Part of the difficulty in fighting wildfires is the inability to accurately predict their path of destruction. A Mizzou Engineering researcher is working to solve this critical problem.
Ming Xin, an associate professor of Mechanical and Aerospace Engineering, is partnering with researchers from the University of Kansas and Georgia State University on “Collaborative Autonomy and Safety for Teamed Human-Unmanned Aircraft Systems in Fast Evolving Wildfire Environment,” a four-year, $1.2 million grant from the U.S. Department of Agriculture and National Science Foundation.
The goal of the project is to develop a system that uses multiple unmanned aerial vehicles (UAVs) to gather critical environmental data, and by using a dynamic simulation model, make accurate predictions on the fire spread path and deliver the results in real-time to firefighters on the ground.
Xin is developing the autonomous guidance, navigation, and control system, which will allow the UAVs to collaboratively collect and process data on their own in order to facilitate the fire prediction, enhance firefighters’ safety, and make fire management more efficient.
“The traditional way is to use satellites, manned aircraft or ground sensors,” Xin said. “But these sensors cannot provide adequate temporal and spatial resolutions. Also, they are static. Fires are very dynamic. We need real-time data.
“If we use multiple UAVs, we can collect real-time data in very good resolution so we can precisely predict the fire spread.”
The ability to predict fire shifts can help teams more efficiently direct resources to places of greatest need. It can also help save lives by alerting firefighters in the midst of the blaze to potential issues before they become trapped in dangerous locations.
The simulation model will be developed by Georgia State and will utilize Xin’s UAV technology to gauge wind, terrain, vegetation and other factors and accurately make predictions. Kansas will host the flight tests.
“We get data from multiple UAVs, have advanced data assimilation technology so we can use that data, run the simulation, then predict what will happen in the next few minutes and hours — where the fire will go, and how fast,” Xin said.