{
  "abstract": "We present a proof-of-principle study demonstrating a conditional generative foundation model for self-organizing magnetized plasma turbulence. Built on a multichannel flow-matching framework with a spectral decomposition strategy, the model is trained on direct numerical simulations of 2D modified Hasegawa-Wakatani (MHW) turbulence across the hydrodynamic to adiabatic parameter range. Without retraining, this \\textit{single} model successfully performs three distinct downstream tasks: (i) unconditional generation of statistically faithful quasi-steady-state snapshots that recover the directional energy spectra and amplitude statistics, from which statistical transport quantities, including turbulent flux and effective diffusivity, alongside their uncertainties, are inferred directly; (ii) super-resolution from $4\\times$ and $8\\times$ downsampled observations to reconstruct fine-scale turbulence and large-scale zonal structures; and (iii) full-field inpainting from sparse spatial observations covering as little as $\\sim 10\\%$ of the domain. The generated fields faithfully reproduce regime-dependent turbulence vs. zonal-flow states and energy partitioning. Under extreme sparsity the long-correlation zonal flows are pinned by only a handful of observations, while the residual uncertainty concentrates in the small-scale turbulent fluctuations. These results establish flow-matching generative models as powerful, unified surrogates for state generation, statistical inference, and sparse-data reconstruction, providing a scalable baseline for 3D plasma turbulence and experimental applications.",
  "abstract_shown": true,
  "affiliations": [],
  "article_type": null,
  "arxiv": "2610.36155",
  "author_total": 4,
  "authors": [
    {
      "name": "Junyi Guo"
    },
    {
      "name": "Meet H. Parikh"
    },
    {
      "name": "Jian-Xun Wang"
    },
    {
      "name": "Ben Zhu"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/0ahfb8qvs0fje.bib",
  "cited_by": 0,
  "doi": "10.48550/arxiv.2610.36155",
  "fulltext_url": null,
  "id": "0ahfb8qvs0fje",
  "issns": [],
  "landing_url": "https://arxiv.org/abs/2610.36155",
  "language": null,
  "licence": "CC-BY-4.0",
  "licence_label": "CC BY 4.0",
  "licence_source": "article",
  "licence_url": "http://creativecommons.org/licenses/by/4.0/",
  "metadata_licence": "CC0-1.0",
  "native_subjects": [
    [
      "arxiv",
      "physics.plasm-ph"
    ],
    [
      "openalex",
      "3109|Model Reduction and Neural Networks"
    ]
  ],
  "openalex": "W7224130594",
  "pdf_url": "https://arxiv.org/pdf/2610.36155",
  "pmcid": null,
  "pmid": null,
  "published": "2026-10-26",
  "publisher": null,
  "ris": "https://research.draconitic.com/paper/0ahfb8qvs0fje.ris",
  "sources": [
    {
      "first_seen": "2026-10-30T12:35:50Z",
      "native_id": "2610.36155",
      "source": "arxiv",
      "url": "https://arxiv.org/abs/2610.36155"
    }
  ],
  "subjects": [
    {
      "field": "physics",
      "origin": "arxiv:physics.plasm-ph",
      "subfield": "plasma"
    }
  ],
  "title": "A generative foundation model for 2D magnetized plasma turbulence",
  "title_text": "A generative foundation model for 2D magnetized plasma turbulence",
  "type": "preprint",
  "updated_at": "2026-10-30T12:35:50Z",
  "url": "https://research.draconitic.com/paper/0ahfb8qvs0fje",
  "venue": "arXiv",
  "versions": []
}