Application of Machine Learning To High-Repetition-Rate Laser-Plasma Physics on The Path to Inertial Fusion Energy




Abstract:
One of the grand challenges of the plasma physics community is mastering controlled nuclear fusion as an energy source, with one approach being inertial confinement fusion (ICF). ICF is an extremely complex scientific and engineering problem that spans many physical regimes and requires precise control of the system over many orders of magnitude in space and time. Recent scientific achievements have raised our confidence in the feasibility of this goal, but much work remains to make inertial fusion energy a reality. An important research thrust has been the implementation of machine learning on ICF and specifically on the high-repetition-rate laser systems needed to make fusion energy practical. With an eye to technology transfer, there has been work attempting to operate, understand, and control of HRRLs on smaller laser-plasma experiments and associated modeling efforts. Presented here will be a series of examples of how machine learning is applied to these topics at LLNL.

CITATION:

IEEE format

B. Đorđević, P. Bremer, G. Williams, T. Ma, D. Mariscal, “Application of Machine Learning To High-Repetition-Rate Laser-Plasma Physics on The Path to Inertial Fusion Energy,” in Sinteza 2023 - International Scientific Conference on Information Technology, Computer Science, and Data Science, Belgrade, Singidunum University, Serbia, 2023, pp. 2-8. doi:10.15308/Sinteza-2023-2-8

APA format

Đorđević, B., Bremer, P., Williams, G., Ma, T., Mariscal, D. (2023). Application of Machine Learning To High-Repetition-Rate Laser-Plasma Physics on The Path to Inertial Fusion Energy. Paper presented at Sinteza 2023 - International Scientific Conference on Information Technology, Computer Science, and Data Science. doi:10.15308/Sinteza-2023-2-8

BibTeX format
Download

RefWorks Tagged format
Download