Predicting fusion ignition at the National Ignition Facility with physics-informed deep learning

• 成果类型: Article
• 署名作者: Spears, Brian K.; Brandon, Scott; Casey, Dan T.; Field, John E.; Gaffney, Jim A.; Humbird, Kelli D.; Kritcher, Andrea L.; Kruse, Michael K. G.; Kur, Eugene; Kustowski, Bogdan; Langer, S.; Munro, Dave; Nora, Ryan; Peterson, J. Luc; Schlossberg, Dave J.; Springer, Paul; Zylstra, Alex
• 署名单位: United States Department of Energy (DOE); Lawrence Livermore National Laboratory
• 刊物名称: SCIENCE
• ISSN/ISSBN: 0036-12577
• DOI: 10.1126/science.adm8201
• 发表日期: 2025-08-14
• 页码: 727-731
• 关键词: inertial confinement fusion; simulations; targets

摘要

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.