Development of a spatially contextualised and AI-enabled digital twin for asthma specific indoor air quality management

Indoor air pollution poses significant health risks, particularly for individuals with respiratory conditions such as asthma. Indoor environments often expose occupants to elevated levels of pollutants, exacerbating respiratory symptoms and increasing health risks. While advancements in Indoor Air Quality (IAQ) monitoring have improved pollutant detection, existing systems remain limited in scope, primarily focusing on independent data collection without integrating spatial visualisation, predictive analytics, or real-time decision support. This study addresses these gaps by developing the Air Quality and Health Responsive Digital Twin (AIR-DT), a Digital Twin (DT) system designed to enhance IAQ management through real-time monitoring, prediction, spatial analytics, and proactive intervention. The methodology combines IoT-based IAQ monitoring with Building Information Modelling (BIM) and an interactive dashboard to provide spatially contextualised insights. AIR-DT was deployed in a residential building with an asthmatic occupant, where it was evaluated for its ability to detect IAQ risks and support intervention strategies. The system successfully monitored six key IAQ parameters and provided real-time assessments, visual alerts, and short-term forecasts to support timely responses. This study demonstrates how DT technology integrates its four core functions (real-time monitoring, spatial visualisation, AI-driven prediction, and automated intervention) into a single, scalable framework for comprehensive air-quality management. The use of asthma-specific IAQ thresholds enables more targeted risk assessment and supports timely interventions for vulnerable occupants. The proposed system enhances decision-making for facility managers and occupants, while laying the foundation for future predictive modelling and automated environmental controls.