Scientists will explore using artificial intelligence to help create the fusion energy sources of tomorrow, it has been announced.
The team, made up of researchers from the University of Rochester and Hewlett Packard Enterprise, will develop machine learning to help predict, design, and improve laser-fusion implosions for inertial fusion energy, the University of Rochester says.
The move comes thanks to nearly $3 million provided by the US Department of Energy, and follows a string of recent advancements in laser fusion over the past year.
“Despite many years of laser-driven inertial confinement fusion research, there is not a clear path to the high-energy gains required for inertial fusion energy,” said principal investigator Riccardo Betti, LLE’s chief scientist and the Robert L. McCrory Professor in the Department of Mechanical Engineering and in the Department of Physics and Astronomy. “However, we now have a wealth of experimental data that we can harness with machine learning to systematically correct the simulations and guide real-time adjustments to experiments.”
The University of Rochester says that scientists have struggled for years to use lasers to generate fusion energy. The process, called inertial confinement fusion, involves filling targets with fuel and then compressing and heating them to initiate nuclear fusion reactions.
However, tests at laser facilities such as OMEGA at Rochester’s Laboratory for Laser Energetics (LLE) have generated less energy than simulations predicted, the university says.
Now, the team will use the OMEGA experimental and LLE radiation hydrodynamic simulation databases to develop machine-learning models for improved implosion design and a deeper understanding of nonlinear fusion physics.
The project, which is set to be completed by 2026, involves LLE fusion physicists and artificial intelligence and machine learning experts from Rochester’s Department of Computer Science and from Hewlett Packard Enterprise.