Climate change is leading to intense and deadly wildfire seasons, stretching the firefighting resources to the limit. However, analytical tools like Suppression Difficulty Index (SDI) are helping firefighters to improve their chance of reducing wildfires by bringing machine learning and big data into the picture. Firefighters are turning to AI tools for building control lines and agendas.
For decades, fire managers have been relying on weather patterns and analytical data on fire behavior. Now, they are utilizing predictive technologies and artificial intelligence to plan wildfire management schedules and manage analytics of their terrain in real-time.
Researchers like Mr. Dunn hope their ML models and tools can ensure that the scarce fire resources are deployed as efficiently as possible. Firefighters are currently using Potential Operational Delineations (PODs), a popular tool that Mr. Dunn helped develop. PODs use advanced spatial analytics that allows teams to plan the location to take on wildfires even before they break out. The POD tool superimposes several statistical models like SDI over a map of a region. This aids fire managers in planning out their control lines and plans of attack in advance.
“You will never take the personal element out of fighting fires, but people make bad decisions under stress – they can’t crunch all this data on their own. This is about reducing the uncertainty, and helping firefighters make better decisions,” said Brad Pietruszka, who has been using analytical tools like PODs since 2017. He is a fire manager at San Juan, a 1.8-million-acre National Forest.
Another complex tool is the Potential Control Locations (PCLs) algorithm, which suggests where to build control lines during a fire. It considers information about ridges, flat grounds, fuel present in the ground, geography, distance from roads and public spaces, and samples it across historical fire perimeters.
Tools like SDI, PODs, PCLs, and others provide crucial information to firefighters during out-of-control wildfire seasons. As firefighters turn to AI to fight wildfires, researchers have stressed that these tools are efficient only when coupled with insights from people living in wildfire-prone areas.