SDG&E, Qualcomm and Scripps team up to curb wildfires and extreme weather with AI
San Diego Gas & Electric, Qualcomm and UC San Diego's Scripps Institution of Oceanography on Monday announced a collaboration that will use an artificial intelligence initiative called Edge Alert Sentinel, or EAS, to battle wildfire and extreme weather events across the region.
Aimed at detecting and analyzing conditions in real time, EAS is designed to process data so that utilities and emergency responders act faster at critical moments.
"By working with Qualcomm Technologies and UC San Diego, we're bringing world-class technology and science together, so intelligence lives where the risk lives - on the front lines - and communities are safer because of it," SDG&E President Scott Crider said in a statement.
EAS is currently being installed on Palomar Mountain, where the system will soon examine wind, weather and environmental data that influence wildfire behavior and the impacts of conditions such as Santa Ana winds, drought and flash floods.
The technology is anticipated to be up and running - and learning - in late August or September.
“Over the last many years, we’ve created so much data,” Brian D’Agostino, SDG&E meteorologist and vice president of wildfire and climate science, said in a phone interview. “What (EAS) does, it’s enhancing data processing capabilities and it’s connecting dots between data that we just wouldn’t be able to do otherwise.”
Southern California is vulnerable to some of the most complex weather and fire conditions in the country and the region’s terrain can lead to unpredictable and rapidly changing danger.
EAS aims to integrate environmental sensors, AI computing and atmospheric science to generate insights almost instantly when emergencies unfold, rather than minutes later in distant data centers.
For example, D’Agostino said when hot Santa Anas blow through San Diego and raise the risk of wildfire ignition, the winds hit the peaks of mountains first.
“It almost drops in on you from above,” he said. “So by using (UC San Diego) sensors on the peaks of all the mountains, it’s going to give us an indicator and a bit of advance warning of about 20 to 40 minutes before those strongest winds start hitting the valley floors below, where all the people are.”
In parallel, Qualcomm and SDG&E are working to extend the same AI applications to field devices that can protect physical grid assets through the use of drones.
"Through this collaboration, we're intending to bring real-time intelligence directly to the front lines of wildfire response," Nakul Duggal, Qualcomm Technologies’ executive vice president and group general manager of Automotive, Industrial and Embedded IoT, and Robotics, said in a statement. "By combining on-site AI with advanced sensing and connectivity, we're helping deliver faster, more reliable insights where conditions are changing - so responders can assess risk and act with greater speed and confidence."
At the core of the deployment is an AI gateway platform that can work in extremely harsh weather conditions.
The platform is powered by a pair of state-of-the-art chips: The Qualcomm Dragonwing IQ9 neural-processing unit that’s capable of delivering up to 100 trillion operations per second and the Snapdragon X35 Modem-RF System.
Together, the platform can process data right from the mountaintop and send it directly to SDG&E’s control center via the utility’s private cellular network. The analytics and telemetry data will help identify emerging risks faster. That will strengthen decision-making, improve safety and enhance overall grid resilience.
Through the collaboration, Qualcomm Technologies will provide advanced on-device AI processing capabilities; SDG&E will contribute its operational expertise, grid infrastructure and weather data networks; and the Scripps Institution of Oceanography will provide long-standing observational data and scientific expertise to enhance modeling and real-time analysis.
Scripps has been making real-time observations of atmospheric conditions throughout San Diego County for about 25 years.
"With this new onsite AI capability, we’re moving beyond observation to predicting impact in real time - at the exact moment and place where danger emerges,” Frank Vernon, director of the UC Scripps Institute of Oceanography High Performance Wireless Research and Education Network, said in a news release announcing EAS.
The initiative is designed to scale to other regions that face similar extreme weather and wildfire risks.
In the coming months, SDG&E, Qualcomm and Scripps will evaluate the performance of EAS at Palomar Mountain - which, at 6,140 feet, has long been a vital place to monitor wildfire and extreme-weather events in the region - with plans to expand the AI technology to additional sites starting next year.
D’Agostino said to date, the collaboration has not added to the bills SDG&E customers pay.
“All of the data already exists,” D’Agostino said. “We’re just leveraging data that’s already existing to support the community.”
This is not the first time that SDG&E has used artificial intelligence to bolster resistance to wildfire and extreme weather conditions. For years, the utility’s meteorology team has incorporated AI and advanced forecasting tools that leverage weather data and partnerships with scientific institutions and the National Weather Service.
Since wildfires in 2007 ravaged large swaths of San Diego County, SDG&E has spent more than $6 billion of ratepayer dollars to reduce the risk of widespread fires.
That includes building what is widely considered a leading-edge Wildfire and Climate Resilience Center, placing 337.4 miles of power lines underground since 2020 and replacing wooden power poles with fire-resistant steel poles.
SDG&E helps support a weather network with UC San Diego that includes 130 cameras that stream views of high-fire risk areas. The system includes 225 stations that measure wind speed, temperature and humidity every 10 minutes.
Copyright 2026 Tribune Content Agency. All Rights Reserved.
This story was originally published June 8, 2026 at 4:42 PM.