SDG&E, Qualcomm Deploy Edge AI for Wildfire Detection
Edge Alert Sentinel processes environmental data on-site to accelerate emergency response during rapidly changing conditions.
San Diego Gas & Electric, Qualcomm Technologies, and UC San Diego's Scripps Institution of Oceanography have launched Edge Alert Sentinel (EAS), a collaboration that deploys artificial intelligence directly at monitoring sites to accelerate wildfire and extreme-weather response.
The initiative, announced June 8, 2026, places AI processing capabilities at the point of data collection rather than routing information to remote cloud servers. The first system is being installed on Mt. Palomar in Southern California, where it will analyze wind, weather, and environmental data in near real-time.
Why it matters
Wildfire conditions in Southern California can shift within minutes, making response speed critical. By eliminating the latency of cloud-based processing, edge AI enables utilities and emergency responders to act on environmental intelligence faster—potentially reducing damage and saving lives during rapidly evolving fire events.
How the technology works
EAS uses a ruggedized edge AI gateway powered by Qualcomm's Dragonwing IQ9 processor, which features a neural-processing unit capable of 100 trillion operations per second. The system integrates environmental sensors with on-device machine learning models developed through Edge Impulse's MLOps platform.
Data and predictive alerts are transmitted to SDG&E's control center via the utility's private cellular network. This architecture allows the system to continue analyzing conditions even when connectivity is compromised during severe weather.
"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," said Scott Crider, president of SDG&E, according to the announcement.
Parallel infrastructure efforts
Qualcomm Technologies and SDG&E are also applying similar edge AI approaches to automated inspections of utility infrastructure through autonomous aerial operations. This extends the intelligence-at-the-edge model to physical grid assets.
Academic and operational integration
Scripps Institution of Oceanography contributes decades of atmospheric observation data and scientific expertise to enhance modeling accuracy. Frank Vernon, director of Scripps' High Performance Wireless Research and Education Network, noted that the institution has been making real-time atmospheric observations throughout San Diego County since 2000.
"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," Vernon said in the announcement.
Deployment timeline
During the upcoming Public Safety Power Shutoff season, the partners will evaluate the Mt. Palomar deployment's performance. Expansion to additional sites is planned for next year, with broader regional rollout targeted for 2027.
While developed for Southern California's specific wildfire risks—including Santa Ana winds, drought, and varied terrain—the approach is designed to scale to other regions facing climate-driven extreme weather events.
Details were first reported by Sempra in a press release.
This is an original analysis by the Omega editorial team. Source reporting: AI Watch.
Want systems like this working for your business?
Book a Call
