Skip to main content

Share story

Science

DOE demonstrates AI tools to accelerate nuclear reactor licensing

A person wearing an orange jumpsuit and white helmet sits in a chair facing two computer screens showing technical diagrams against a blue background. Image: Primary
The U.S. Department of Energy, in collaboration with Idaho National Laboratory, Argonne National Laboratory, Microsoft and Everstar, has demonstrated the use of artificial intelligence tools to convert a safety analysis document into sections equivalent to a U.S. Nuclear Regulatory Commission license application. The team applied Everstar's Gordian AI solution, built on the Microsoft Azure platform, to the Preliminary Documented Safety Analysis for the National Reactor Innovation Center's generic high temperature gas reactor. The tool produced a 208-page document in one day. The same task typically requires a team of people between four and six weeks. Gordian was designed for nuclear-grade technical work. It includes physics and engineering tools and uses semantic ontology mapping to compute and verify output rather than infer it. The AI also identified missing or incomplete information required for a complete NRC application. An expert subsequently evaluated the output for accuracy, missing information, consistency, grammar and structure. The review found that the document demonstrated quality, rigor and depth and that the tool correctly identified its own gaps in data knowledge. Rian Bahran, deputy assistant secretary for nuclear reactors, said the partnership has the potential to transform how industry prepares its regulatory submissions and deploys nuclear energy while upholding the highest standards of safety and compliance. Kevin Kong, chief executive and founder of Everstar, said the company is partnering with INL to accelerate regulatory review and commercialization. Carmen Krueger, corporate vice president for U.S. federal at Microsoft, said the work shows how secure, scalable AI technologies can address key energy challenges. The demonstration is part of efforts under the Genesis Mission. The Department of Energy recently announced 293 million dollars in competitive funding to advance national science and technology challenges, including one focused on expediting nuclear energy deployment.
Sources
In this story
Published by Tech & Business, a media brand covering technology and business. This story was sourced from DOE and reviewed by the T&B editorial agent team.
Back to Newswire
Keep reading
Full wire
AI Science
AI Science

Google researchers demonstrate ten-minute AI-generated video

Google researchers say their video-generation frameworks produced a ten-minute film while keeping characters and settings consistent across shots. The work combines planning, visual memory and repeated review of generated material...

Science Infrastructure
Science Infrastructure

NASA selects Teledyne for lunar power system development

NASA has selected Teledyne Energy Systems for a collaboration to develop its Hydrogen Electrical Power System for space use, the company said. Under a Space Act Agreement, Teledyne will work with NASA's Glenn and Johnson centers t...

AI Science
AI Science

MIT researchers test lightweight suicide risk tool on crisis texts

MIT researchers reported that a lightweight model estimated suicide risk in previously unseen crisis text conversations by looking for language tied to 49 risk factors. They developed and tested it using de-identified texts from a...