Harnessing AI and Digital Twins in BIM for Wildfire-Resilient WUI Communities: A Systematic Review

Abstract

Communities within the wildland–urban interface (WUI) are increasingly exposed to severe and frequent wildfire threats due to climate change, land-use change, and expanding urban development. Traditional fire management approaches have proven inadequate to address the complex interactions of fire behavior, human exposure, and infrastructure vulnerability. Emerging digital technologies, particularly Building Information Modeling (BIM) and digital twins, present opportunities to transform WUI community resilience by enabling data-rich, predictive, and adaptive strategies for fire preparedness and response. This review examines the current state of research on integrating BIM, digital twins, and artificial intelligence (AI) to support multi-scale wildfire modeling, dynamic risk assessment, real-time situational awareness, and post-event recovery in the built environment. A systematic literature review methodology was applied to synthesize studies on predictive fire spread models, sensor-driven fuel condition monitoring, and integration of geospatial and structural data. The review identifies key technical enablers and barriers, including challenges of data interoperability, real-time integration, and the lack of standardized protocols for linking AI models with BIM-based systems. The findings propose a conceptual framework for advancing AI-enabled digital twin applications to support proactive WUI fire resilience. These insights have significant implications for researchers, practitioners, and policymakers seeking to leverage the built environment as a lever of change through digital transformation, offering directions for future research to enhance the safety, adaptability, and sustainability of WUI communities facing escalating wildfire risks.