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

Fundamental understanding of the oxidation behavior of O ₂, H ₂O, and CO ₂ in the process of oxyfuel combustion is of great significance. Extensive MD simulations with reactive force-field (ReaxFF) were performed to compare the gasification behavior under the individual influence of three oxidant molecules on a pristine and a mono-vacant graphene sheet. Distinct differences were observed in almost every aspect including initial kinetics, rate changes, complete/incomplete combustion, gasified regions, and the role of vacancy defects. In the case of O ₂, the nucleation stage is harder while the later stages contained no limiting behavior; The gasification kinetics is highest for H ₂O during initial periods, but the oxidative behavior changes as higher gas consumption levels are reached; CO ₂ has the highest thermodynamic stability and the formation of stable intermediate structures troubles the gasification. Significant out-of-plane activity is observed in the case of H ₂O oxidant. Results suggest that there may be little overlap in the oxidation sites for CO ₂ and H ₂O. In-depth atomic level investigations consistent with the experimental phenomenon will have implications for future design, process optimization, and their commercial application.

@en