An Overview of Lifecycle Assessment of Nanocellulose Using Machine Learning Techniques
Deepa Sreedev, Rubie Mavelil Sam, Taniya Rose Abraham, Nandakumar Kalarikkal, Subila Kurukkal BalakrishnanLife cycle assessment (LCA) is a widely recognised process for systematically evaluating the environmental impacts of human activities. Machine learning (ML) has been applied in the life cycle assessment (LCA) of nanocellulose to estimate environmental impact characterisation factors and conduct sensitivity analyses. Surrogate LCAs have been developed using ML, which have enabled the prediction of nanocellulose full life cycle environmental impacts on the basis of design-phase product characteristics. Besides LCA, ML algorithms have also been utilised in ecosystem informatics, data cleaning, system optimisation, and predicting system output flows or performance. Given these uses and capabilities of ML, there are opportunities to use ML in cleaning data for life cycle inventories (LCI). ML can also be used to estimate flow data for unit processes and to improve the quality and quantity of data used to determine impact characterisation factors. It is also used to generate inventory data for scenario analyses. This chapter introduces the LCA of nanocellulose and the fundamentals of ML and examines how ML has been employed in LCA and the development of surrogate LCAs. This chapter also discusses other applications that could inform future ML-based tools for LCA.