Machine learning in life cycle assessment

Abstract Machine learning (ML) has been used in life cycle assessment (LCA) to estimate the values of environmental impact characterization factors and to conduct sensitivity analyses. ML has even been used to develop surrogate LCAs, which have enabled prediction of future products’ full life cycle environmental impacts based on design-phase product characteristics. Outside of LCA, applications of ML algorithms have included data cleaning, predicting system output flows or performance, ecosystem informatics, and system optimization. Considering these uses and capabilities of ML, opportunities exist for using ML in cleaning data for life cycle inventories (LCI), estimating flow data for unit processes, improving the quality and quantity of data used to determine impact characterization factors, and generating inventory data for scenario analyses. In this chapter, we introduce LCA and ML, look at how ML has been used in LCA and in development of surrogate LCAs, and discuss other applications that could inform future ML-based tools for LCA.

[1]  Frédéric Magoulès,et al.  A review on the prediction of building energy consumption , 2012 .

[2]  Matthew J. Eckelman,et al.  Predictive modeling for US commercial building energy use: A comparison of existing statistical and machine learning algorithms using CBECS microdata , 2018 .

[3]  Gerald Whittaker,et al.  Geospatial identification of optimal straw-to-energy conversion sites in the Pacific Northwest , 2010 .

[4]  Pascal Lesage,et al.  Guidelines for Social Life Cycle Assessment of Products. : Social and socio-economic LCA guidelines complementing environmental LCA and Life Cycle Costing, contributing to the full assessment of goods and services within the context of sustainable development. , 2009 .

[5]  A.E. Landis,et al.  Comparison of life cycle impact assessment tools in the case of biofuels , 2008, 2008 IEEE International Symposium on Electronics and the Environment.

[6]  Thiago Antonini Alves,et al.  Ensemble method based on Artificial Neural Networks to estimate air pollution health risks , 2020, Environ. Model. Softw..

[7]  Q. Wei,et al.  Impacts of exposure to humidex on the risk of childhood asthma hospitalizations in Hefei, China: Effect modification by gender and age. , 2019, The Science of the total environment.

[8]  D. Robinson,et al.  Three pillars of sustainability: in search of conceptual origins , 2018, Sustainability Science.

[9]  H. Dewes,et al.  Life cycle assessment of beef cattle production in two typical grassland systems of southern Brazil , 2015 .

[10]  Thiago Antonini Alves,et al.  Unorganized machines to predict hospital admissions for respiratory diseases , 2016, 2016 IEEE Latin American Conference on Computational Intelligence (LA-CCI).

[11]  Christel Cederberg,et al.  System expansion and allocation in life cycle assessment of milk and beef production , 2003 .

[12]  Kwang-Kyu Seo,et al.  Approximate life cycle assessment of product concepts using multiple regression analysis and artificial neural networks , 2003 .

[13]  W. Ripple,et al.  Substituting beans for beef as a contribution toward US climate change targets , 2017, Climatic Change.

[14]  Serenella Sala,et al.  Environmental impacts of household consumption in Europe: Comparing process-based LCA and environmentally extended input-output analysis , 2019, Journal of cleaner production.

[15]  Andrej Udovč,et al.  Extending life cycle assessment normalization factors and use of machine learning – A Slovenian case study , 2015 .

[16]  Dora Marinova,et al.  Modelling sustainability , 2011, Math. Comput. Simul..

[17]  Thomas G. Dietterich.  Machine Learning in Ecosystem Informatics and Sustainability , 2009, IJCAI.

[18]  L.B. Lave,et al.  Comparing two life cycle assessment approaches: a process model vs. economic input-output-based assessment , 1997, Proceedings of the 1997 IEEE International Symposium on Electronics and the Environment. ISEE-1997.

[19]  David Wallace,et al.  Approximate Life‐Cycle Assessment of Product Concepts Using Learning Systems , 2000 .

[20]  David Wallace,et al.  Product classification to support approximate life-cycle assessment of design concepts , 2006 .

[21]  Hongwen He,et al.  Continuous reinforcement learning of energy management with deep Q network for a power split hybrid electric bus , 2018, Applied Energy.

[22]  Seppo I Junnila,et al.  Empirical comparison of process and economic input-output life cycle assessment in service industries. , 2006, Environmental science & technology.

[23]  Marilyn A. Brown,et al.  Machine learning approaches for estimating commercial building energy consumption , 2017 .

[24]  Hans-Jürgen Dr. Klüppel,et al.  The Revision of ISO Standards 14040-3 - ISO 14040: Environmental management – Life cycle assessment – Principles and framework - ISO 14044: Environmental management – Life cycle assessment – Requirements and guidelines , 2005 .