Francis, A and Thomas, A (2022) A machine learning-based life cycle assessment prediction model for the environmental impacts of buildings. In: Tutesigensi, A and Neilson, C J (eds.) Proceedings of 38th Annual ARCOM Conference, 5-7 September 2022, Glasgow Caledonian University, Glasgow, UK.
Abstract
With the emerging importance of achieving climate targets and net-zero levels, assessing the environmental sustainability of buildings is of paramount importance. Life Cycle Assessment (LCA) is a popular tool used for such assessment. However, performing LCA for buildings is time-consuming and challenging due to inconsistencies in the databases, software limitations, and data intensiveness, making it a complex tool for decision-making applications. Therefore, this study proposes a methodological framework to develop surrogate LCA models for buildings using modern machine learning (ML) tools such as Multiple Regression and Artificial Neural Networks (ANN). Such a framework improves the application of LCA in environmental decision-making during the planning of building projects by reducing the time, effort, and complexity associated with conducting LCA of buildings. It can be found that the mean absolute percentage error (MAPE) for the tested dataset in the regression-based model is less than 5 percent rendering it a good surrogate model.
| Item Type: | Conference Paper (Paper) |
|---|---|
| Uncontrolled Keywords: | life cycle assessment; artificial neural network; multiple regression; environmental sustainability of buildings; decision-making |
| Index terms: | environmental sustainability, artificial neural network, database, life cycle assessment, dataset, decision-making, machine learning, prediction model, environmental impact, multiple-regression, complexity |
| Subjects: | health safety and environment, statistical analysis, environmental impact, decision analysis, modelling and simulation, data management, prediction and forecasting, systems engineering, artificial intelligence |
| Topics: | Engineering Principles, Health and Safety, Risk Management, Research Practice, Digital Applications, Sustainability |
| Descriptive scope: | 3 PCA |
N.B. Descriptive scope is a count of how many of the five facets of empirical research are indicated by the words used in title, abstract and keywords. It is not intended as a judgement on the research; merely a count of the kind of word we would expect to indicate Phenomenon, Concepts, Theoretical framing, Empirical techniques, Analytical techniques. If all five are present, then a code of “5 PCTEA” will indicate this. If you feel the coding for this record is questionable, we welcome discussion around the terms we matched or the way we categorized them. The facet you would expect may not be coded, or a facet may be coded inappropriately. This can also bear on a larger question, of which facets should be treated as defining in construction management research. Please get in touch, and we will look at it. More details here