Rapid Life-Cycle Impact Screening Using Artificial Neural Networks
| Autor: | Runsheng Song, Sangwon Suh, Arturo A. Keller |
|---|---|
| Jazyk: | angličtina |
| Rok vydání: | 2017 |
| Předmět: |
Engineering
Neural Networks media_common.quotation_subject 010501 environmental sciences Machine learning computer.software_genre Global Warming 01 natural sciences Computer Application domain Molecular descriptor Animals Humans Environmental Chemistry Quality (business) Screening tool Ecosystem Reliability (statistics) Simulation 0105 earth and related environmental sciences media_common Principal Component Analysis Artificial neural network 010405 organic chemistry business.industry Global warming Reproducibility of Results General Chemistry 0104 chemical sciences Principal component analysis Environmental Pollutants Neural Networks Computer Artificial intelligence business computer Environmental Sciences |
| Zdroj: | Song, R; Keller, AA; & Suh, S. (2017). Rapid Life-Cycle Impact Screening Using Artificial Neural Networks. Environmental Science and Technology, 51(18), 10777-10785. doi: 10.1021/acs.est.7b02862. UC Santa Barbara: Retrieved from: http://www.escholarship.org/uc/item/7tr8n61t Environmental science & technology, vol 51, iss 18 |
| DOI: | 10.1021/acs.est.7b02862. |
| Popis: | © 2017 American Chemical Society. The number of chemicals in the market is rapidly increasing, while our understanding of the life-cycle impacts of these chemicals lags considerably. To address this, we developed deep artificial neural network (ANN) models to estimate life-cycle impacts of chemicals. Using molecular structure information, we trained multilayer ANNs for life-cycle impacts of chemicals using six impact categories, including cumulative energy demand, global warming (IPCC 2007), acidification (TRACI), human health (Impact2000+), ecosystem quality (Impact2000+), and eco-indicator 99 (I,I, total). The application domain (AD) of the model was estimated for each impact category within which the model exhibits higher reliability. We also tested three approaches for selecting molecular descriptors and identified the principal component analysis (PCA) as the best approach. The predictions for acidification, human health, and the eco-indicator 99 model showed relatively higher performance with R2values of 0.73, 0.71, and 0.87, respectively, while the global warming model had a lower R2of 0.48. This study indicates that ANN models can serve as an initial screening tool for estimating life-cycle impacts of chemicals for certain impact categories in the absence of more reliable information. Our analysis also highlights the importance of understanding ADs for interpreting the ANN results. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|