Diablo Canyon Nuclear Power Plant Leverages AI for Compliance

By Stephen Nellis

(Reuters) – California's only remaining nuclear power plant plans to use artificial intelligence tools to help it comply with new licensing requirements to keep the decades-old facility running.

Atomic Canyon, a startup based in San Luis Obispo, California, said on Wednesday it has signed a deal with Pacific Gas & Electric (PG&E) to install an AI software system called Neutron Enterprise at PG&E's Diablo Canyon facility. The deal’s value was not disclosed, but it aims to help PG&E sift through decades of documents to create plans to manage the plant's aging concrete and systems.

Commissioned in 1985 and located about halfway between San Francisco and Los Angeles, Diablo Canyon was once slated to shut down. However, California officials reversed course in 2022 to align with the state's carbon-reduction goals.

Maureen Zawalick, vice president of business and technical services at Diablo Canyon, stated that the facility has approximately 9,000 procedures and 9 million documents, many scanned from paper or microfiche. Under PG&E's federal license to operate the facility for 20 more years, they must devise plans to manage its age with information drawn from these decades-old documents.

Atomic Canyon's software, running on Nvidia-supplied computers, will read these documents and render them searchable in natural language. The startup collaborated with Oak Ridge National Laboratory in Tennessee to develop an AI model capable of understanding the specialized terminology prevalent in nuclear regulatory documents.

According to Trey Lauderdale, Atomic Canyon's founder, nuclear plants often have a vast amount of data, making document retrieval challenging. Many resources exist in microfiche without proper labels.

PG&E's Zawalick noted that the AI system could also assist with complex functions like maintenance scheduling, which requires understanding the interplay of different systems.

"Maintenance scheduling is labor intensive," Zawalick explained. "That's where we're going to gain a lot of efficiencies."