☆ 4.3 Article

Data-driven model for divertor plasma detachment prediction

JOURNAL OF PLASMA PHYSICS (2022)

Related references

Note: Only part of the references are listed.

Article Multidisciplinary Sciences

Magnetic control of tokamak plasmas through deep reinforcement learning

Jonas Degrave et al.

Summary: Nuclear fusion using magnetic confinement, specifically in the tokamak configuration, is a promising method for sustainable energy. In this study, researchers introduce a previously undescribed architecture for the design of tokamak magnetic controllers, which autonomously learns to command the full set of control coils. This approach demonstrates unprecedented flexibility and generality in problem specification, leading to a notable reduction in design effort and the ability to produce new plasma configurations.

NATURE (2022)

Add to Collection

Article Computer Science, Theory & Methods

Enabling machine learning-ready HPC ensembles with Merlin

J. Luc Peterson et al.

Summary: This paper presents Merlin, a workflow framework for large ML-friendly ensembles of scientific HPC simulations. By incorporating distributed compute technologies, Merlin lowers the barrier for scientific subject matter experts to integrate ML into their analysis.

FUTURE GENERATION COMPUTER SYSTEMS-THE INTERNATIONAL JOURNAL OF ESCIENCE (2022)

Add to Collection

Article Physics, Fluids & Plasmas

Enhancement of detachment control with simplified real-time modelling on the KSTAR tokamak

D. Eldon et al.

Summary: Detachment control based on ion saturation current I-sat measurements has been implemented in the KSTAR tokamak, allowing for accurate tracking of target trajectories and adaptability to changing scenarios.

PLASMA PHYSICS AND CONTROLLED FUSION (2022)

Add to Collection

Article Physics, Fluids & Plasmas

Encoder-decoder neural network for solving the nonlinear Fokker-Planck-Landau collision operator in XGC

M. A. Miller et al.

Summary: An encoder-decoder neural network has been utilized to accelerate the Fokker-Planck-Landau collision operator, incorporating physics-inspired learning with conservation constraints in the loss function. The training has achieved a median relative loss of order 10(-4), but may be affected by drift nature in time steps. The run time of the operator's Picard iterative solver is O(n(2)), while the neural network training scales only as O(n).

JOURNAL OF PLASMA PHYSICS (2021)

Add to Collection

Article Instruments & Instrumentation

Measuring the electron temperature and identifying plasma detachment using machine learning and spectroscopy

C. M. Samuell et al.

Summary: A machine learning approach is used to measure electron temperature in tokamak plasma, showing good performance at low temperatures. Additionally, a classifier trained using machine learning can accurately identify plasma detachment states at a fast rate, demonstrating high accuracy.

REVIEW OF SCIENTIFIC INSTRUMENTS (2021)

Add to Collection

Article Physics, Fluids & Plasmas

Simulation of the SPARC plasma boundary with the UEDGE code

S. B. Ballinger et al.

Summary: The study investigates edge transport in the SPARC tokamak using the UEDGE code for various levels of carbon impurity and core power, finding that impurity seeding can reduce heat flux significantly and detachment of the plasma in the outer leg can lead to lower heat flux and temperatures. The detachment state is sensitive to boundary conditions, neutral pumping, and target plate tilt.

NUCLEAR FUSION (2021)

Add to Collection

Article Physics, Fluids & Plasmas

Uncovering turbulent plasma dynamics via deep learning from partial observations

A. Mathews et al.

Summary: This study demonstrates a physics-informed deep learning framework that accurately learns turbulent fields consistent with the two-fluid theory, providing a new paradigm for advanced plasma diagnostics and validation of magnetized plasma turbulence theories in challenging thermonuclear environments.

PHYSICAL REVIEW E (2021)

Add to Collection

Article Multidisciplinary Sciences

Improved surrogates in inertial confinement fusion with manifold and cycle consistencies

Rushil Anirudh et al.

PROCEEDINGS OF THE NATIONAL ACADEMY OF SCIENCES OF THE UNITED STATES OF AMERICA (2020)

Add to Collection

Article Physics, Fluids & Plasmas

Machine learning surrogate models for Landau fluid closure

Chenhao Ma et al.

PHYSICS OF PLASMAS (2020)

Add to Collection

Article Physics, Fluids & Plasmas

Neural network representability of fully ionized plasma fluid model closures

Romit Maulik et al.

PHYSICS OF PLASMAS (2020)

Add to Collection

Article Nuclear Science & Technology

Progress Toward Interpretable Machine Learning-Based Disruption Predictors Across Tokamaks

C. Rea et al.

FUSION SCIENCE AND TECHNOLOGY (2020)

Add to Collection

Article Nanoscience & Nanotechnology

Deep learning surrogate model for kinetic Landau-fluid closure with collision

Libo Wang et al.

AIP ADVANCES (2020)

Add to Collection

Article Physics, Fluids & Plasmas

Divertor heat flux challenge and mitigation in SPARC

A. Q. Kuang et al.

JOURNAL OF PLASMA PHYSICS (2020)

Add to Collection

Article Physics, Fluids & Plasmas

The role of particle, energy and momentum losses in 1D simulations of divertor detachment

B. D. Dudson et al.

PLASMA PHYSICS AND CONTROLLED FUSION (2019)

Add to Collection

Article Multidisciplinary Sciences

Predicting disruptive instabilities in controlled fusion plasmas through deep learning

Julian Kates-Harbeck et al.

NATURE (2019)

Add to Collection

Article Physics, Fluids & Plasmas

Machine learning for disruption warnings on Alcator C-Mod, DIII-D, and EAST

K. J. Montes et al.

NUCLEAR FUSION (2019)

Add to Collection

Article Physics, Fluids & Plasmas

Divertor power load studies for attached L-mode single-null plasmas in TCV

R. Maurizio et al.

NUCLEAR FUSION (2018)

Add to Collection

Article Physics, Fluids & Plasmas

Basic physical processes and reduced models for plasma detachment

P. C. Stangeby

PLASMA PHYSICS AND CONTROLLED FUSION (2018)

Add to Collection

Article Instruments & Instrumentation

Fast analysis of collective Thomson scattering spectra on Wendelstein 7-X

J. van den Berg et al.

REVIEW OF SCIENTIFIC INSTRUMENTS (2018)

Add to Collection

Article Materials Science, Multidisciplinary

Electron pressure balance in the SOL through the transition to detachment

A. G. McLean et al.

JOURNAL OF NUCLEAR MATERIALS (2015)

Add to Collection

Article Materials Science, Multidisciplinary

The new SOLPS-ITER code package

S. Wiesen et al.

JOURNAL OF NUCLEAR MATERIALS (2015)

Add to Collection

Article Nuclear Science & Technology

Edge-plasma models and characteristics for magnetic fusion energy devices

TD Rognlien et al.

FUSION ENGINEERING AND DESIGN (2002)

Add to Collection

© Peeref 2019-2024. All rights reserved.