A data engineering approach for sustainable chemical end-of-life management

Hernández-Betancur, Jose D.; Martı́n, Mariano; Ruiz-Mercado, Gerardo J.

doi:10.1016/j.resconrec.2021.106040

Cited by 8 publications

(14 citation statements)

References 26 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Modoi and Mihai proposed the economy model between e-waste and end-of-life vehicles [39]. Hernandez-Betancur et al [40] suggested a new approach for managing the EOL for the chemical industry. Zuidwijk and Krikke [41] focused on sustainable supply chain (SC) and RLs.…”

Section: Literature Reviewmentioning

confidence: 99%

Designing Sustainable Recovery Network of End‐of‐Life Product during the COVID‐19 Pandemic: A Real and Applied Case Study

Abbasi

Daneshmand-Mehr

Kanafi

2022

Discrete Dynamics in Nature and Society

View full text Add to dashboard Cite

One of the most important aspects of supply chain management (SCM) is the recovery network (RN), which covers all activities associated with return products (such as collection, recovery, repair, recycling, and waste disposal). Our goal in this paper is to provide a new mathematical model of sustainable end-of-life management (SEOLM) during the COVID-19 pandemic for readers. The suggested recovery network model (RNM) can explain the trade-offs between economic (minimizing total costs), environmental (minimizing bad environmental impacts), and social (minimizing bad social impacts) aspects during the pandemic and the great lockdown. A new RN can be designed with a sustainable and hygienic design when taking environmental, economic, and social considerations into account. It proposes guidelines for managers and scholars on how to address recovery network design (RND) challenges during the pandemic through a mathematical article with a sustainable approach. The scalarization approach of a multi-objective mixed-integer programming (MOMIP) problem in this paper is the weighted sum method. The validation of the presented model and the related Pareto frontier has been illustrated by a case study and numerical example. To perform the optimization process, Lingo software is used.

show abstract

Section: Literature Reviewmentioning

confidence: 99%

Designing Sustainable Recovery Network of End‐of‐Life Product during the COVID‐19 Pandemic: A Real and Applied Case Study

Abbasi

Daneshmand-Mehr

Kanafi

2022

Discrete Dynamics in Nature and Society

View full text Add to dashboard Cite

show abstract

“…Hernandez-Betancur et al used data at the pollution abatement unit technology level to perform CFA and allocate chemical flows downstream of the pollution abatement units. Hernandez-Betancur et al combined the above two frameworks , and extended them beyond the EoL management chain boundaries to identify and track recycled chemical flows. Using a Markov random field model, Hernandez-Betancur et al outlined the relationship between the entities through the EoL management chain and recycling loops.…”

Section: Introductionmentioning

confidence: 99%

“…Hernandez-Betancur et al combined the above two frameworks , and extended them beyond the EoL management chain boundaries to identify and track recycled chemical flows. Using a Markov random field model, Hernandez-Betancur et al outlined the relationship between the entities through the EoL management chain and recycling loops. Due to the legal, economic, market, and policy implications, the behavior of the EoL management chain may vary from country to country and year to year .…”

Section: Introductionmentioning

confidence: 99%

“…Due to the legal, economic, market, and policy implications, the behavior of the EoL management chain may vary from country to country and year to year . In addition, to create a database called PRTR_transfers that contains global inventory data of EoL chemical off-site transfers reported by industrial facilities and businesses, Hernandez-Betancur et al expanded the EoL data engineering framework suggested by Hernandez-Betancur et al by incorporating data from siloed (i.e., isolated) and publicly accessible international database systems. Thus, the data engineering frameworks can supply the EoL CFA and life cycle inventory (LCI) data of existing chemicals reported in regulatory primary data sources.…”

Section: Introductionmentioning

confidence: 99%

“…The extensive number of techniques and strategies for ML QSAR modeling makes it a viable alternative for extending the CFA described above to chemicals that are either not reported to regulatory primary data sources or are new to the market. Based on the work developed by Hernandez-Betancur et al, this work utilizes the PRTR_transfers database to develop ML QSAR models for predicting potential EoL activities and identifying EoL exposure scenarios for chemicals found in industrial material transfers to off-site locations for further EoL management. Thus, allocating EoL chemicals flows by the predicted EoL activities and their operating conditions establish potential environmental releases and exposure pathways at the EoL stage .…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Predicting Chemical End-of-Life Scenarios Using Structure-Based Classification Models

Hernández-Betancur

Ruiz-Mercado

Martín

2023

ACS Sustainable Chem. Eng.

Self Cite

View full text Add to dashboard Cite

Analyzing chemicals and their effects on the environment from a life cycle viewpoint can produce a thorough analysis that takes end-of-life (EoL) activities into account. Chemical risk assessment, predicting environmental discharges, and finding EoL paths and exposure scenarios all depend on chemical flow data availability. However, it is challenging to gain access to such data and systematically determine EoL activities and potential chemical exposure scenarios. As a result, this work creates quantitative structure-transfer relationship (QSTR) models for aiding environmental managment decision-making based on chemical structure-based machine learning (ML) models to predict potential industrial EoL activities, chemical flow allocation, environmental releases, and exposure routes. Further multi-label classification methods may improve the predictability of QSTR models according to the ML experiment tracking. The developed QSTR models will assist stakeholders in predicting and comprehending potential EoL management activities and recycling loops, enabling environmental decision-making and EoL exposure assessment for new or existing chemicals in the global marketplace.

show abstract