By Belle Lin

A revival in nuclear power -- partly fed by ravenous demand from data centers for artificial intelligence -- is leading to greater interest in harnessing AI to make those nuclear plants more efficient.

The Energy Department's Argonne National Laboratory, based in Lemont, Ill. and known for its work on nuclear reactors, has developed an AI-based tool that can assist with reactor design and help operators run nuclear plants, according to Richard Vilim, a senior nuclear engineer within the lab's nuclear science and engineering division.

Argonne's tool, called the Parameter-Free Reasoning Operator for Automated Identification and Diagnosis, or PRO-AID, marks a technological leap in a field that saw its heyday in the last quarter of the 20th century.

"The nuclear plants were built over 30 years ago," Vilim said, "so they're kind of dinosaurs when it comes to technology."

Today, nearly all of the nation's 94 operating nuclear reactors have had their licenses extended, and together still provide almost 20% of U.S. electricity. Their average age is roughly 42, according to the U.S. Energy Information Administration.

Argonne's plan is to offer PRO-AID to new, tech-forward nuclear builds, but it's also eyeing the so-called dinosaurs, some of which are being resurrected by companies like Amazon and Microsoft to help power their AI data centers. The global push for AI is poised to fuel a sharp rise in electricity demand, with consumption from data centers expected to more than double by the end of the decade, the International Energy Agency said Thursday.

The owners of roughly a third of U.S. nuclear plants are in talks with tech companies to provide electricity for those data centers, the Wall Street Journal has reported.

PRO-AID performs real-time monitoring and diagnostics using generative AI combined with large language models that notify and explain to staff when something seems amiss at a plant. It also uses a form of automated reasoning -- which uses mathematical logic to encode knowledge in AI systems -- to mimic the way a human operator asks questions and comes to understand how the plant is operating, Vilim said.

The tool can also help improve the efficiency of the personnel needed to operate a nuclear plant, Vilim said. That's especially important as older employees leave the workforce. "If we can hand off some of these lower-level capabilities to a machine, when someone retires, you don't need to replace him or her," he said.

Compared with gas-powered plants -- which are newer, and more automated with digital monitoring tools -- the technology at nuclear plants is far behind, Vilim added. Part of the efficiency in updating technology will come from consolidating the monitoring staff at a utility's nuclear plants at a single, centralized location -- much as gas-powered plants already do.

For legacy nuclear plants, however, it's not always obvious that the technology is worth the cost, said Vilim. PRO-AID, a tool that can be licensed to a software developer or nuclear supplier, hasn't yet found its way into a commercial nuclear plant.

While some power plants might want to update with technology, it's also a challenge to take power off the grid for an extended period of time in order to upgrade it, said Bob Johnson, an analyst at market research and IT consulting firm Gartner.

"The utilities are faced with, 'Is there sufficient value in putting this in? Or do we have what we need and we just go to the finish line, which might be just 20 years away?'" Vilim said.

Bill Gates-founded TerraPower, one of a newer generation of nuclear companies, has been using advanced computer modeling to design its reactor technologies since its start in the early aughts, the company said. TerraPower's Natrium reactor will be the first to be designed and modeled "from inception to commercialization in a completely digital environment," said Chris Levesque, the company's president and chief executive.

The Sam Altman-backed nuclear startup Oklo has been using AI to do design analysis on its reactors. With the help of those tools, it's possible to reduce the amount of time needed to run high-fidelity simulation cases, said Jacob DeWitte, Oklo's co-founder and chief executive.

Still, it will take time for AI to fully arrive in commercial nuclear power, he said.

"It is a big accelerator, it's a massive productivity accelerant," DeWitte said. "But to be candid, I think nuclear is really, really early in the days of this."

Write to Belle Lin at belle.lin@wsj.com

(END) Dow Jones Newswires

April 11, 2025 07:00 ET (11:00 GMT)

Copyright (c) 2025 Dow Jones & Company, Inc.