Princeton Plasma Physics Laboratory is leading a new initiative with the goal of using AI technology to accelerate the development of fusion energy research through high-fidelity computer simulations. The project includes national laboratories, universities, technology companies, and other partners.

Simulation, Technology, and Experiment Leveraging Learning-Accelerated Research enabled by AI (STELLAR-AI) has been developed as part of the Department of Energy’s Genesis Mission, which was established by presidential executive order last year to speed up the application of AI in scientific research.

A key component needed for the National Spherical Torus Experiment–Upgrade (NSTX-U), the flagship fusion facility currently under repair at the Department of Energy’s Princeton Plasma Physics Laboratory (PPPL), has been delivered to the lab’s New Jersey campus.

According to the Department of Energy’s Princeton Plasma Physics Laboratory, recent simulations and analysis demonstrate that the design of its flagship fusion facility, the National Spherical Torus Experiment Upgrade (NSTX-U), which is currently under repair, could serve as a model for an economically attractive next-generation fusion pilot plant.

PPPL physicist Dan Boyer. (Photo: Amber Boyer/Kiran Sudarsanan)

Researchers at the Department of Energy’s Princeton Plasma Physics Laboratory are using machine learning to predict electron density and pressure profile shapes on the National Spherical Torus Experiment-Upgrade (NSTX-U), the flagship fusion facility at PPPL that is currently under repair.

The hope is that such predictions, generated by artificial neural networks, could improve the ability of NSTX-U researchers to optimize the components of experiments that heat and shape the fusion plasma.

“This is a step toward what we should do to optimize the actuators,” said PPPL physicist Dan Boyer, author of the paper, “Prediction of electron density and pressure profile shapes on NSTX-U using neural networks,” published by Nuclear Fusion, a journal of the International Atomic Energy Agency. “Machine learning can turn historical data into a simple model that we can evaluate quickly enough to make decisions in the control room or even in real time during an experiment.”

The NSTX-U “umbrella.” Photo: Elle Starkman/ PPPL Office of Communications

The Department of Energy on September 8 announced funding for research at the National Spherical Tokamak Experiment Upgrade (NSTX-U), an Office of Science user facility at the DOE’s Princeton Plasma Physics Laboratory in Princeton, N.J.

Total planned funding is $17 million for the NSTX-U work over five years in duration. As much as $6 million in fiscal year 2020 dollars and out-year funding could be available this year, contingent on congressional appropriations and satisfactory progress.

The initiative will support experiments, data analysis, and computer modeling and simulation of plasma behavior. A major focus will be on the start of laying the scientific groundwork for a next-generation facility through better understanding of the behavior of plasmas in spherical tokamaks, the DOE said.