AI-Driven Environmental and Adaptive Design for Heritage University Buildings: Toward Practical Applications for Enhancing Learning Quality
Heritage university buildings, designed for historical contexts, face challenges in meeting modern environmental and educational demands, leading to poor indoor environmental quality (IEQ) that impairs occupant well-being and learning outcomes. This study introduces an AI-driven hybrid deep learning framework (HDLF) to assess and enhance IEQ in such buildings. Integrating convolutional, generative, and recurrent neural networks, the HDLF evaluates thermal comfort, ventilation, daylight, acoustics, and spatial flexibility. Data from ten heritage campuses in hot-arid and Mediterranean regions were analyzed using environmental simulations, non-invasive sensors, and surveys (N=217, a subset of broader data). The framework identified critical gaps, such as CO₂ levels exceeding standards by up to 80% and ventilation rates 50–70% below optimal, proposing six heritage-sensitive retrofit strategies that achieved a simulated IEQ improvement of 20–40%. The HDLF can be adapted into a practical application for architects to support real-time IEQ assessments and heritage-sensitive retrofitting, contributing to SDG 4 (Quality Education) and SDG 11 (Sustainable Cities and Communities).
إن هذا الكتاب ينطلق من قناعة راسخة مفادها أن التخطيط العمراني لا يبدأ برسم المُخططات أو التصورات المجردة؛ بل يبدأ بفهم السردية الاجتماعية. فالحي الذي يبدو من الجو مجرد كتلة عمرانية متداخلة، يكشف…
لقد جاءت فكرة هذا الكتاب عن قناعة تامة بأن فهم الإشكالات الحضرية في المدن لا يمكن أن يتحقق من خلال تحليل التقارير والإحصاءات الحكومية فحسب؛ بل يتطلب النزول إلى الميدان ومعايشة الواقع والتفاعل…
This study develops and applies an adapted New Urbanism–Transit-Oriented Development (NU–TOD) framework to evaluate spatial, functional, and climatic performance in Al Malqa District, Riyadh.