Architecture of a Digital Twin-Enabled Multimodal Monitoring Platform for Firefighter Safety

Firefighters operate in dynamic urban environments where limited real-time situational awareness can compromise emergency response and personnel safety. This study presents a digital twin-enabled architecture and proof-of-concept prototype for multimodal physiological and environmental monitoring of firefighters. The proposed architecture integrates wearable and environmental sensing, communication, data processing, digital twin representation, and decision-support components within a scalable layered framework. A Grafana-based prototype was developed using simulated physiological and environmental data streams to demonstrate multimodal data integration, threshold-based risk classification, and real-time visualization at individual and fleet levels. Risk classification was implemented using parameter-specific threshold rules rather than a trained machine learning model. At the same time, advanced AI-based prediction, anomaly detection, and adaptive response capabilities are defined as future extensions of the proposed architecture. The prototype dashboard implementation demonstrates the feasibility of the proposed system by visualizing physiological metrics, environmental exposure, geospatial information, and operational risk indicators at both individual and fleet levels. The study’s primary contribution is therefore architectural and integrative, providing a structured framework for connecting multimodal sensing, risk indication, visualization, and decision support while establishing a foundation for future development and validation of predictive digital twin systems for firefighter safety and urban emergency response.