An Inverse Grad-Shafranov Neural Network Approach to Tokamak Magnetic Control

Abstract

A new approach to tokamak magnetic control enabling high-precision plasma shaping and novel real-time adaptability is experimentally demonstrated on the Tokamak a Configuration Variable (TCV). The method is motivated by the insight that, under appropriate assumptions, a real-time inverse Grad-Shafranov solver approximates an optimal control policy for plasma boundary regulation. Building on this, a control architecture is developed in which classical controllers enforce operational constraints while a fast surrogate model provides a real-time inverse mapping from the desired plasma boundary to Poloidal Field Coil currents. Experimental results on TCV demonstrate improved plasma shaping with respect to the standard discharge preparation procedure --- albeit without explicit real-time shape feedback --- while enabling flexible response to asynchronous events. It is shown that a single network provides satisfactory performance across a range of plasma magnetic configurations. Real-time adaptivity is demonstrated in simulation, and partially in experiment, through adaptive strike point motion and early termination in response to a real-time trigger. These results suggest a viable path toward magnetic control architectures that reduce reliance on dense diagnostic coverage while maintaining high-accuracy plasma shaping, with potential relevance for future fusion power plant operation.

Physics-Informed Kolmogorov-Arnold Networks for Grad-Shafranov Tokamak Equilibria
D. A. Kaltsas, A. Kuiroukidis, J. Liu +2
arXiv20 Sep 2026PreprintarXiv licenceFull textComputational physics Plasma physicsarXiv
Geodesic Acoustic Modes in pair plasmas confined in tokamak magnetic fields
Alessandro Biancalani
arXiv21 Sep 2026PreprintCC BY-SA 4.0Full textPlasma physicsarXiv
Impact of magnetic drift configuration on the edge radial electric field in the TCV tokamak
S. Rienäcker, L. Vermare, P. Hennequin +8
arXiv25 Sep 2026PreprintCC BY-NC-SA 4.0Full textPlasma physicsarXiv
Experimental validation of a fast control-oriented, physics-informed surrogate model for plasma equilibrium reconstruction in the TCV tokamak
M. Grandin, A. Mele, C. Galperti +5
arXiv23 Sep 2026PreprintarXiv licenceFull textPlasma physicsarXiv
From Forecasting to Feedback: Evaluating Learned Dynamics for Tokamak Control
Guoyang Shi, Siqi Ding, Xuanhe Wang +7
arXiv1 Nov 2026PreprintCC BY 4.0Full textPlasma physicsarXiv

Cite

BibTeX RIS

BibTeX

@misc{wang2026inverse,
  title = {{An Inverse Grad-Shafranov Neural Network Approach to Tokamak Magnetic Control}},
  author = {Allen M. Wang and Adriano Mele and Cosmas Heiß and Cristian Galperti and Zander Keith and Alessandro Pau and Antoine Merle and Olivier Sauter and Daniel Gonzalez Castiñeiras and Francesco Carpanese and Federico Felici and Mark Dan Boyer and Cristina Rea and TCV Team and EUROfusion Tokamak Exploitation Team},
  howpublished = {arXiv},
  year = {2026},
  month = sep,
  doi = {10.48550/arxiv.2608.23976},
  eprint = {2608.23976},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2608.23976},
}

RIS

TY  - UNPB
TI  - An Inverse Grad-Shafranov Neural Network Approach to Tokamak Magnetic Control
AU  - Allen M. Wang
AU  - Adriano Mele
AU  - Cosmas Heiß
AU  - Cristian Galperti
AU  - Zander Keith
AU  - Alessandro Pau
AU  - Antoine Merle
AU  - Olivier Sauter
AU  - Daniel Gonzalez Castiñeiras
AU  - Francesco Carpanese
AU  - Federico Felici
AU  - Mark Dan Boyer
AU  - Cristina Rea
AU  - TCV Team
AU  - EUROfusion Tokamak Exploitation Team
PY  - 2026
DA  - 2026/09/01
PB  - arXiv
DO  - 10.48550/arxiv.2608.23976
UR  - https://arxiv.org/abs/2608.23976
AB  - A new approach to tokamak magnetic control enabling high-precision plasma shaping and novel real-time adaptability is experimentally demonstrated on the Tokamak a Configuration Variable (TCV). The method is motivated by the insight that, under appropriate assumptions, a real-time inverse Grad-Shafranov solver approximates an optimal control policy for plasma boundary regulation. Building on this, a control architecture is developed in which classical controllers enforce operational constraints while a fast surrogate model provides a real-time inverse mapping from the desired plasma boundary to Poloidal Field Coil currents. Experimental results on TCV demonstrate improved plasma shaping with respect to the standard discharge preparation procedure --- albeit without explicit real-time shape feedback --- while enabling flexible response to asynchronous events. It is shown that a single network provides satisfactory performance across a range of plasma magnetic configurations. Real-time adaptivity is demonstrated in simulation, and partially in experiment, through adaptive strike point motion and early termination in response to a real-time trigger. These results suggest a viable path toward magnetic control architectures that reduce reliance on dense diagnostic coverage while maintaining high-accuracy plasma shaping, with potential relevance for future fusion power plant operation.
ER  -

Abstract

Related

Cite