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

Data centers planned at four DOE sites

July 25, 2025, 7:01AMNuclear News

At the end of his July 15 speech at the inaugural Pennsylvania Energy and Innovation Summit, President Trump promised that “a lot more [was] going to be announced in the coming week” for...

Westinghouse awarded $180M ITER contract

July 3, 2025, 9:30AMNuclear News

Westinghouse Electric Company announced that it has signed a $180 million contract with the ITER Organization for the assembly of the vacuum vessel for the fusion reactor being built in...