Artificial intelligence-based strategies for indoor environmental quality optimisation

Purpose – This review examines how data-driven technologies are being applied to improve indoor environmental quality (IEQ) while enhancing energy efficiency in buildings. It further highlights the need for intelligent solutions that balance occupant comfort and environmental impact. Design/methodology/approach – A PRISMA-based systematic review identified studies integrating AI, machine learning, and digital twins for IEQ monitoring, prediction, and control, yielding 152 reviewed papers. Findings – The review indicates that data-driven research largely concentrates on monitoring and predicting IEQ with particular emphasis on thermal comfort and air quality. Considerable attention is also given to enhancing energy efficiency. A wide spectrum of artificial intelligence and machine learning techniques has been applied, including regression and classification models, to represent continuous and categorical IEQ variables. Several studies further integrate AI with BIM and IoT platforms to develop digital twin frameworks enabling real-time performance assessment and adaptive control, though adoption is constrained by data quality, interoperability, and scalability challenges. Research limitations/implications – The review is limited by database scope and keyword selection, suggesting opportunities for broader future investigations. Practical implications – Findings support the development of intelligent building strategies that enhance occupant well-being, reduce emissions, and promote sustainable indoor environments. Originality/value – This review provides a consolidated perspective on how emerging data-driven technologies simultaneously support IEQ improvement and energy efficiency, highlighting the growing role of digital twin systems in intelligent building management.