Awards

This research project investigates the development of a method to leverage AI as a tool to research indigenous architecture. The focus is on establishing a new AI application by developing and applying an AI-driven design framework, “DEEP-TEK,” to fine-tune diffusion models with diverse datasets of vernacular architectures. Learning from Traditional Ecological Knowledge (TEK), we can rediscover the environmental strategies used in those examples and the intelligent adaptations to climate that achieved resilient design as well as sensitivity to locales and contexts. Developing the prototype was pursued using a workflow structure of multiple connected iterations for fine-tuning and insertion of TEK datasets, supported by pre-processing methods of dataset curation and augmentation.

While architecture has often been associated with high-tech solutions that increase the carbon footprint, this research reconsiders “low-tech” solutions found in indigenous design and vernacular architecture. It delves into Florida’s vernacular architecture and its array of passive design strategies, applying this understanding within a comprehensive design case study. The workflow employs advanced technologies of machine learning and building-performance simulation—including daylight analysis and thermal simulation—to drive the design process toward a net-zero outcome.

The project examines cross-ventilation with the aim of optimizing airflow inside habitable environments. Simulating airflow patterns within architectural and urban design yields significance in pursuing higher environmental performance and resiliency; for such analysis, Computational Fluid Dynamics (CFD) becomes an accurate method. This work contributes to a shift in the design process to include building-performance simulation early in the design phases to inform decision-making and achieve higher efficiency. As part of the methodology, a prototype framework was developed—modeling the urban built environment, followed by an outdoor airflow analysis of the site conditions and immediate urban context.