In California , firefighters are employing artificial intelligence ( AI ) to detect wildfires, utilizing video feeds from over 1,000 strategically positioned cameras across the state. These cameras are connected to an AI system known as ALERTCalifornia, which notifies first responders when mobilization is necessary.
As an illustration of the program’s potential, ALERT California AI recently identified a fire that ignited at 3 a.m. local time in the remote Cleveland National Forest, about 50 miles east of San Diego. Despite the darkness and sleeping residents, AI alerted a fire captain who promptly dispatched around 60 firefighters, resulting in the rapid containment of the fire within 45 minutes.
DigitalPath
Engineers from the University of California San Diego collaborated with DigitalPath, an AI company based in Chico, California, to develop the platform .The initiative harnesses 1,038 cameras installed by various public agencies and power utilities across the state, each capable of remote 360-degree rotation.
Since its launch on July 10, the Artificial Intelligence system has demonstrated instances of detecting fires before individuals made 911 calls, although a comprehensive report is still pending.Neal Driscoll, a geology and geophysics professor at UCSD and principal investigator of ALERTCalifornia, noted that the current sample size is too small to draw firm conclusions.
California Fire (Cal Fire) envisions this technology becoming a model for other states and countries, particularly in light of the increasing severity and frequency of wildfires globally due to climate change. Suzann Leininger, a Cal Fire intelligence specialist, highlighted the universal applicability of the system.
“Video feeds”
The AI learning process involves specialists reviewing recorded video feeds to validate the system’s fire identification accuracy. The AI is improving rapidly with ongoing reviews conducted by specialists throughout the state.
Beyond the camera network, the platform gathers extensive additional data, including aerial surveys for vegetation assessment and Earth’s surface mapping. Drones and aircraft collect infrared and other wavelength data not perceptible to the human eye.
During winter, the system measures atmospheric rivers and snowpack. The UCSD team also captures information about burn scars and their impacts on erosion, sediment dispersion, water quality, and soil quality.
This data, accessible to private companies and researchers, holds potential for modeling fire behavior and unanticipated AI applications in environmental studies. The extreme climate calls for technological solutions to address pressing challenges, emphasized Driscoll, “We’re in extreme climate right now. So we give them the data, because this problem is bigger than all of us. We need to use technology to help move the needle, even if it’s a little bit.”