AI accelerates fusion energy research

By John Greenwald

Image by Eliot Feibush/PPPL and Julian Kates-Harbeck/Harvard University

Artificial intelligence could speed the development of safe, clean and abundant energy from fusion, the same process that powers the sun and stars. Scientists at the U.S. Department of Energy’s Princeton Plasma Physics Laboratory (PPPL) are using AI to forecast disruptions that can halt fusion reactions and damage the doughnut-shaped devices that house the reactions. Led by William Tang, a PPPL physicist and lecturer with the rank of professor at Princeton, the project has demonstrated the ability to predict disruptions within 30 milliseconds, the amount of time required for use in ITER, the next-generation fusion facility under construction in France. “This opens a promising new chapter in the effort to bring unlimited energy to Earth,” said Steven Cowley, PPPL director and Princeton professor of astrophysical sciences.