Metraipolis › archive › dc_b375ca3e2ad8

Physics-Informed Kolmogorov-Arnold Networks for Grad-Shafranov Tokamak Equilibria — arXiv:2609.23846

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.23846
License (as archived)
CC0-1.0
Archived
2026-10-09T23:41:26.569Z
SHA-256 of the archived text
95ffe58eb8836f6916ac974d11310d37553a65e9d94f0be0324ca85f8101d943
Stable URL of this page
https://metraipolis.com/documento/dc_b375ca3e2ad8

How to cite

Physics-Informed Kolmogorov-Arnold Networks for Grad-Shafranov Tokamak Equilibria — arXiv:2609.23846 — arXiv (en), https://arxiv.org/abs/2609.23846 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_b375ca3e2ad8 (Metraipolis archive dc_b375ca3e2ad8, sha256 95ffe58eb8836f6916ac974d11310d37553a65e9d94f0be0324ca85f8101d943)
BibTeX
@misc{dcb375ca3e2ad8,
  title = {Physics-Informed Kolmogorov-Arnold Networks for Grad-Shafranov Tokamak Equilibria — arXiv:2609.23846},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.23846},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_b375ca3e2ad8; sha256 95ffe58eb8836f6916ac974d11310d37553a65e9d94f0be0324ca85f8101d943},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.23846. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

We employ equation-driven, physics-constrained deep learning to solve the fixed-boundary Grad-Shafranov (GS) equilibrium problem, constructing axisymmetric magnetohydrodynamic equilibria with tokamak-relevant characteristics. Equilibria across linear (Solov'ev) and nonlinear profile functions are constructed using Physics-Informed Kolmogorov-Arnold Networks (KANs) that approximate GS solutions while satisfying appropriate boundary conditions. A highly nonlinear pressure profile recreating high-confinement mode phenomenology, such as pressure pedestals and significant bootstrap current components, is also considered. To enable efficient convergence, guided training schemes are employed, specifically homotopy-based continuation curriculum learning and transfer learning via pretrained networks. While computing nonlinear equilibria employing standard Multi-Layer Perceptrons under unguided physics-informed training remains an elusive or computationally inefficient task, our framework overcomes this limitation. Specifically, we demonstrate that the combination of three key elements, namely KAN architecture, guided training schemes, and the self-scaled Broyden optimization method, enables stable, efficient, and accurate equilibrium computation with simultaneous profile parameter identification in view of equilibrium constraints.

Tema degli esploratori: fisica e astronomia (retro-catalogo arXiv: annunci del 2026-09-22 in physics.comp-ph).
Categorie arXiv: Plasma Physics (physics.plasm-ph) ; Computational Physics (physics.comp-ph).
Pagina del lavoro: https://arxiv.org/abs/2609.23846 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-09T22:46:47.390Z dalla pagina https://arxiv.org/catchup/physics.comp-ph/2026-09-22?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).