Machine learning framework for modeling flocculation kinetics using non-intrusive dynamic image analysis

Registro completo de metadados
MetadadosDescriçãoIdioma
Autor(es): dc.contributorUniversidade Estadual Paulista (UNESP)-
Autor(es): dc.contributorFederal University of Agriculture-
Autor(es): dc.contributorUniversity of Birmingham-
Autor(es): dc.creatorBankole, Abayomi O.-
Autor(es): dc.creatorMoruzzi, Rodrigo-
Autor(es): dc.creatorNegri, Rogerio G.-
Autor(es): dc.creatorBressane, Adriano-
Autor(es): dc.creatorReis, Adriano G.-
Autor(es): dc.creatorSharifi, Soroosh-
Autor(es): dc.creatorJames, Abraham O.-
Autor(es): dc.creatorBankole, Afolashade R.-
Data de aceite: dc.date.accessioned2025-08-21T19:38:57Z-
Data de disponibilização: dc.date.available2025-08-21T19:38:57Z-
Data de envio: dc.date.issued2025-04-29-
Data de envio: dc.date.issued2024-01-14-
Fonte completa do material: dc.identifierhttp://dx.doi.org/10.1016/j.scitotenv.2023.168452-
Fonte completa do material: dc.identifierhttps://hdl.handle.net/11449/306513-
Fonte: dc.identifier.urihttp://educapes.capes.gov.br/handle/11449/306513-
Descrição: dc.descriptionThe implementation of a machine learning (ML) model to improve both the effectiveness and sustainability of the water treatment system is a significant challenge in the water sector, with the optimization of flocculation processes being a major setback. The objective of this study was to develop a ML model for predicting flocs evolution of the flocculation process in water treatment. Furthermore, we have devised a framework for its potential adoption in large-scale water treatment. Therefore, the paper can be split into two parts. In the first one, flocculation evolution has been studied from an experimental setup, using a non-intrusive image acquisition method. Subsequently, the ML framework has been implemented. Batch assay data of two velocity gradients (Gf 20 and 60 s−1) and flocculation time of three hours were partitioned into five groups for flocs length range 0.27–3.5 mm and upscaled using linear method. Multilayer Perceptron (MLP) and Long-Short Term Memory (LSTM) models, and traditional time series model, Auto Regressive Integrated Moving Average (ARIMA) were explored to predict floc length evolution data. The experiments illustrate the kinetics of flocculation, where the initial stage is characterized by a rapid floc growth followed by a plateau during which floc length fluctuates within a narrow range. Results demonstrate that ML is sensitive to flocculation; however, the model should be selected with care. ARIMA model is not suitable for predicting number of flocs with negative test accuracy (R2). In contrast, MLP recorded R2 of 0.86–1.0 for training and 0.92–1.0 for testing, across Gf 20 s−1 and Gf 60 s−1. LSTM model has the best prediction R2 of 0.92–1.00 for Gf 20 s−1 and accurately predicts the number of flocs across all groups and Gfs. Our study has proven that the developed framework could be replicated for water treatment modeling and promotes the application of smart technology in water treatment.-
Descrição: dc.descriptionCivil and Environmental Engineering Department Faculty of Engineering Sao Paulo State University-
Descrição: dc.descriptionWater Resources Management and Agrometeorology Department COLERM Federal University of Agriculture-
Descrição: dc.descriptionEnvironmental Engineering Department Institute of Science and Technology Sao Paulo State University-
Descrição: dc.descriptionDepartment of Civil Engineering Faculty of Engineering University of Birmingham-
Descrição: dc.descriptionEnvironmental Management and Toxicology Department COLERM Federal University of Agriculture-
Descrição: dc.descriptionCivil and Environmental Engineering Department Faculty of Engineering Sao Paulo State University-
Descrição: dc.descriptionEnvironmental Engineering Department Institute of Science and Technology Sao Paulo State University-
Idioma: dc.languageen-
Relação: dc.relationScience of the Total Environment-
???dc.source???: dc.sourceScopus-
Palavras-chave: dc.subjectFlocculation-
Palavras-chave: dc.subjectFlocs length evolution-
Palavras-chave: dc.subjectMachine learning-
Palavras-chave: dc.subjectNeural network-
Palavras-chave: dc.subjectSmart water treatment-
Título: dc.titleMachine learning framework for modeling flocculation kinetics using non-intrusive dynamic image analysis-
Tipo de arquivo: dc.typelivro digital-
Aparece nas coleções:Repositório Institucional - Unesp

Não existem arquivos associados a este item.