Integrated data-driven and knowledge-based performance evaluation for machine assistance in building design decision support

Abstract

The building design process requires architects to consider interdisciplinary knowledge and data support based on the vision of sustainable development. In this context, we develop a process-integrated, dynamic machine assistance to support the decision-making process for building designers in the early design phases. In this paper, we present 1. a framework for integrating data-driven models with knowledge-based methods that provide multi-objective assistance considering energy performance and embodied environmental impact; 2. the alignment of the methods in the design process and respective decision situations to disclose the potential situated design space including its uncertainty ranges as well as detailed strategy suggestions. A case of real-world building data serves to illustrate and validate the approach. The research presented in this paper is part of research aiming at assistance by augmented intelligence for sustainable building design decision support.