Design variable analysis and generation for performance-based parametric modeling in architecture

TLDR

Parametric models are increasingly used for performance‑driven design, yet defining a flexible design space that yields compelling solutions remains challenging. This study proposes and evaluates extending machine learning and data analysis techniques to the early problem setup to interrogate, modify, relate, transform, and automatically generate design variables for architectural investigations. The authors apply machine learning and data analysis methods during early problem setup to interrogate, modify, relate, transform, and automatically generate design variables. Analysis of two case studies in structure and daylight demonstrates workflows for identifying variable importance, deriving performance‑linked control sliders, and automatically generating meaningful variables for specific typologies.

Abstract

Many architectural designers recognize the potential of parametric models as a worthwhile approach to performance-driven design. A variety of performance simulations are now possible within computational design environments, and the framework of design space exploration allows users to generate and navigate various possibilities while considering both qualitative and quantitative feedback. At the same time, it can be difficult to formulate a parametric design space in a way that leads to compelling solutions and does not limit flexibility. This article proposes and tests the extension of machine learning and data analysis techniques to early problem setup in order to interrogate, modify, relate, transform, and automatically generate design variables for architectural investigations. Through analysis of two case studies involving structure and daylight, this article demonstrates initial workflows for determining variable importance, finding overall control sliders that relate directly to performance and automatically generating meaningful variables for specific typologies.