AI Accelerates Fusion Energy Grid Integration

New DOE project aims to speed up stellarator fusion device design using AI and digital models

Feb. 3, 2026 at 8:55pm

Got story updates? Submit your updates here. ›

A project led by the U.S. Department of Energy's Princeton Plasma Physics Laboratory is using artificial intelligence (AI) and digital models to accelerate the design of complex fusion devices known as stellarators. The StellFoundry project focuses on replacing lengthy calculations in the design process with faster AI-powered approximations, and enabling separate stellarator computer programs to work together for more complete simulations in less time. Researchers predict these innovations could accomplish in milliseconds what now takes hours or days, helping to make fusion a viable source of electricity.

Why it matters

Expanding the nation's energy portfolio by making fusion a viable source of electricity is a key priority, but the design of fusion devices like stellarators involves sifting through enormous amounts of data. The StellFoundry project aims to use AI and digital models to dramatically speed up this design process, which could help accelerate the development of commercial fusion energy and strengthen U.S. leadership in this critical technology.

The details

The StellFoundry project is led by PPPL and comprises around 30 researchers from 10 organizations, including universities, software companies and national labs. It focuses on two main innovations: replacing lengthy calculations with fast AI-powered approximations, and enabling separate stellarator computer programs to work together for more complete and efficient simulations. The team believes these advances could cut design timelines from hours/days down to milliseconds, allowing researchers to quickly test a large number of possible stellarator configurations.

  • StellFoundry is supported by the DOE's Advanced Scientific Computing Research program and Fusion Energy Sciences, and is part of the DOE's Scientific Discovery through Advanced Computing program.
  • The project aligns with the DOE's new Genesis Mission to accelerate scientific discovery using AI, as well as the DOE's recently released Fusion Science and Technology Roadmap.

The players

Princeton Plasma Physics Laboratory (PPPL)

A U.S. Department of Energy national laboratory that has continuously used advanced computer models to increase understanding of fusion plasma and design innovative fusion systems.

Michael Churchill

The head of AI for Science and digital engineering at PPPL and principal investigator of the StellFoundry project.

Robert Hager

A PPPL research physicist and member of the StellFoundry team.

Jean Paul Allain

The associate director for Fusion Energy Sciences at the DOE's Office of Science.

DOE's Office of Science

The lead federal agency supporting fundamental scientific research for energy and the environment, and the nation's largest supporter of basic research in the physical sciences.

Got photos? Submit your photos here. ›

What they’re saying

“When designing stellarators, computation has an outsized return on investment. I'm excited about the possibility of giving stellarator designers the tools they need to make the process faster.”

— Michael Churchill, Head of AI for Science and digital engineering at PPPL

“StellFoundry directly advances the DOE Fusion Science and Technology Roadmap by accelerating the integration of advanced computation, AI and digital engineering into fusion system design.”

— Jean Paul Allain, Associate director for Fusion Energy Sciences at the DOE's Office of Science

“But the more the tools are combined and the more they can interact, the more accurate the calculations will be at the very beginning. That's what you get from an effective framework - software tools talking to each other and producing better results with fewer steps.”

— Robert Hager, PPPL research physicist

What’s next

The StellFoundry team is making progress, including plans to create a digital surrogate for a divertor, the part of a fusion system that removes unwanted plasma particles and waste heat. The team is also looking forward to overcoming some fundamental hurdles along the way to completion, such as getting different computer codes to work together effectively.

The takeaway

By using AI and digital models to dramatically accelerate the design of fusion devices like stellarators, the StellFoundry project could help make fusion energy a viable and economical source of electricity, strengthening U.S. leadership in this critical clean energy technology.