Estimate ecotoxicity characterization factors for chemicals in life cycle assessment using machine learning models.

Affiliation

School for Environment and Sustainability, University of Michigan, Ann Arbor, MI, USA; Department of Civil and Environmental Engineering, University of Michigan, Ann Arbor, MI, USA. Electronic address: [Email]

Abstract

In life cycle assessment, characterization factors are used to convert the amount of the chemicals and other pollutants generated in a product's life cycle to the standard unit of an impact category, such as ecotoxicity. However, as a widely used impact assessment method, USEtox (version 2.11) only has ecotoxicity characterization factors for a small portion of chemicals due to the lack of laboratory experiment data. Here we develop machine learning models to estimate ecotoxicity hazardous concentrations 50% (HC50) in USEtox to calculate characterization factors for chemicals based on their physical-chemical properties in EPA's CompTox Chemical Dashborad and the classification of their mode of action. The model is validated by ten randomly selected test sets that are not used for training. The results show that the random forest model has the best predictive performance. The average root mean squared error of the estimated HC50 on the test sets is 0.761. The average coefficient of determination (R2) on the test set is 0.630, meaning 63% of the variability of HC50 in USEtox can be explained by the predicted HC50 from the random forest model. Our model outperforms a traditional quantitative structure-activity relationship (QSAR) model (ECOSAR) and linear regression models. We also provide estimates of missing ecotoxicity characterization factors for 552 chemicals in USEtox using the validated random forest model.

Keywords

Characterization factors,Ecotoxicity,Hazardous concentration,Life cycle assessment,Machine learning,Quantitative structure-activity relationship (QSAR),

OUR Recent Articles