AI helps automate nuclear reactor licensing process at INL

AI helps automate nuclear reactor licensing process at INL
by Clarence Oxford
Los Angeles CA (SPX) Jul 22, 2025
The Idaho National Laboratory (INL) has partnered with Microsoft to apply Azure cloud and artificial intelligence (AI) technologies to streamline the complex process of nuclear reactor licensing and permitting.

Backed by funding from the U.S. Department of Energy's Office of Nuclear Energy via the National Reactor Innovation Center, the collaboration aims to speed up how reactor developers generate required engineering and safety documentation.

"This is a big deal for the nuclear licensing process," said Jess Gehin, associate laboratory director for Nuclear Science and Technology at INL. "Introducing AI technologies will enhance efficiency and accelerate the deployment of advanced nuclear technologies."

Microsoft developed an Azure AI-based solution capable of ingesting and analyzing technical documents to produce draft reports needed for construction permits and operational licenses. These reports, while still requiring human review, are critical to U.S. Nuclear Regulatory Commission (NRC) and DOE regulatory applications.

Traditionally, generating these safety and engineering reports is labor-intensive, involving the integration of data and language from various sources. The new AI-driven tool reduces both the time and cost required to compile them.

"Artificial intelligence technologies can enable a new frontier of innovation and advancement by automating routine processes, accelerating development and freeing scientists and researchers to focus on the real complex challenges affecting our society," said Heidi Kobylski, vice president for Federal Civilian Agencies at Microsoft. "We are honored to collaborate with INL to help address the complicated process of nuclear licensing to potentially help speed the approval of nuclear reactors necessary to support our increasing energy demands."

INL officials say the tool has broad potential use across licensing applications for nuclear energy systems, including both traditional light water reactors and next-generation designs that use alternative fuels, coolants, and materials. The system can support documentation for facilities regulated under both NRC and DOE authorities.

"AI holds significant potential to accelerate the process to design, license, and deploy new nuclear energy for the nation's increasing energy needs," said Chris Ritter, division director of Scientific Computing and AI at INL. "INL looks forward to early research to evaluate the applicability of generative AI in the nuclear licensing space."

The effort builds on an earlier collaboration between Microsoft and INL. In 2023, they worked with Idaho State University students to create the first-ever digital twin of a nuclear reactor, a virtual model of the AGN-201 reactor, using Microsoft's Azure cloud platform.