A revolutionary licensing process aims to speed up the process for nuclear power plants in the U.S. by leveraging artificial intelligence. The Department of Energy’s Oak Ridge National Laboratory (ORNL) partnered with AI firm Atomic Canyon to jumpstart the new process. This collaboration aims to integrate AI into the license application reviews. According to the agencies, the lengthy process should “significantly accelerate.”

AI Acceleration For Nuclear Energy

The agreement was formalized during the Nuclear Opportunities Workshop (NOW) in Knoxville, Tennessee. According to the press release, the agreement outlines plans to use supercomputers to create high-fidelity simulations while AI automates the review process. Simulations ensure the safety of nuclear designs.

Researchers say the United States recently set “ambitious” deadlines for reactor design licensing and commissioning of new plants. Meeting those demands will require dynamic collaboration between public and private entities.

“The time is now,” ORNL Director Stephen Streiffer said. “With new capabilities enabled by AI and partners like Atomic Canyon, we can help the nuclear industry unleash American energy.” Streiffer also emphasized the lab’s role in nuclear energy and its commitment to advancing technologies that support nuclear expansion.

ORNL’s resources, such as the High Flux Isotope Reactor and the Frontier supercomputer, are crucial to a company like Atomic Cantion. Researchers say these facilities provide essential 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.”

An Efficient Collaboration

Atomic Canyon’s FERMI is a novel AI model designed specifically for the nuclear industry and utilizes ORNL’s Frontier supercomputer. FERMI models power Atomic Canyon’s Neutron AI platform, which allows it to search and quickly locate relevant documents. Because the nuclear industry is heavily regulated, licensing new reactors requires extensive research and reporting. According to the researchers, AI has the potential to dramatically reduce time and labor.

Frontier’s “immense” computing power was essential to training FERMI models on the nuclear industry’s complex language. This process reportedly involved processing over 53 million pages of nuclear documents. Atomic Canyon’s AI platform helps users find information effectively and provides clear context to complex data. As a result, it aids professionals in understanding and solving problems.

“ORNL’s expertise in nuclear science and high-performance computing was critical for us to be able to build AI in a reliable format,” Atomic Canyon CEO Trey Lauderdale said. “We want to double-down on that relationship to build AI that can be used to help every reactor in America’s nuclear fleet.”