Graph Neural Networks (GNNs) have become a popular toolkit for generative floor plan design. Although design variation has improved greatly, few studies consider non- geometrical characteristics, such as building energy performance, in the generative design process. This paper presents a GNN-based approach to predict the energy performance for floor plan customization (energy-aware design). The approach lays the foundation for a performance-aware generative design using GNN. The results show that the GNN can achieve high accuracy in energy performance prediction.@en

In addition to the well-documented resource efficiency and geometrical freedom, Digital Fabrication (DFAB) revolutionizes architecture by integrating functionalities into building elements, unlocking untapped potential from the micro- to the macroscales. This study uses binder-jet printed sand for a DFAB prototype—Fireplace2—tailored for indoor heating. Named after its traditional counterpart, Fireplace2 showcases DFAB’s prowess in crafting precise microclimates for heightened thermal comfort. Our research, tuning mechanical and thermal properties across micro and meso scales, illustrates DFAB's utility in architects' hands for crafting tailored microclimates. This approach manipulates the effective thermal conductivity and macroscale topology for stability against toppling (0.8 kN). A vertical infill porosity gradient establishes a surface temperature gradient, countering ventilation-induced thermal gradients. With a minimal operational temperature vertical gradient (+0.2°C), complying with international comfort standards (Predicted Mean Vote −0.23, People Dissatisfied 6%), Fireplace2 stands testament to DFAB’s microclimate-shaping capabilities despite challenges like foot-level ventilation. The study propels DFAB into a sustainable paradigm, aligning occupant comfort with environmental consciousness, thereby fostering more efficient and enjoyable indoor spaces.@en