UI Looking At How Can Drones Help Wildland Firefighters

A University of Idaho researcher has developed an artificial intelligence system that could help firefighters better predict how wildfires will spread. Phinehas Lampman, a former North Idaho wildland firefighter, used drones equipped with thermal infrared cameras to capture real-time images of active fires. He then used machine learning to analyze the imagery and predict a fire’s rate of spread, intensity and radiant heat.

“Most incident commanders in the field rely on their vast experience to assess and ultimately predict wildfire movement,” said Lampman who worked as a firefighter for both the Clearwater-Potlatch Timber Protective Association and the Forest Service on engine crews and a hotshot crew in North Idaho.

Where Should Firefighters Make A Stand?

Lampman says those measurements could help incident commanders decide where to deploy firefighting resources — and where to make a stand to protect homes, highways and communities. The research found a Random Forest machine-learning model performed particularly well, requiring less training data while producing stronger predictions.

“Using repeat passes with drones that collected TIR imagery, we derived high-resolution metrics and trained an artificial neural network (ANN) and random forest (RF) models to predict rate of spread with low error,” Lampman said

AI Was Not Part Of The Initial Plan

U of I Professor Leda Kobziar said the technology combines real-time observations with existing knowledge of fire behavior, potentially providing more precise predictions as wildfire conditions become increasingly difficult to forecast.

“This is an important application of machine learning using AI techniques,” Kobziar said. “We had no intention initially to use AI to make these predictions, but Phinehas learned to create these models, and it became obvious that machine learning could be a good way to approach these questions.”

Click Here to check out Lampman's research.

If you have a story idea for the PNW Ag Network, call (509) 547-9791, or e-mail glenn.vaagen@townsquaremedia.com