Citation:

Hernandez-Betancur, J., Gerardo J. Ruiz-Mercado, AND M. Martín. Predicting Chemical End-of-Life Scenarios Using Structure-Based Classification Models. ACS Sustainable Chemistry & Engineering. American Chemical Society, Washington, DC, 11(9):3594-3602, (2023). https://doi.org/10.1021/acssuschemeng.2c05662

Impact/Purpose:

Chemicals in commercial products play key roles in the life quality of humankind. But some chemicals need proper management during their life cycle stages (e.g., manufacturing, end-of-life) to avoid harmful effects on human health and the environment. Chemical risk assessment looks to determine those events or exposure scenarios that may result in adverse environmental and human health outcomes by understanding and preventing their causes. Moreover, the amended Toxic Substances Control Act (TSCA) instructs the USEPA to conduct risk evaluations of existing high-priority chemicals. Therefore, estimating comprehensive data about the conditions of use (e.g., recycling, disposal) of chemicals is a crucial step in risk assessment.This product describes a computational framework based on data-driven and machine learning (ML) models to predict chemical releases in end-of-life (EoL) scenarios. The framework output features are potential EoL activities and the amount of chemical transfers allocated to such activities. Also, this product incorporates a comprehensive EoL database created from different domestic and international regulatory publicly accessible database systems.These product models and their results enable existing foundations and practices from generic scenario studies to a broader set of chemicals at their EoL stage. Also, the results can be used as probabilistic solutions for new scenarios. This product supports chemical prioritization activities related to the TSCA risk assessment program by assisting stakeholders in determining if chemical products at their EoL stage meet environmental regulations or need redesign before going into the market. Thus, this contribution aids stakeholders in determining if chemical products at their EoL stage meet environmental regulations or need redesign before going into the market.  

Description:

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.

URLs/Downloads:

Record Details: