FIRE-NET: Fast Fire Risk Across the US West: Cross-Sector Synthesis to Advance Discovery and Solutions

Fires are growing faster across the West—with a 250% increase in just the past two decades. While fast fires only represent 3% of all wildfires, they are the most destructive and deadly because they challenge suppression efforts and compromise evacuation routes. Fire science and policy need to expand the focus from 'megafires' to also address 'fast fires.' To tackle this urgent threat, this effort will build a Fast Fire Network to develop a new framework for ‘fast fire risk’, leveraging expertise across disciplines in the natural, social, data, and computer sciences, hazards and risk analysis, and engineering. This novel framework will utilize big data and next-generation AI models centered on the three fundamental elements of risk: hazard, exposure, and vulnerability. Given recent fast fire disasters, such as the Paradise, Marshall, and Lahaina wildfires, which took over a hundred lives and destroyed tens of thousands of homes, there is a critical need to improve risk estimates of who and what is potentially in the fire’s path. This work will contribute to better protecting American lives and property, as the pace of wildfires increases. Building upon the Environmental Data Science Innovation and Impact Lab’s (ESIIL) data synthesis approach, this team will empower the Fast Fires Network, a community of over 200 people, to build critically needed solutions to faster-moving wildfires. ESIIL, an NSF-funded synthesis center, is experienced in building large science teams that hold a broad spectrum of ideas and perspectives, while also offering advanced cyberinfrastructure (CI) tools for seamless data integration via CyVerse. Within the ‘fast fire risk’ framework, three cross-sector and cross-discipline Incubator Working Groups and Stakeholder Forums on fast fire hazard, exposure, and vulnerability will advance the science around: i) what are the best metrics on fire speed and what are the biophysical and built environment drivers; ii) what western US towns have potentially compromised evacuation during a fast fire; and iii) what are the social and structural attributes that increase potential home losses. A Fast Fires Hackathon in Year 1 will incubate ideas and kick off data integration and AI model development. A closing Fast Fires Solutions Summit in Year 5 will solidify an adaptation menu of risk-reduction approaches. This effort will employ a novel data-infused translation model, where possible solutions are tested in real-time using collaborative cloud-based analytics. Overall, the Fast Fire Network will address the increasing pace of wildfires with science-backed resilience solutions. This award reflects NSF's statutory mission and has been deemed worthy of support through evaluation using the Foundation's intellectual merit and broader impacts review criteria.