University of Houston engineers develop AI model for pandemic prediction

A team of engineers from the University of Houston has developed an AI model to analyze the impact of international air travel on the spread of COVID-19. The study, published in Nature, highlights regions such as Western Europe, the Middle East, and North America as significant contributors to the pandemic due to their high volume of outgoing flights.

"Our work provides a robust deep learning-based tool to study global pandemics and is of key relevance to policymakers for making informed decisions regarding air traffic restrictions during future outbreaks," stated Hien Van Nguyen, lead researcher and associate professor at UH.

The research involved a computer program called Dynamic Weighted GraphSAGE. This tool examines large networks with changing data like flight schedules to identify patterns that influence disease transmission. "It looks at spatiotemporal graphs, or how things are linked across both space (different locations) and time to better understand how this affects things like the spread of diseases or transportation patterns," explained Nguyen.

Van Nguyen and his team conducted perturbation analysis by testing small changes in their model. This allowed them to assess which aspects of air traffic most significantly affect virus spread and identify where flight reductions could effectively decrease global cases.

"We propose air traffic reduction strategies that can significantly impact controlling the pandemic with minimal disruption to human mobility," said Nguyen. He added that reducing flights from Western Europe could notably lower global COVID-19 cases. Although based on COVID-19 data, these findings are applicable to other pandemics.

Additional researchers from the Houston Methodist Research Institute contributed to this project.