NLP-based semantic model healing for calculating LCA in early building design stages

To limit the global warming, the environmental impacts of new buildings need to be quantified and optimized already in the early design stages. Semantically rich models, such as Building Information Modeling (BIM), facilitate deriving consistent and automated quantity take-offs of the relevant components for calculating whole building life cycle assessments (LCA). A particular challenge is that early-stage BIM models typically lack stringency in terms of component modeling and material classification. Hence, this paper presents a methodology for enriching knowledge and characteristics from the coarse information available at the early design stages, in a process denoted as semantic model healing. In more detail, the proposed method employs different Natural Language Processing (NLP) strategies to increase the performance of automatically matching materials defined in a BIM model to a knowledge database with environmental indicators of commonly used components, facilitating a seamless LCA in the early stages of design.