DC Field | Value | Language |
---|---|---|
dc.contributor.author | Lin, Subin | ko |
dc.contributor.author | Kim, Jiwoong | ko |
dc.contributor.author | Hua, Chuanbo | ko |
dc.contributor.author | Park, Mi-Hyun | ko |
dc.contributor.author | Kang, Seoktae | ko |
dc.date.accessioned | 2023-02-17T08:00:15Z | - |
dc.date.available | 2023-02-17T08:00:15Z | - |
dc.date.created | 2023-02-17 | - |
dc.date.created | 2023-02-17 | - |
dc.date.created | 2023-02-17 | - |
dc.date.issued | 2023-04 | - |
dc.identifier.citation | WATER RESEARCH, v.232 | - |
dc.identifier.issn | 0043-1354 | - |
dc.identifier.uri | http://hdl.handle.net/10203/305200 | - |
dc.description.abstract | Determination of coagulant dosage in water treatment is a time-consuming process involving nonlinear data relationships and numerous factors. This study provides a deep learning approach to determine coagulant dosage and/or the settled water turbidity using long-term data between 2011 and 2021 to include the effect of various weather conditions. A graph attention multivariate time series forecasting (GAMTF) model was developed to determine coagulant dosage and was compared with conventional machine learning and deep learning models. The GAMTF model (R2 = 0.94, RMSE = 3.55) outperformed the other models (R2 = 0.63 - 0.89, RMSE = 4.80 - 38.98), and successfully predicted both coagulant dosage and settled water turbidity simultaneously. The GAMTF model improved the prediction accuracy by considering the hidden interrelationships between features and the past states of features. The results demonstrate the first successful application of multivariate time series deep learning model, especially, a state-of-the-art graph attention-based model, using long-term data for decision-support systems in water treatment processes. © 2023 | - |
dc.language | English | - |
dc.publisher | PERGAMON-ELSEVIER SCIENCE LTD | - |
dc.title | Coagulant dosage determination using deep learning-based graph attention multivariate time series forecasting model | - |
dc.type | Article | - |
dc.identifier.wosid | 000963319600001 | - |
dc.identifier.scopusid | 2-s2.0-85147596230 | - |
dc.type.rims | ART | - |
dc.citation.volume | 232 | - |
dc.citation.publicationname | WATER RESEARCH | - |
dc.identifier.doi | 10.1016/j.watres.2023.119665 | - |
dc.contributor.localauthor | Kang, Seoktae | - |
dc.contributor.nonIdAuthor | Lin, Subin | - |
dc.description.isOpenAccess | N | - |
dc.type.journalArticle | Article | - |
dc.subject.keywordAuthor | Coagulant | - |
dc.subject.keywordAuthor | Prediction model | - |
dc.subject.keywordAuthor | Deep learning | - |
dc.subject.keywordAuthor | Attention -based mechanism | - |
dc.subject.keywordAuthor | Time series | - |
dc.subject.keywordAuthor | Big data | - |
dc.subject.keywordPlus | ARTIFICIAL NEURAL-NETWORKS | - |
dc.subject.keywordPlus | RANDOM FOREST | - |
dc.subject.keywordPlus | PREDICTION | - |
dc.subject.keywordPlus | TURBIDITY | - |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.