Estimate ecotoxicity characterization factors for chemicals in life cycle assessment using machine learning models
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...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2020-02-01
|
| Series: | Environment International |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S0160412019314412 |
| _version_ | 1818277662723932160 |
|---|---|
| author | Ping Hou Olivier Jolliet Ji Zhu Ming Xu |
| author_facet | Ping Hou Olivier Jolliet Ji Zhu Ming Xu |
| author_sort | Ping Hou |
| collection | DOAJ |
| description | 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: Life cycle assessment, Ecotoxicity, Hazardous concentration, Characterization factors, Machine learning, Quantitative structure-activity relationship (QSAR) |
| first_indexed | 2024-12-12T23:05:07Z |
| format | Article |
| id | doaj.art-1a356b7172794545801401a496ffb790 |
| institution | Directory Open Access Journal |
| issn | 0160-4120 |
| language | English |
| last_indexed | 2024-12-12T23:05:07Z |
| publishDate | 2020-02-01 |
| publisher | Elsevier |
| record_format | Article |
| series | Environment International |
| spelling | doaj.art-1a356b7172794545801401a496ffb7902022-12-22T00:08:44ZengElsevierEnvironment International0160-41202020-02-01135Estimate ecotoxicity characterization factors for chemicals in life cycle assessment using machine learning modelsPing Hou0Olivier Jolliet1Ji Zhu2Ming Xu3School for Environment and Sustainability, University of Michigan, Ann Arbor, MI, USA; Michigan Institute for Computational Discovery & Engineering, University of Michigan, Ann Arbor, MI, USAEnvironmental Health Sciences, School of Public Heath, University of Michigan, Ann Arbor, MI, USADepartment of Statistics, University of Michigan, Ann Arbor, MI, USASchool for Environment and Sustainability, University of Michigan, Ann Arbor, MI, USA; Department of Civil and Environmental Engineering, University of Michigan, Ann Arbor, MI, USA; Corresponding author at: 440 Church St., Ann Arbor, MI 48109-1041, USA.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: Life cycle assessment, Ecotoxicity, Hazardous concentration, Characterization factors, Machine learning, Quantitative structure-activity relationship (QSAR)http://www.sciencedirect.com/science/article/pii/S0160412019314412 |
| spellingShingle | Ping Hou Olivier Jolliet Ji Zhu Ming Xu Estimate ecotoxicity characterization factors for chemicals in life cycle assessment using machine learning models Environment International |
| title | Estimate ecotoxicity characterization factors for chemicals in life cycle assessment using machine learning models |
| title_full | Estimate ecotoxicity characterization factors for chemicals in life cycle assessment using machine learning models |
| title_fullStr | Estimate ecotoxicity characterization factors for chemicals in life cycle assessment using machine learning models |
| title_full_unstemmed | Estimate ecotoxicity characterization factors for chemicals in life cycle assessment using machine learning models |
| title_short | Estimate ecotoxicity characterization factors for chemicals in life cycle assessment using machine learning models |
| title_sort | estimate ecotoxicity characterization factors for chemicals in life cycle assessment using machine learning models |
| url | http://www.sciencedirect.com/science/article/pii/S0160412019314412 |
| work_keys_str_mv | AT pinghou estimateecotoxicitycharacterizationfactorsforchemicalsinlifecycleassessmentusingmachinelearningmodels AT olivierjolliet estimateecotoxicitycharacterizationfactorsforchemicalsinlifecycleassessmentusingmachinelearningmodels AT jizhu estimateecotoxicitycharacterizationfactorsforchemicalsinlifecycleassessmentusingmachinelearningmodels AT mingxu estimateecotoxicitycharacterizationfactorsforchemicalsinlifecycleassessmentusingmachinelearningmodels |