hero image
Xilei Zhao - University of Florida. Gainesville, FL, US

Xilei Zhao

Assistant Professor | University of Florida

Gainesville, FL, UNITED STATES

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


Xilei Zhao is an assistant professor in transportation engineering in the Herbert Wertheim College of Engineering, where she leads the Smart, Equitable, Resilient Mobility Systems (SERMOS) Lab. She specializes in big data analytics and evacuation behavior modeling for wildfires and hurricanes, quantifying resilience for critical infrastructure systems, societal systems, communities, and modeling and planning for emerging travel modes (e.g., ridesourcing and micromobility).

Areas of Expertise (5)

Machine Learning

Public Transit

Hurricane Evacuation

Community Resilience

Artificial Intelligence

Media Appearances (3)

Lifting communities through improved public transit: UF part of USDOT-funded research in equitable transportation

UF Engineering School of Sustainable Infrastructure & Environment  online


The University of Florida (UF) and four other institutions were selected by the U.S. Department of Transportation (USDOT) to create a consortium to study equitable transit-oriented communities. Led by the University of New Orleans—the group, which also includes the Florida Atlantic University, the University of Utah and the University of Colorado Denver—was awarded a five-year, $10 million grant to the Center for Equitable Transit-Oriented Communities (CETOC).

view more

Escaping Hurricane Ian

The Atlantic  online


This week, Ian slammed into southwestern Florida as a Category 4 (almost 5) hurricane. The state is still very much in the process of assessing the damage: Emergency teams have rescued hundreds of stranded people, while some 1.9 million people remain without power. Officials have identified as many as 21 dead, and that number may still rise. Ahead of the storm’s landfall, Florida officials ordered the evacuation of about 2.5 million people. Xilei Zhao, an evacuations researcher, was not one of them.

view more

GPS data to aid evacuations

Engineering New Zealand  online


Wildfire is becoming an escalating problem around the world – fires are getting more common and severe. This change is driven partly by climate change, but also by the fact that Wildland-Urban Interface (WUI), the transition area between wilderness and land developed by human activity, is expanding. In recent years, wildfires have posed a threat to properties and human lives, requiring the evacuation of large numbers of people. Countries like Australia and the USA have experienced many wildfires in the past.

view more


Articles (3)

Evaluating shared e-scooters’ potential to enhance public transit and reduce driving

Science Direct

Xiang Yang, et. al


This study evaluates if and to what extent shared e-scooters can enhance public transit and reduce driving. Survey results from Washington D.C. and Los Angeles confirm that many have used shared e-scooters to connect with transit and to replace car trips. Mode choice models further suggest that males, non-Whites, and people without a college degree are more inclined to use shared e-scooters.

view more

Real-Time Forecasting of Dockless Scooter-Sharing Demand: A Spatio-Temporal Multi-Graph Transformer Approach

Institute of Electrical and Electronics Engineers (IEEE)

Yiming Xu, et. al


Accurately forecasting the real-time travel demand for dockless scooter-sharing is crucial for the planning and operations of transportation systems. Deep learning models provide researchers with powerful tools to achieve this task, but research in this area is still lacking. This paper thus proposes a novel deep learning architecture named Spatio-Temporal Multi-Graph Transformer (STMGT) to forecast the real-time spatiotemporal dockless scooter-sharing demand.

view more

Predicting and Assessing Wildfire Evacuation Decision-Making Using Machine Learning: Findings from the 2019 Kincade Fire

Springer Link

Ningzhe Xu, et. al


To develop effective wildfire evacuation plans, it is crucial to study evacuation decision-making and identify the factors affecting individuals’ choices. Statistic models (e.g., logistic regression) are widely used in the literature to predict household evacuation decisions, while the potential of machine learning models has not been fully explored. This study compared seven machine learning models with logistic regression to identify which approach is better for predicting a householder’s decision to evacuate.

view more





loading image