BUFFALO, N.Y. – The University at Buffalo is leading a new $2 million research project funded by the National Science Foundation (NSF) to develop tools that help communities better understand and prepare for the cascading disasters that wildfires can unleash on people and critical infrastructure.

The project brings together multidisciplinary researchers from three partner institutions: the University of California, Berkeley, Northeastern University and the U.S. Department of Energy’s Pacific Northwest National Laboratory (PNNL). The award is part of NSF’s Fire Science Innovations through Research and Education (FIRE) program and runs from September 2026 through August 2029.

Over the next three years, the team will examine communities in the wildland‑urban interface (WUI), where human development such as housing and power lines meets or mixes with forests, grasslands and other natural vegetation. The study is titled “Collaborative Research: FIRE‑WUI: REKINDLE: Resilient Engineering through Knowledge Integration for NetworkeD Lifelines and Ecosystem.”

As wildfires become more frequent and severe, WUI communities face increasing risks. Beyond the immediate destruction, wildfires can trigger debris flows, flash floods and other related environmental hazards, while also causing significant disruptions to lifeline infrastructure, including power grids, water systems and transportation networks.

However, current approaches to wildfire resilience planning typically consider these interconnected risks in isolation, making it difficult to see how they interact and how people respond. REKINDLE is designed to address this gap by combining artificial intelligence (AI), infrastructure modeling and social science to assess these risks together and identify ways to bolster public safety and community resilience.

“People are familiar with wildfire risk, but what is often overlooked are the additional hazards and cascading effects that can follow,” said the project’s lead principal investigator Sayanti Mukherjee, PhD, associate professor in UB’s Department of Industrial and Systems Engineering. “A region affected by wildfire can become more vulnerable to subsequent hazards like debris flows and flash floods. When those events cut off roads or interrupt power or water service, the impacts can quickly compound for communities already struggling to recover.”

Mukherjee, who is also an affiliate faculty member with UB’s Department of Electrical and Computer Engineering and the Institute for Artificial Intelligence and Data Science, is joined on the project by co-principal investigator Susan Spierre Clark, PhD, of UB’s Department of Environment and Sustainability. Investigators from the other three institutions include Auroop R. Ganguly, PhD, of Northeastern University; Marta González, PhD, and Anna Serra-Llobet, PhD, of UC Berkeley; and Andre Coleman, PhD, and Sam Chatterjee, PhD, of PNNL.

Through REKINDLE, researchers will investigate how wildfires and the hazards they trigger can compromise key infrastructure, setting off disruptions that affect the essential services people depend on for their daily lives and well‑being.

“We want to understand not only how infrastructure systems are affected, but how those disruptions shape household decisions and community response,” Clark said. “Bringing those pieces together can help communities build resilience, restore critical infrastructure and recover faster from future disasters.”

AI will play a central role in this work. Researchers will build a physics-informed, geospatial-AI model that combines Earth observation data with wildfire expertise to produce maps showing where wildfires and related hazards are most likely to occur. They will also use machine learning models to trace how failures could spread across interconnected power, water and transportation systems.

In addition, the research team will look at how those disruptions affect people. Using household surveys, focus groups and simulation games, researchers will examine how infrastructure failures can impact families’ livelihoods and their ability to recover from these cascading disasters. The team will use these findings to help determine where investments in stronger infrastructure could have the greatest impact before a fire and how recovery efforts should be prioritized afterward.

“Deciding where to invest resources, whether it’s hardening infrastructure or increasing community engagement and outreach, will be an important part of this project,” Mukherjee said. “AI and optimization can help us assess different strategies and pinpoint where those investments would have the most value. That kind of insight can support emergency managers, infrastructure operators and environmental planners in making more informed decisions for their communities.”

Researchers will build and test REKINDLE with case studies from the Los Angeles and Montecito regions of California, both of which have experienced major wildfires and post-fire debris flows in recent years. The research team will work with government agencies, utility providers and community stakeholders to help ensure the tools they develop reflect the needs of the people and communities that will use them.

The project will also have education and workforce development components. Researchers will create wildfire-focused educational materials for students from middle school through graduate school, introducing them to wildfire resilience and related hazards. The team will make educational resources and research data publicly available so others can build on its work. Undergraduate and graduate students will have opportunities to gain experience through internships with industry partners and national laboratories.