AI can predict and prevent fusion plasma instabilities in milliseconds

March 4, 2024, 2:59PMNuclear News
The Princeton Plasma Physics Laboratory. (Photo: PPPL)

A team of engineers, physicists, and data scientists from Princeton University and the Princeton Plasma Physics Laboratory (PPPL) have used artificial intelligence (AI) to predict—and then avoid—the formation of a specific type of plasma instability in magnetic confinement fusion tokamaks. The researchers built and trained a model using past experimental data from operations at the DIII-D National Fusion Facility in San Diego, Calif., before proving through real-time experiments that their model could forecast so-called tearing mode instabilities up to 300 milliseconds in advance—enough time for an AI controller to adjust operating parameters and avoid a tear in the plasma that could potentially end the fusion reaction.

To continue reading, log in or create a free account!

Related Articles

AI and productivity growth

May 19, 2025, 3:02PMNuclear News

This month’s issue of Nuclear News focuses on supply and demand. The “supply” part of the story highlights nuclear’s continued success in providing electricity to the grid more than 90...

Fusion Energy Week begins today

May 5, 2025, 3:01PMNuclear News

Excitement around fusion has only grown this year since the French magnetic confinement fusion tokamak known as WEST maintained a plasma for 1,337 seconds in February, toppling the...

ANFM 2025 is on the horizon

May 1, 2025, 3:01PMANS News

The first Advances in Nuclear Fuel Management (ANFM) conference in eight years is being held July 20–23, 2025, at the Sheraton Sand Key Resort in Clearwater Beach, Fla....