Federal dollars support AI/machine learning for fusion research

August 25, 2020, 3:00PMNuclear News

The Department of Energy on August 19 announced several awards to research teams applying artificial intelligence and machine learning to fusion energy. The planned total funding of $21 million is targeted at projects with time frames of up to three years; $8 million in fiscal year 2020 funding has already been committed to the work. Delivery of the balance-of-project funding will depend on future congressional appropriations.

“These awards will enable fusion researchers to take advantage of recent rapid advances in artificial intelligence and machine learning,” said Chris Fall, director of the DOE’s Office of Science. “AI and ML will help us to accelerate progress in fusion and keep American scientists at the forefront of fusion research.”

Specifics: The selected awards will seek to improve operational efficiencies at Office of Science fusion facilities by automating data analysis workflows and enabling real-time control algorithms while making use of supercomputing resources at DOE national laboratories. The awards were made to multiple institutions for five topics:

  • Machine Learning for Real-time Fusion Plasma Behavior Prediction and Manipulation
  • FusMatML: Machine Learning Atomistic Modeling for Fusion Materials
  • EFIT-AI: Machine Learning and Artificial Intelligence Assisted Equilibrium Reconstruction for Tokamak Experiments and Burning Plasmas
  • Accelerating Radio Frequency Modeling Using Machine Learning
  • Developing Real-Time Accelerated Cognitive Simulation to Advance HEDLP [High Energy Density Laboratory Plasmas] with High-Rep-Rate Lasers

Institutions receiving awards:

  • Argonne National Laboratory
  • Carnegie Mellon University
  • General Atomics
  • Lawrence Berkeley National Laboratory
  • Lawrence Livermore National Laboratory
  • Los Alamos National Laboratory
  • the Massachusetts Institute of Technology
  • Princeton Plasma Physics Laboratory
  • Princeton University
  • Sandia National Laboratories
  • SLAC National Accelerator Laboratory
  • Tech-X Corporation
  • the University of Tennessee
  • the University of Wisconsin

Background: Awards were made based on competitive peer review under a funding opportunity announcement released in March 2020 along with a parallel, companion announcement for DOE laboratories. The effort is part of the DOE’s Scientific Discovery through Advanced Computing program, a joint effort of the Offices of Fusion Energy Sciences (FES) and Advanced Scientific Computing Research within the DOE’s Office of Science.

A full list of projects can be found on the FES homepage under the heading What’s New.

Related Articles