Scalable Digital Twins for Indoor Air Quality Management: A Review of Current Systems and Future Directions

Abstract

Indoor air quality (IAQ) management is moving from episodic assessment toward continuous, context-aware operation in which measurements, building-system data, and validated models are interpreted together. Within this transition, digital twins (DTs) offer a candidate scalable framework for linking calibrated sensing, building information modeling (BIM), semantic metadata, physics-based and hybrid IAQ simulation, data fusion, analytics, and control-oriented decision support. This review synthesizes DT and IAQ literature to identify the data, modeling, interoperability, and governance conditions that appear necessary for reliable deployment beyond isolated building pilots. The evidence reviewed suggests that scalable IAQ DTs are likely to depend on sensor calibration and uncertainty reporting, explicit spatial and system metadata, robust quality assurance/quality control (QA/QC), interoperable BIM and semantic representations, fit-for-purpose airflow and contaminant-transport models, edge-cloud processing, and privacy- and cybersecurity-aware governance. Although recent work demonstrates progress in IoT-enabled IAQ monitoring, BIM-linked asset representation, cloud/edge architectures, and machine-learning-based forecasting, many implementations remain pilot-scale because they lack standardized semantics, transparent validation, and documented operational performance across heterogeneous buildings. The review therefore envisions a layered IAQ DT architecture and staged implementation roadmap that could connect building-level pilots to federated urban-scale deployment.