How artificial intelligence technology could be a ‘game changer’ in fighting wildfires
As more people across the country see the effects of wildfires and smoke, scientists are turning to the promise of big data, technology and collaboration to prevent the spread of big fires.
“If you manage to stop it in the first couple of hours, it will be much easier to stop,” said Dr. Ilkay Altintas, founder and director of the WIFIRE laboratory at UC San Diego.
Accurate fire detection quickly increases the chances of localizing a fire. Altintas and her team have developed a platform called Firemap designed to reduce the response time of a wildfire attack.
The platform analyzes the data in new ways, starting with the collection of emergency call data, where callers often give a very general idea of the location of the fire.
To improve this accuracy, the platform relies on a mountain camera system called ALERTWildfire, built by the Scripps Institution of Oceanography, the University of Nevada at Reno, and the University of Oregon.
AI cameras scan the horizon looking for puffs of smoke. When smoke appears on multiple cameras, the system can triangulate the exact location of the fire.
This exact location is then quickly matched with local weather data and real-time video from the aircraft sent to the scene.
All this data allows the computer modeler to build a map that predicts the growth and direction of the fire.
In 2019, during a tick fire in Southern California, the lab said it was able to predict that embers would cross the main highway in Santa Clarita and send the fire to the other side. In response, the Los Angeles County Fire Department deployed resources to the other side of the highway to actively put out small fires caused by embers before the fires spread.
WIFIRE Firemap software has been developed and tested with major fire departments in Los Angeles, Ventura and Orange counties and is available for management throughout California for their initial firefighting needs.
“Knowing that this is where the fire is going right now and that this is exactly the direction in which it is moving is extremely valuable information,” California Fire Battalion Chief David Krassow told CBS News Sacramento about the capabilities of mountain chambers. “It really is a game changer.”
In addition to working on the reaction time problem, the lab is also developing technology to keep the fires on target, which are deliberately set to help clear the forest of debris in a more predictable and controlled manner.
At the national level, there is a movement to use more prescribed fire in order to better manage fire risk. However, there is a big backlog in fueling these fires. In California, for example, the state wants to burn a million acres a year by 2025, but only 110,000 acres were burned last year.
The use of prescribed fires is also under scrutiny after one went out of control last year and accidentally started the largest wildfire in New Mexico’s history.
Drawing on technology developed at Los Alamos National Laboratory, Altintas and her colleagues are developing highly detailed mapping software that shows things like the amount of vegetation in a forest, the height of the canopy, and how dry it is.
“Knowing what is going on there and the local fire situation is becoming very important,” Altintash said.
Using artificial intelligence, they can run a computer model that shows how a given fire will behave in a real environment even before it is set, and possibly reduce the risk of a prescribed fire getting out of hand.
“The problem of forest fires is solvable if we do some things right together,” Altintash added.
