Abstract The advancement of Artificial Intelligence (AI) has emerged as a transformative force in the building sector, offering enhanced capabilities for evaluating habitability with increased accuracy and efficiency. This paper presents and validates a custom-trained AI model developed to assess building habitability based on key indicators such as thermal comfort, energy efficiency, indoor air quality, accessibility, and sustainability. The methodology employs a hybrid approach, combining a comprehensive literature review with the design and supervised training of the AI model, utilizing inputs from technical standards (e.g., NBR 15575) and sustainability certifications (such as LEED). To validate the model, a case study was conducted on the Piracanjuba Administrative Headquarters (certified LEED Platinum), where the AI system effectively classified the building’s performance across multiple criteria. The findings highlight the model's ability to provide accurate and consistent assessments, demonstrating its potential as a decision-support tool for architects and engineers aiming to enhance project sustainability and occupant well-being.
Carrara et al. (Mon,) studied this question.