Predicting fusion ignition at the National Ignition Facility with physics-informed deep learning
B. K. Spears, S. Brandon, D. T. Casey, J. E. Field, Jim Gaffney, Kelli Humbird, A. L. Kritcher, Michael Kruse, Eugene Kur, Bogdan Kustowski, S. Langer, D. H. Munro, R. Nora, J. L. Peterson, D. J. Schlossberg, Paul J. Springer, A. B. Zylstra
Abstract
An inertial confinement fusion experiment, carried out at the National Ignition Facility, has achieved ignition by generating fusion energy exceeding the laser energy that drove the experiment. Prior to the experiment, a generative machine learning model that combines radiation hydrodynamics simulations, deep learning, experimental data, and Bayesian statistics was used to predict, with a probability greater than 70%, that ignition was the most likely outcome for this shot.
Topics & Concepts
National Ignition FacilityIgnition systemInertial confinement fusionBayesian probabilityFusionArtificial intelligenceNuclear engineeringComputer scienceSimulationPhysicsLaserAerospace engineeringEngineeringOpticsLinguisticsPhilosophyLaser-Plasma Interactions and DiagnosticsNuclear Physics and ApplicationsCold Fusion and Nuclear Reactions