Officials at US Oak Ridge National Laboratory (ORNL) and artificial intelligence company Atomic Canyon have signed a memorandum of understanding (MOU) to streamline the licensing process for NPPs with artificial intelligence for licence application reviews.
The aim is to use high-performance computing to create high-fidelity simulations that ensure the safety of designs while accelerating licensing with artificial intelligence to automate aspects of the review process. The agreement was signed during the Nuclear Opportunities Workshop (NOW) at the Knoxville Convention Center.
“ORNL was critical to the development of nuclear energy more than 75 years ago, and we are committed to advancing the technologies needed to sustain and grow the nation’s nuclear capacity today,” ORNL Director Stephen Streiffer said. “The time is now. With new capabilities enabled by AI and partners like Atomic Canyon, we can help the nuclear industry unleash American energy.”
ORNL is home to DOE Office of Science user facilities including the High Flux Isotope Reactor and the Oak Ridge Leadership Computing Facility, which houses the Frontier supercomputer and other world-leading facilities for applied energy sciences. This enables companies such as Atomic Canyon to access tools for simulation, digital qualification, materials development and component testing.
“We’re entering into a new, radically more advanced era of nuclear power, and the demand for steady-state energy consumption is growing rapidly,” said Tom Evans, ORNL’s lead scientist on the project. “Agreements like this are exactly how we can meet those demands through innovative approaches that accelerate the process by which nuclear power is brought to the grid.”
Using ORNL’s Frontier, the world’s first exascale supercomputer, Atomic Canyon developed AI models designed specifically for the nuclear industry called FERMI, which powers Atomic Canyon’s Neutron AI platform. FERMI models enable intelligent search capabilities, allowing users to quickly locate relevant documents across vast repositories of technical documentation.
AI has the potential to save the industry vast amounts of time and labour by streamlining reporting requirements and accelerating licensing and regulatory compliance processes. The computing power of Frontier was necessary to teach FERMI models the technical language of the nuclear industry based on the vocabulary used in the more than 53m pages of nuclear documents contained within the NRC’s ADAMS database, the NRC’s official record-keeping system that documents the history of every reactor in the country.
Atomic Canyon’s Neutron AI Platform not only allows users to find information faster and more efficiently, but also provides clear and meaningful context to complex information, making it easier for nuclear power professionals to understand and develop problem-solving solutions.
“Our mission at Atomic Canyon is to build the most advanced generative AI platform for the nuclear industry,” Atomic Canyon CEO Trey Lauderdale said. “ORNL’s expertise in nuclear science and high-performance computing was critical for us to be able to build AI in a reliable format. We want to double-down on that relationship to build AI that can be used to help every reactor in America’s nuclear fleet.”
The agreement also allows Atomic Canyon to further develop Neutron Enterprise – a proprietary version of their Neutron AI platform, but with exclusive capabilities and enhanced cybersecurity.
