Early design prediction of embodied carbon in buildings
Résumé
The digitalization of the building industry has facilitated the introduction of embodied carbon (EC) assessment tools in the structural engineering practice. However, it is rarely computed at early design stages, when changes with highest impact are made, but quantitative volumetric and material information – “hard” features – are still unavailable. This research uses machine learning regression models and investigates alternative strategies to predict the EC of a building, using descriptive data available in design briefs – “soft” features. The methodology developed combines multiple selection and regression methods to first build base models, and further blended models. It is tested on the Embodied Carbon of European Buildings EUCB-D database, describing the embodied GHG emissions of 625 buildings. Despite limited data available for the learning, results prove the potential of the methodology, and motivate its further developments into a tool for prediction, comparison and explanation of building EC at early design stages.