FSU Wins $2.3M NSF Grant to Build AI for Hurricane-Fueled Wildfires in Florida's Panhandle

FSU wins $2.3M NSF grant to build AI tools that strengthen wildfire management in Florida's hurricane belt

Florida State University has secured a $2.3 million National Science Foundation award to develop artificial intelligence systems that help agencies and communities manage wildfires fueled by hurricane debris in the Florida Panhandle. The four-year project, led by assistant professor of computer science Yushun Dong, is the largest research award to date for FSU's Department of Computer Science.

The work targets the wildland-urban interface (WUI) where forests such as the Apalachicola National Forest meet homes, roads, and critical infrastructure. The goal: deliver practical, testable tools that reduce ignition risk, protect road access, and limit damage when fire conditions escalate after major storms.

What this project will build

FIRE: An Integrated AI System Tackling the Full Lifecycle of Wildfires in Hurricane-Prone Regions will bring together computer scientists, fire researchers, engineers, and educators to deliver end-to-end capabilities:

• Ignition forecasting tied to hurricane-driven fuel loads and weather
• Roadway disruption prediction to support evacuation and emergency logistics
• Condition estimation for live fire monitoring and response planning
• Damage assessment to inform mitigation, insurance, and recovery

"The modern practice of prescribed burns began over 60 years ago, which was a huge leap in working with nature to help manage an ecosystem," Dong said. "Now, we're positioned to make another leap: we're able to use powerful AI technology to transform wildfire risk management with tools such as ignition forecasting, roadway disruption prediction, condition estimations, damage assessments and more."

Why this matters for the Panhandle

Low-intensity wildfires and prescribed burns are essential in many fire-adapted ecosystems. They reduce fuel loads, recycle nutrients, and can limit pests and disease. But repeated hurricanes leave downed trees and debris that change fire behavior and increase the chance of fast-moving, high-consequence events in the WUI.

These conditions demand better forecasts for where fire might start, how it could spread, and which roads could be blocked. That knowledge improves evacuation timing, supports road maintenance and clearance operations, and helps safeguard homes and lives.

Program details and team

The project is funded through NSF's Fire Science Innovations through Research and Education (FIRE) program, which backs interdisciplinary research and education that realigns how society deals with wildland fire and its drivers. Two of the four projects funded so far by FIRE are led by FSU researchers, including a complementary study by associate professor Neda Yaghoobian that examines canopy dynamics contributing to wildfire behavior.

Co-principal investigator Eren Ozguven (civil and environmental engineering; director of the Resilient Infrastructure and Disaster Response Center) joins Dong alongside contributors James Reynolds (STEM outreach, Learning Systems Institute) and Jie Sun (postdoctoral researcher, Earth, Ocean and Atmospheric Science). The award also funds education and workforce development in AI and disaster resilience-positioning the department to train the next generation of researchers at the intersection of AI and wildfire science.

What practitioners can expect

• Operational forecasts that integrate hurricane impacts, fuel conditions, and weather to anticipate ignition and spread in the WUI
• Road impact predictions that help transportation, emergency management, and utilities plan clearance, staging, and rerouting
• Damage assessment tools that speed decision-making for response and recovery
• Stakeholder engagement so models reflect local fuels, terrain, and infrastructure constraints

"I became passionate about applying my research to hurricane-related phenomena after experiencing my first hurricane living in Tallahassee," Dong said. "I want to use AI techniques to help Florida Panhandle residents better understand and prepare for extreme events in this ecosystem with its unique hurricane-fire coupling dynamics."

Outlook

Over four years, the team will prototype, validate, and share an integrated AI platform aimed at the full wildfire lifecycle-from pre-ignition risk analysis to post-event assessment. Results are expected to support agencies and communities across hurricane-prone regions facing similar WUI risks.

Learn more about NSF's FIRE program at nsf.gov.

Upskilling for researchers and engineers

If you're building AI fluency for climate and hazard applications, explore role-based learning paths at Complete AI Training.