Cited 0 time in
Advanced deep learning-based hybrid framework for predicting reaction rate constants in oxidation systems with char catalysts synthesized via pyrolysis
| DC Field | Value | Language |
|---|---|---|
| dc.contributor.author | Shin, Yong-Uk | - |
| dc.contributor.author | Kwon, Gihoon | - |
| dc.contributor.author | Song, Hocheol | - |
| dc.date.accessioned | 2026-01-14T06:30:16Z | - |
| dc.date.available | 2026-01-14T06:30:16Z | - |
| dc.date.issued | 2025-11 | - |
| dc.identifier.issn | 2214-7144 | - |
| dc.identifier.issn | 2214-7144 | - |
| dc.identifier.uri | https://scholarworks.bwise.kr/hanyang/handle/2021.sw.hanyang/210316 | - |
| dc.description.abstract | Carbon composites derived from the pyrolysis of waste materials have recently been proposed as a new media for advanced oxidation processes (AOP). These materials can address the limitations of conventional AOPs that rely on costly noble metal catalysts. By valorizing waste resources, this new approach enables the development and application of high-performance catalysts for environmental remediation. In this study, we developed a multi-input deep learning model to establish optimal operational strategies for char-based catalysts in AOP applications. Model was constructed by integrating AOP experimental parameters and char characterization data to systemically identify the most effective predictive algorithm. The results demonstrated that the artificial neural network (ANN) model resulted in limited predictive capability when the parameters involved in the catalysts production were excluded (R2 = 0.72, MAE = 0.102). In contrast, incorporating those data markedly improved model performance (R2 = 0.86, MAE = 0.051), increasing the coefficient of determination (R2) value. Notably, the multi-modal approach combining an ANN with a one-dimensional convolutional neural network (1D-CNN) further improved predictive accuracy by integrating additional physicochemical property data of the produced catalysts, achieving R2 = 0.99. In addition, shapley additive explanations (SHAP) analysis and two-dimensional model simulations revealed that process parameters including pH, precursor concentration, and pollutant concentration, together with catalyst properties such as BET surface area and XPS-N binding states, play crucial roles in improving predictive performance. Collectively, these findings highlight the potential of hybrid deep learning architectures as robust tools for predicting and optimizing reaction mechanisms in AOPs employing pyrolysis-derived catalysts. | - |
| dc.format.extent | 10 | - |
| dc.language | 영어 | - |
| dc.language.iso | ENG | - |
| dc.publisher | Elsevier Ltd | - |
| dc.title | Advanced deep learning-based hybrid framework for predicting reaction rate constants in oxidation systems with char catalysts synthesized via pyrolysis | - |
| dc.type | Article | - |
| dc.publisher.location | 네델란드 | - |
| dc.identifier.doi | 10.1016/j.jwpe.2025.109012 | - |
| dc.identifier.scopusid | 2-s2.0-105020985654 | - |
| dc.identifier.wosid | 001614863600013 | - |
| dc.identifier.bibliographicCitation | Journal of Water Process Engineering, v.79, pp 1 - 10 | - |
| dc.citation.title | Journal of Water Process Engineering | - |
| dc.citation.volume | 79 | - |
| dc.citation.startPage | 1 | - |
| dc.citation.endPage | 10 | - |
| dc.type.docType | Article | - |
| dc.description.isOpenAccess | N | - |
| dc.description.journalRegisteredClass | scie | - |
| dc.description.journalRegisteredClass | scopus | - |
| dc.relation.journalResearchArea | Engineering | - |
| dc.relation.journalResearchArea | Water Resources | - |
| dc.relation.journalWebOfScienceCategory | Engineering, Environmental | - |
| dc.relation.journalWebOfScienceCategory | Engineering, Chemical | - |
| dc.relation.journalWebOfScienceCategory | Water Resources | - |
| dc.subject.keywordPlus | ENERGY | - |
| dc.subject.keywordPlus | TECHNOLOGY | - |
| dc.subject.keywordAuthor | Pyrolysis-based char catalysts | - |
| dc.subject.keywordAuthor | Azo dye | - |
| dc.subject.keywordAuthor | Artificial neural network (ANN) | - |
| dc.subject.keywordAuthor | Convolutional neural network (CNN) | - |
| dc.subject.keywordAuthor | Multi-modal model | - |
| dc.identifier.url | https://www.sciencedirect.com/science/article/pii/S2214714425020859?via%3Dihub | - |
Items in ScholarWorks are protected by copyright, with all rights reserved, unless otherwise indicated.
222, Wangsimni-ro, Seongdong-gu, Seoul, 04763, Korea+82-2-2220-1366
COPYRIGHT © 2024 HANYANG UNIVERSITY.
Certain data included herein are derived from the © Web of Science of Clarivate Analytics. All rights reserved.
You may not copy or re-distribute this material in whole or in part without the prior written consent of Clarivate Analytics.
