Featured Post from University of Florida

Multi-university AI research may revolutionize wildfire evacuation

Oct 28, 2025

3 min

Xilei Zhao


CaptionResizeWrap TextRemove


As wildfires grow wilder, the University of Florida and two other universities are developing large language models to make evacuations safer and more efficient.


Armed with a nearly $1.2 million National Science Foundation grant, UF, Johns Hopkins University and the University of Utah are creating these AI-based models to simulate human behavior during evacuations – information that will help emergency managers shape more effective evacuation plans.


“Strengthening wildfire resilience requires accurate modeling and a deep understanding of collective human behavior during evacuations,” said UF project lead Xilei Zhao, Ph.D., an associate professor with the Engineering School of Sustainable Infrastructure and Environment. “There is a critical need for simulation models that can realistically capture how civilians, incident commanders and public safety officials make protective decisions during wildfires.”


CaptionResizeWrap TextRemove


Xilei Zhao focuses on developing and applying data and computational science methods to tackle problems in transportation and resilience.


View her profile here





Existing simulation models face limitations, particularly with reliable predictions under various wildfire scenarios. New AI models can simulate how diverse groups of people behave and interact during the hurried scramble to seek safety.


Zhao’s team is developing a convergent AI framework for wildfire evacuation simulations powered by psychological theory-informed large language models. The project will produce simulation methods to promote teaching, training and learning, and support wildfire resilience by allowing public safety officials to use open-access tools.


“This research seeks to be a transformative step toward improving the behavioral realism, prediction accuracy and decision-support capability of wildfire evacuation simulation models,” Zhao said.


Zhao partnered with John Hopkins professor Susu Xu, Ph.D., and University of Utah professors Thomas Cova, Ph.D., and Frank Drews, Ph.D. The preliminary results of the study were recently presented at the 63rd Annual Meeting of the Association for Computational Linguistics.


“In that paper, we started to train the model on the survey data we collected to see how we can accurately predict people's evacuation decisions with LLMs,” Zhao said.


Research objectives include extending the Protective Action Decision Model for civilians and public safety officials, developing psychological theory-informed large language model agents for protective modeling and generating a realistic synthetic population as input for the simulation platform. The team also plans to develop learning-based simulations and predict human behavior under scenarios such as fire spread, warning and infrastructure damage.



This research comes at a critical time, as the number of wildfires has significantly increased globally. About 43% of the 200 most damaging fires occurred in the last decade leading up to 2023, according to a recent study in Science. The intensity, size and volume of wildfires are threatening more urban areas.


“If you go into the urban area, many people do not have cars, or they need additional mobility support,” Zhao said. “For example, the LA fires impacted nursing homes with a lot of elderly people, many of whom are immobile or lack the ability to drive. That's a big problem. This would be very relevant to them.”


The large language models will provide important context for evacuation planning as well as real-time decision making.


“We envision this tool being used during planning,” Zhao said, “so emergency managers can test different kinds of scenarios to determine how to draw the evacuation zones, where to issue the orders first and how to design the communications messaging.”


This is important research and critical as wildfires become more common across North America.  If you're a reporter looking to connect and learn more - then let us help.


Xilei Zhao is available to speak with media - simply click on her icon now to arrange an interview today.

Connect with:
Xilei Zhao

Xilei Zhao

Assistant Professor

Xilei Zhao focuses on developing and applying data and computational science methods to tackle problems in transportation and resilience.

Machine LearningPublic TransitHurricane EvacuationCommunity ResilienceArtificial Intelligence

You might also like...

Check out some other posts from University of Florida

2 min

Simple display changes in grocery stores could cut food waste while boosting profits

New research from the University of Florida suggests that supermarkets could significantly reduce food waste while increasing their profits through smarter product display and pricing strategies. The study found that retailers could cut food waste by more than 20% while increasing profits by 6% on average. “It’s rare to find solutions that benefit both business and the environment, but this appears to be one of them,” said Amy Pan, study co-author and associate professor at the UF Warrington College of Business. “Our findings highlight that strategically selling older products alongside fresh ones can simultaneously boost profits and minimize waste by leveraging the right product display, discounting rate and discount time.” The findings provide crucial insight into a growing global challenge. Recent estimates suggest that 17% of global food production goes to waste, with retail accounting for 13% of that waste. In the United States alone, up to 40% of food produced is wasted, while one in eight Americans faces food insecurity. The researchers identified two effective strategies for retailers, depending on the predictability of store traffic. When store traffic is predictable, the researchers find two optimal solutions: Unsold products are swapped with a new batch when the current products are due to be replaced, so that there is only one batch on shelves at a time Newer batch products are displayed on shelves alongside older products that are sold at a discount In contrast, when store traffic isn’t predictable, the product display depends on the characteristics of the product, store and consumers. Specifically, the researchers find: For products that spoil quickly and have a low disposal cost, like fresh pastries, the best approach is to remove unsold items when new stock arrives However, for items with longer shelf lives and high disposal cost, like dairy products, stores can sell older items at discounted prices at the front of shelves while keeping fresher items at their full price on the back of shelves Even stores that prefer not to discount their products can benefit from simply optimizing their display strategies. The study found that thoughtful product placement alone can significantly improve profits while reducing waste. The researchers emphasize that while their findings focus on retail-level waste, the benefits extend throughout the supply chain. Farmers benefit from increased orders, retailers save money by reducing waste and consumers get more affordable access to healthy food options. “What’s particularly exciting about these findings is that everyone wins,” Pan said. “Retailers make more money, consumers get more affordable options and we reduce the environmental impact of food waste.” Looking to know more about this topic or connect with Amy Pan?  Simply click on her icon now to arrange an interview today.

