Toward Semantic-Driven Building Data Architectures for AI-Based Architectural Design
With the rapid advancement of digitalization and artificial intelligence , architectural design faces a fundamental limitation: the dominance of geometric representations with insufficient semantic depth. This imbalance restricts the interpretability, reasoning capacity, and transferability of AI-driven design systems across the building lifecycle. Addressing this challenge, the present study explores how architectural geometry models can be semantically enhanced to support AI-based modeling and reasoning, laying the foundation for more intelligent, explainable, and integrated design processes. Limit thinking in Geometry-Centric Architectural Models The study critically examines the limitations of conventional geometric representations across the design–performance–construction chain. Through bibliometric analysis and an extensive literature review, it reveals how geometry-only models fail to capture intent, performance logic, construction rules, and associative knowledge. These shor...