We Build Teams That Win: LSU Combined Effort Advances AI to Predict and Prevent Wildfires

When communities face increasingly destructive wildfires, the most powerful tool isn’t just response, it’s prevention. At LSU, a multidisciplinary research team is pushing the boundaries of what’s possible, using artificial intelligence (AI) to help predict wildfires before they ignite, giving fire managers critical time to act.   

“DeepFire allows fire managers to know when and where to deploy their resources ahead of time, so they can prevent disasters like the January 2025 wildfires in Southern California,” said Supratik Mukhopadhyay, professor of environmental science and Center of Computation & Technology (CCT) faculty member.  

Led by Mukhopadhyay, the DeepFire team has emerged as a global leader in wildfire innovation. Alongside Thomas Douthat, associate professor of environmental science, Rubayet Bin Mostaviz, research assistant professor with the LSU AgCenter and LaHouse, and Saiful Sajol, research assistant professor with the AgCenter and LaHouse, the team has reached the finals of the $11 million Wildfire XPRIZE, placing among the top teams worldwide in the space-based detection and intelligence track.    

Out of more than 300 international teams, DeepFire stands out for developing an AI-driven engine capable of predicting wildfires weeks in advance with more than 90% accuracy. The system integrates fire prediction, early detection, and fire-spread modeling by factoring in weather conditions, analyzing visual data for smoke, and cross-referencing findings with predictive risk maps.      

The DeepFire team reflects LSU’s commitment to innovation and teamwork.  

Mukhopadhyay provides the strategic vision and leadership behind the project, while Douthat contributes deep expertise in environmental systems and wildfire behavior. Bin Mostaviz and Rahim strengthen the applied research and outreach components through their work with the AgCenter and LaHouse, ensuring the technology connects to real-world resilience and hazard mitigation efforts.    

Students are at the heart of DeepFire’s success. 2023 LSU graduate Dylan Wichman, a computer science graduate who grew up in wildfire-prone Montana, led much of the work on the prediction model. His early interest in using AI to prevent wildfires found a natural home at LSU. The detection model was driven by Robert DiBiano, who earned his PhD at LSU in artificial intelligence, machine learning, and computer vision.   

The impact of the team’s work has reached a national audience, with DeepFire featured in LSU’s nationally televised commercial airing during LSU football games and other major sporting events.   

Through innovation, collaboration, and a shared commitment to public good, the DeepFire team is advancing LSU’s research mission while positioning the university as a leader in solutions that protect lives, communities, and natural resources.     

Next Step

Discover stories showcasing LSU’s academic excellence, innovation, culture, and impact across Louisiana.

See more LSU News