Texas A&M University researchers are developing an artificial intelligence tool designed to assist emergency managers in sorting through large volumes of information during crises such as hurricanes. The system filters and categorizes disaster, weather, and humanitarian reports to help professionals quickly locate relevant data for decision-making.
The project is led by postdoctoral researcher Dr. Bo Li, along with Dr. Ali Mostafavi and Kai Yin, all within the Zachry Department of Civil and Environmental Engineering. The team uses a large language model to process the stream of information that emerges during emergencies. This includes monitoring weather conditions, damage reports, public requests for assistance, and search-and-rescue needs.
In a recent study on crisis-related social media classification, the researchers utilized a benchmark of human-annotated social media posts from multiple disaster events. The model categorizes crisis-related information into three primary areas: disaster-related, weather-related, and humanitarian information. It further classifies each post by event type, informativeness, and specific humanitarian information type.
Dr. Li stated that organizing information into categories allows emergency personnel to more easily locate details relevant to their needs, such as storm condition updates or damage reports. The system is currently under development and has not been deployed during an active disaster.
“The team plans to build an AI agent that emergency professionals can talk to when disaster strikes,” Li said. “Ultimately, we want to move from classification toward a more interactive AI system that can better support situational awareness during disasters.”
