Zobia Khatoon , Suiliang Huang , Adeel Ahmed Abbasi
{"title":"Machine learning-driven predictive frameworks for optimizing chemical strategies in Microcystis aeruginosa mitigation","authors":"Zobia Khatoon , Suiliang Huang , Adeel Ahmed Abbasi","doi":"10.1016/j.jwpe.2025.107235","DOIUrl":null,"url":null,"abstract":"<div><div>Traditional chemical approaches to control <em>Microcystis aeruginosa</em> often struggle to define optimal treatment conditions resulting in inconsistent outcomes. Previous research largely depended on single-source data, significantly compromising generalizability of these findings. These studies overlooked comparisons among various machine learning models. To address these limitations, we integrated experimental data from multiple sources for the first time and applied various machine learning models to predict removal efficiency. This research enhances chemical treatment efficiency through data driven optimization of critical factors such as time and dosage required for effective <em>Microcystis aeruginosa</em> removal, removing uncertainties in traditional experimental studies. Another key point of novelty is to extract key features influencing output, which have not been quantitatively explored in earlier studies. The study observed variability in removal time, dosage and efficiency rates, with an average removal efficiency of 50.03 %. Random Forest Regressor and Bagging Regressor were recommended as optimum models, demonstrating their effectiveness in accurately predicting removal efficiency based on the given dataset. Our findings indicate that removal efficiency was most sensitive during initial 0–500 min of treatment and at dosages below 250 mg/L. The optimal dosage range of 0–250 mg/L was identified, with significant drops in removal efficiency beyond this range, indicating potential risks of reduced effectiveness and adverse effects at higher concentrations. The study also underscores the potential of photocatalysts, heterogeneous catalysts, and the chemical Bi<sub>2</sub>O<sub>3</sub> in optimizing removal efficiency. This predictive framework provides decision-makers with essential tools for effectively predicting the efficiency of chemical mitigation strategies against harmful algal blooms.</div></div>","PeriodicalId":17528,"journal":{"name":"Journal of water process engineering","volume":"71 ","pages":"Article 107235"},"PeriodicalIF":6.3000,"publicationDate":"2025-02-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Journal of water process engineering","FirstCategoryId":"5","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S2214714425003071","RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"ENGINEERING, CHEMICAL","Score":null,"Total":0}
引用次数: 0
Abstract
Traditional chemical approaches to control Microcystis aeruginosa often struggle to define optimal treatment conditions resulting in inconsistent outcomes. Previous research largely depended on single-source data, significantly compromising generalizability of these findings. These studies overlooked comparisons among various machine learning models. To address these limitations, we integrated experimental data from multiple sources for the first time and applied various machine learning models to predict removal efficiency. This research enhances chemical treatment efficiency through data driven optimization of critical factors such as time and dosage required for effective Microcystis aeruginosa removal, removing uncertainties in traditional experimental studies. Another key point of novelty is to extract key features influencing output, which have not been quantitatively explored in earlier studies. The study observed variability in removal time, dosage and efficiency rates, with an average removal efficiency of 50.03 %. Random Forest Regressor and Bagging Regressor were recommended as optimum models, demonstrating their effectiveness in accurately predicting removal efficiency based on the given dataset. Our findings indicate that removal efficiency was most sensitive during initial 0–500 min of treatment and at dosages below 250 mg/L. The optimal dosage range of 0–250 mg/L was identified, with significant drops in removal efficiency beyond this range, indicating potential risks of reduced effectiveness and adverse effects at higher concentrations. The study also underscores the potential of photocatalysts, heterogeneous catalysts, and the chemical Bi2O3 in optimizing removal efficiency. This predictive framework provides decision-makers with essential tools for effectively predicting the efficiency of chemical mitigation strategies against harmful algal blooms.
期刊介绍:
The Journal of Water Process Engineering aims to publish refereed, high-quality research papers with significant novelty and impact in all areas of the engineering of water and wastewater processing . Papers on advanced and novel treatment processes and technologies are particularly welcome. The Journal considers papers in areas such as nanotechnology and biotechnology applications in water, novel oxidation and separation processes, membrane processes (except those for desalination) , catalytic processes for the removal of water contaminants, sustainable processes, water reuse and recycling, water use and wastewater minimization, integrated/hybrid technology, process modeling of water treatment and novel treatment processes. Submissions on the subject of adsorbents, including standard measurements of adsorption kinetics and equilibrium will only be considered if there is a genuine case for novelty and contribution, for example highly novel, sustainable adsorbents and their use: papers on activated carbon-type materials derived from natural matter, or surfactant-modified clays and related minerals, would not fulfil this criterion. The Journal particularly welcomes contributions involving environmentally, economically and socially sustainable technology for water treatment, including those which are energy-efficient, with minimal or no chemical consumption, and capable of water recycling and reuse that minimizes the direct disposal of wastewater to the aquatic environment. Papers that describe novel ideas for solving issues related to water quality and availability are also welcome, as are those that show the transfer of techniques from other disciplines. The Journal will consider papers dealing with processes for various water matrices including drinking water (except desalination), domestic, urban and industrial wastewaters, in addition to their residues. It is expected that the journal will be of particular relevance to chemical and process engineers working in the field. The Journal welcomes Full Text papers, Short Communications, State-of-the-Art Reviews and Letters to Editors and Case Studies