UC Davis Electrical and Computer Engineering

ECE Alum, Claudio Lopez Osses, M.S. ’20, Ph.D. ’22, is accelerating the next generation of nuclear science through the use of artificial intelligence at Crocker Nuclear Laboratory, or CNL, at the University of California, Davis.

Nuclear labs like CNL contain some of the most complicated machines ever built, such as particle accelerators. For decades, scientists have relied on sophisticated control systems that are meticulously maintained and calibrated.

In fact, these machines are so complex that only a highly skilled and trained individual on the nuclear lab’s team can understand, monitor and maintain them. This means that when a problem arises, it is not only very difficult for the team to address but also to return the system to its normal state.

The control center of the cyclotron in the Crocker Nuclear Lab in John Jungerman Hall at UC Davis. Alum Claudio Lopez Osses is using AI to automate oversight on complicated control systems, such as this one, to improve safety and efficiency in nuclear labs. (Gregory Urquiaga/ UC Davis)

To address this problem, Lopez Osses, who joined CNL as an R&D electrical engineer in 2023, is integrating AI systems into CNL’s control systems for nuclear machines. The AI system functions like that specialized team member, serving as the source of knowledge on how the system works and how to keep it running. Beyond automating what was once a time-consuming and delicate process, the AI system has demonstrated the ability to predict problems before they occur — something that was previously almost impossible.

Full article:

In On-Campus Lab, Alum Advances Nuclear Lab Control Systems with AI Electrical and computer engineer Claudio Lopez Osses, M.S. ’20, Ph.D. ’22, is accelerating the next generation of nuclear science through the use of artificial intelligence at Crocker Nuclear Laboratory, or CNL, at the University of California, Davis.

Congratulations to Achintha Wijesinghe on his successful PhD defense!

Achintha’s research advances next-generation wireless systems through generative AI, semantic communication, and federated learning. His work develops generative models for semantic-level transmission and efficient image compression, allowing networks to communicate meaning rather than raw data. He also designs federated learning frameworks that adapt these models across heterogeneous devices, enabling scalable and privacy-preserving intelligence for future 6G networks