Means for Life Cycle Assessment (LCA) in the early design phases are becoming more important to make informed decisions on choosing environmentally sustainable structural systems and materials, enabling an awareness of environmental sustainability through their Embodied Carbon (EC). Our research has developed a proof-of-concept data-driven LCA tool based on Bayesian Neural Network (BNN) regression models, usable prior to the definition of floor plan layouts to perform embodied carbon evaluation of building designs.
The BNN is built from data drawn from existing floor plans of residential buildings, and predicts material volumes and embodied carbon from generic design parameters typical in the early design stage.Users are able to interact with the tool in a Grasshopper environment or in an online resource. They can ener generic design parameters such as dimensions, ratios of served and serving spaces. This helps to obtain comparative visualisations based on different choices of construction systems and their environmental sustainability in a ‘shoebox’ interface, a simplified three-dimensional representation of a building’s primary spatial units.
