4.6 Article

APPROPRIATE Life Cycle Assessment: A PROcess-Specific, PRedictive Impact AssessmenT Method for Emerging Chemical Processes

期刊

出版社

AMER CHEMICAL SOC
DOI: 10.1021/acssuschemeng.2c07682

关键词

Graph neural networks; Latent space; Autoencoder; Gaussian process regression; Automatizedflowsheeting

向作者/读者索取更多资源

A sustainable chemical industry needs to quantify its emissions and resource consumption by life cycle assessment (LCA), but detailed mass and energy balances are usually not available at early process development stages. To address this issue, a fully automated, predictive LCA framework (APPROPRIATE) based on Gaussian Process Regression is introduced, which is applicable at Technology Readiness Level 2. By employing an encoder-decoder network combined with transfer learning, the framework achieves a condensed molecular descriptor as a latent representation to overcome limited LCA data availability. The proposed framework also integrates process descriptors, such as the stoichiometric sum of the reactants' impacts, to distinguish between process alternatives and incorporate changes in the background systems. Compared to state-of-the-art predictive LCA approaches, the APPROPRIATE framework shows increased prediction accuracy, especially in terms of the global warming impact.
A sustainable chemicalindustry needs to quantify its emissionsand resource consumption by life cycle assessment (LCA). However,LCA requires detailed mass and energy balances, which are usuallynot available at early process development stages. Here, we introducea framework (A PROcess-specific, PRedictive impact AssessmenT method for Emerging chemical processes, APPROPRIATE) to provide a fullyautomated, predictive LCA framework for the early phases of processdevelopment. Based on Gaussian Process Regression, the framework isalready applicable at Technology Readiness Level 2. To overcome thelimited LCA data availability, we employ an encoder-decodernetwork in combination with transfer learning to achieve a latentrepresentation as a condensed molecular descriptor. We further proposeto integrate not only molecular but also process descriptors, e.g.,the stoichiometric sum of the reactants' impacts. Thereby,we can distinguish between process alternatives and incorporate changesin the background systems. The framework is compared to state-of-the-artpredictive LCA approaches and shows increased prediction accuracyin terms of the coefficient of determination of R (2) = 0.61 for the global warming impact compared to an R (2) = 0.3 in former studies. Highly relevant featuresare the stoichiometric sum of the reactants' impacts and thecondensed molecular descriptors. APPROPRIATE supports decision makingin early process development stages by allowing the distinction betweenprocess alternatives and quantifying predictions' uncertainty. The APPROPRIATE framework enables theprocess-specific predictionof environmental impacts by combining machine learning with processshort cuts.

作者

我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。

评论

主要评分

4.6
评分不足

次要评分

新颖性
-
重要性
-
科学严谨性
-
评价这篇论文

推荐

暂无数据
暂无数据