Princeton-led team develops AI for fusion plasma monitoring

October 27, 2025, 7:03AMANS Nuclear Cafe

A new AI software tool for monitoring and controlling the plasma inside nuclear fuel systems has been developed by an international collaboration of scientists from Princeton University, Princeton Plasma Physics Laboratory (PPPL), Chung-Ang University, Columbia University, and Seoul National University. The software, which the researchers call Diag2Diag, is described in the paper, “Multimodal super-resolution: discovering hidden physics and its application to fusion plasmas,” published in Nature Communications.

PPPL study points to better fusion plasma control

May 9, 2024, 12:00PMNuclear News
The image on the left shows the tokamak and 3D magnetic perturbation generated by 3D coils, with the purple-blue hues representing lower amplitude perturbations and the red representing higher amplitude perturbations. The image on the right is a closer view showing the top half of the tokamak and plasma. The coils are used to generate the magnetic field perturbations that produce the islands (blue). Another coil can also be found on the bottom of the machine. The injection system for the ECCD microwaves is depicted on top (red). These can be used to adjust the width of the islands. (Image: Qiming Hu / PPPL)

The combination of two previously known methods for managing plasma conditions can result in enhanced control of plasma in a fusion reactor, according to a simulation performed by researchers at the Department of Energy’s Princeton Plasma Physics Laboratory.