AI‑Enhanced Conceptual Framework for Evaluating Indoor Environmental Quality in Contemporary Architectural Practice

Abstract

This study presents an AI-assisted hybrid computational framework for evaluating Indoor Lighting Quality (ILQ) as a core component of Indoor Environmental Quality (IEQ) during early design stages. The framework combines a simplified daylight-feasibility proxy with climate-based parametric simulations (Ladybug and Honeybee) and machine-learning prediction to reduce computational cost while maintaining accuracy. ILQ is emphasized because visual comfort and daylight provision critically influence occupant performance, learning outcomes, and energy consumption in educational spaces. Applied to a drawing hall at Jazan University (hot-humid climate), the framework achieved a calibrated Daylight Feasibility Factor (DF = 0.31), Spatial Daylight Autonomy (sDA = 0.70), and UDI coverage of 85–95% of the floor area. These results validate the hybrid approach’s reliability and demonstrate its potential to support evidence-based, resource-efficient design decisions in educational buildings, contributing directly to the sustainability goals of Saudi Vision 2030.