Uncovering turbulent plasma dynamics via deep learning from partial observations
- OSTI
One of the most intensely studied aspects of magnetic confinement fusion is edge plasma turbulence which is critical to reactor performance and operation. Drift-reduced Braginskii two-fluid theory has for decades been widely applied to model boundary plasmas with varying success. Towards better understanding edge turbulence in both theory and experiment, we demonstrate that a novel multi-network physics-informed deep learning framework constrained by partial differential equations can accurately learn turbulent fields consistent with the two-fluid theory from partial observations of electron pressure which is not otherwise possible using conventional equilibrium models. This technique presents a novel paradigm for the advanced design of plasma diagnostics and validation of magnetized plasma turbulence theories in challenging thermonuclear environments.
- Research Organization:
- Massachusetts Inst. of Technology (MIT), Cambridge, MA (United States). Plasma Science and Fusion Center; Univ. of Texas, Austin, TX (United States); Lawrence Livermore National Lab. (LLNL), Livermore, CA (United States)
- Sponsoring Organization:
- USDOE Office of Science (SC), Fusion Energy Sciences (FES); USDOE National Nuclear Security Administration (NNSA)
- DOE Contract Number:
- SC0014264; FC02-08ER54966; FG02-04ER54742; AC52-07NA27344
- OSTI ID:
- 1882600
- Country of Publication:
- United States
- Language:
- English
Uncovering turbulent plasma dynamics via deep learning from partial observations
|
journal | August 2021 |
Similar Records
Uncovering turbulent plasma dynamics via deep learning from partial observations
Journal Article
·
Thu Aug 12 20:00:00 EDT 2021
· Physical Review. E
·
OSTI ID:1813020