Researchers at Texas A&M University have developed an artificial intelligence tool that sorts disaster, weather and humanitarian reports to help emergency professionals find relevant information during a response. The work is led by postdoctoral researcher Dr. Bo Li, Dr. Ali Mostafavi and Kai Yin in the Zachry Department of Civil and Environmental Engineering.
The model uses a large language model to sort crisis-related information into three areas: disaster-related, weather-related and humanitarian information. It also classifies each post by event type, informativeness and humanitarian information type. In a recent study, the researchers tested it on a benchmark of human-annotated social media posts from multiple disaster events.
Li said the categories could help emergency personnel locate details such as storm updates, damage reports and requests for aid and rescue. The system is still under development and has not been used during an active disaster. Li said the team plans to build an AI agent that emergency professionals can talk to during a disaster.