2 min

Florida needs veterinarians trained to respond to natural disasters. Congress can help.

When Hurricane Helene struck, we were on the frontlines in Florida’s Big Bend region, racing against time to support the Humane Society as they rescued animals displaced by the most powerful storm ever to hit this part of the state. Two weeks later, we were back in action, facing the devastating flooding from Hurricane Milton. These back-to-back disasters showcased the urgency and critical need for emergency-response veterinarians who can act fast to save lives. We lead one of the nation’s only three emergency veterinary response teams — the University of Florida Veterinary Emergency Treatment Service (UF VETS). Founded after the 2004 hurricane season and operating under the UF College of Veterinary Medicine, the UF VETS program hosts two distinct, yet complementary, branches: a medical response unit for disaster-affected animals and an animal technical rescue branch, which manages complex operations like overturned livestock trailers. Larry Garcia specializes in veterinary disaster preparedness and response, animal technical rescue/training and shelter medicine operations. View his profile here Our team is on call whenever disaster strikes, working alongside local and state veterinary organizations, animal rescues and law enforcement to save animals in crisis. But here’s the problem: Without a nationwide system for coordinating these efforts, it’s often chaotic, and animals suffer because of it. Now Congress has a golden opportunity to change that. As they return to Washington, they have the chance to make a game-changing impact by including funding in the final FY 2025 Homeland Security Appropriations bill to create a nationwide network of veterinary emergency teams. This funding could revolutionize how the U.S. handles animal care during national disasters — and it needs to happen, fast. Read more ... Looking to know more about this important topic or connect with Lawrence Garcia - simply click on his icon now to arrange an interview today.

3 min

UF scientist studies muscle loss in space to benefit astronauts and patients on Earth

Astronauts traveling to Mars will face many challenges, but one of the most serious is muscle loss during long space missions. A new study led by University of Florida researcher Siobhan Malany, Ph.D., sheds light on how human biology changes in microgravity and could help protect astronaut health while also offering hope for patients with muscle-wasting diseases on Earth. Malany, an associate professor in the College of Pharmacy, a member of UF’s Astraeus Space Institute, and director of the in-space Biomanufacturing Innovation Hub, recently published findings showing how muscle cells adapt in space. Her team studied bioengineered three-dimensional muscle tissues derived from biopsy cells from both younger and older individuals and observed how they responded to electrical stimulation in microgravity. These micro-scale tissues called “tissue chips” were given nutrients and electric pulses autonomously in a miniature laboratory the size of a shoe box called a CubeLab.x. A camera system inside the box recorded the rate of muscle contraction. “This research is about more than just space,” Malany said. “By understanding how muscle tissue deteriorates much faster in microgravity, we can uncover new strategies to address muscle loss that occurs naturally with aging and with age-related diseases here on Earth.” Siobhan Malany studies the effects of microgravity on human muscle biology using an automated tissue chip system. View her profile here The study found that younger muscle tissue showed more pronounced changes in mitochondrial pathways — cellular systems that produce energy — than older tissue did when exposed to microgravity. Researchers also discovered that, on Earth, older muscle tissue responds less to electrical stimulation than younger tissue. But in space, the younger tissue showed a noticeable drop in its ability to contract, suggesting that younger muscle may experience a greater change when exposed to the space environment. These insights may help researchers design new treatments to protect muscles in astronauts during long missions, as well as develop therapies for people experiencing age-related muscle loss on Earth. The project was part of UF’s broader efforts to advance space biology. Through the Astraeus Space Institute, UF brings together experts across disciplines, from medicine and pharmacy to engineering and plant science, to address the unique challenges of space exploration. “UF researchers are helping lay the groundwork for humanity’s next giant leap,” Malany said. “It’s exciting to see our work contribute to both the health of astronauts and the lives of patients back home.” UF’s leadership in space biology is strengthened through collaboration with partners including the Kennedy Space Center Consortium and the Center for Science, Technology and Advanced Research in Space), both initiatives bringing together universities in Florida’s high-tech corridor, government agencies and industry leaders. Malany’s work also builds on long-term collaborations with AdventHealth, using donated tissue samples to model age-related muscle changes in space. Her team also works with SpaceTango, a NASA-certified aerospace company, to design the CubeLab that flew to the International Space Station on multiple SpaceX missions. Looking ahead, Malany and her team are developing new ways to study astronaut-derived cells, including both skeletal and heart muscle, generated from blood samples. These “avatars” could help researchers track changes before, during and after space missions, providing an unprecedented window into how microgravity affects the human body. “Now we can study cells from individual astronauts and see how they respond over time,” Malany said. “This helps us understand the risks of long-term spaceflight and also gives us a platform for testing potential treatments for muscle-wasting conditions on Earth.” By using tissue chips, small, bioengineered devices that mimic the structure and function of human organs, scientists in space can gather data more quickly and accurately than with traditional animal studies, potentially accelerating the discovery of therapies for aging-related muscle loss. Looking to know more about this amazing research or connect with Siobhan Malany - simply click on her icon now to arrange an interview today.

View all posts
Powered by