Elshaboury () and Milad Sharafi ()
Additional contact information
Mohammed Achite: Hassiba Benbouali University of Chlef
Saeed Samadianfard: University of Tabriz
Nehal Elshaboury: Construction and Project Management Research Institute, Housing and Building National Research Centre
Milad Sharafi: Urmia University

Environment, Development and Sustainability: A Multidisciplinary Approach to the Theory and Practice of Sustainable Development, 2023, vol. 25, issue 10, No 26, 11189-11207

Abstract: Abstract In water treatment plants (WTPs), the most common processes are coagulation and flocculation. Determination of the coagulant dosage is one of the most difficult procedures in the water treatment process, and it is commonly determined using the jar test technique. Given that this approach is time-consuming, expensive, prone to human error, and greatly influenced by raw water quality changes, this research presents a prediction model to make proactive decisions about coagulant doses based on changes in raw water characteristics. The model eliminates the need to employ expensive chemicals for jar testing regularly and allows for rapid response to abrupt changes in water quality. The forecasting model is developed using standalone random forest (RF) and hybridized RF model with genetic algorithm (GA) optimization, namely GA-RF, to simulate coagulant dose in the Sidi Yacoub WTP in Algeria. Different input scenarios are used in the development of the conventional and hybrid models to determine the best input combination. This study establishes the most efficient model for assessing the coagulation process using four evaluation metrics; correlation coefficient (CC), scattered index (SI), Willmott’s index of agreement (WI), and mean absolute percentage error (MAPE). According to the findings, the GA-RF model (CC = 0.975, SI = 0.150, WI = 0.986, and MAPE = 7.9), which accounts for raw water production, turbidity water, conductivity, and suspended materials input parameters, outperforms the other models. The proposed model will help operators to not only reduce costs and time spent performing experimental jar testing but also to anticipate optimum coagulant dose and project water quality under real-world conditions.

Keywords: Modeling and optimization; Coagulant dosage; Turbidity removal; Water treatment; Random forest; Genetic algorithm (search for similar items in EconPapers)
Date: 2023
References: View references in EconPapers View complete reference list from CitEc
Citations:

Downloads: (external link)
http://link.springer.com/10.1007/s10668-022-02523-z Abstract (text/html)
Access to the full text of the articles in this series is restricted.

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:spr:endesu:v:25:y:2023:i:10:d:10.1007_s10668-022-02523-z

Ordering information: This journal article can be ordered from
http://www.springer.com/economics/journal/10668

DOI: 10.1007/s10668-022-02523-z

Access Statistics for this article

Environment, Development and Sustainability: A Multidisciplinary Approach to the Theory and Practice of Sustainable Development is currently edited by Luc Hens

More articles in Environment, Development and Sustainability: A Multidisciplinary Approach to the Theory and Practice of Sustainable Development from Springer
Bibliographic data for series maintained by Sonal Shukla () and Springer Nature Abstracting and Indexing ().