Computational challenges in magnetic-confinement fusion physics

A Fasoli, S Brunner, WA Cooper, JP Graves, P Ricci… - Nature Physics, 2016 - nature.com
Magnetic-fusion plasmas are complex self-organized systems with an extremely wide range
of spatial and temporal scales, from the electron-orbit scales (∼ 10− 11 s,∼ 10− 5 m) to the …

[HTML][HTML] Development of a concept and basis for the DEMO diagnostic and control system

W Biel, M Ariola, I Bolshakova, KJ Brunner… - Fusion engineering and …, 2022 - Elsevier
An initial concept for the plasma diagnostic and control (D&C) system has been developed
as part of European studies towards the development of a demonstration tokamak fusion …

Progress in disruption prevention for ITER

EJ Strait, JL Barr, M Baruzzo, JW Berkery… - Nuclear …, 2019 - iopscience.iop.org
Key plasma physics and real-time control elements needed for robustly stable operation of
high fusion power discharges in ITER have been demonstrated in recent research …

Offline model-based reinforcement learning for tokamak control

I Char, J Abbate, L Bardóczi, M Boyer… - … for Dynamics and …, 2023 - proceedings.mlr.press
Control for tokamaks, the leading candidate technology for nuclear fusion, is an important
pursuit since the realization of nuclear fusion as an energy source would result in virtually …

Exploration via planning for information about the optimal trajectory

V Mehta, I Char, J Abbate, R Conlin… - Advances in …, 2022 - proceedings.neurips.cc
Many potential applications of reinforcement learning (RL) are stymied by the large numbers
of samples required to learn an effective policy. This is especially true when applying RL to …

ITER breakdown and plasma initiation revisited

PC De Vries, Y Gribov - Nuclear Fusion, 2019 - iopscience.iop.org
This paper revisits a number of key aspects of plasma initiation, aiming to clarify concepts,
provide definitions and improve understanding, in view of ITER First Plasma operation. It …

Advancing fusion with machine learning research needs workshop report

D Humphreys, A Kupresanin, MD Boyer, J Canik… - Journal of Fusion …, 2020 - Springer
Abstract Machine learning and artificial intelligence (ML/AI) methods have been used
successfully in recent years to solve problems in many areas, including image recognition …

Path-oriented early reaction to approaching disruptions in ASDEX Upgrade and TCV in view of the future needs for ITER and DEMO

M Maraschek, A Gude, V Igochine… - Plasma Physics and …, 2017 - iopscience.iop.org
Routine reaction to approaching disruptions in tokamaks is currently largely limited to
machine protection by mitigating an ongoing disruption, which remains a basic requirement …

Real-time-capable prediction of temperature and density profiles in a tokamak using RAPTOR and a first-principle-based transport model

F Felici, J Citrin, AA Teplukhina, J Redondo… - Nuclear …, 2018 - iopscience.iop.org
The RAPTOR code is a control-oriented core plasma profile simulator with various
applications in control design and verification, discharge optimization and real-time plasma …

Demonstration of tokamak discharge shutdown with shell pellet payload impurity dispersal

EM Hollmann, PB Parks, D Shiraki, N Alexander… - Physical review …, 2019 - APS
The first rapid tokamak discharge shutdown using dispersive core payload deposition with
shell pellets has been achieved in the DIII-D tokamak. Shell pellets are being investigated …