{
  "abstract": "Full-order surrogates for high-dimensional nonlinear flows are often unnecessary when applications require only selected degrees of freedom. We propose reduced-order models that bypass full-state reconstruction by deploying graph neural networks (GNNs) directly on coarse meshes. Applied to parameterized 2D/3D confined cylinder flows and an unevenly heated cavity over Reynolds/Rayleigh-number ranges, the models generalize to unseen conditions and accurately predict sparse probe locations and integrated quantities. Coarse-mesh GNNs match or outperform finer-mesh surrogates while reducing training time and memory, even for 3D chaotic dynamics. A dynamics-informed adaptive sampling strategy guided by frequency-spectrum variations reduces maximum errors by an order of magnitude versus uniform sampling at negligible cost. Coarse-mesh training also makes noise-augmented multi-step unrolling practical, improving long-horizon autoregressive predictions. The approach outperforms parametric DMD, sparse MLPs, U-Nets, and Fourier neural operators at lower cost, and enables system identification and state estimation from sparse observations. These results show that coarse-mesh representations, adaptive sampling, and noise-augmented unrolled training form an efficient framework for reduced-order modeling of parameterized unsteady flows without solver-resolution reconstruction.",
  "abstract_shown": true,
  "affiliations": [],
  "article_type": null,
  "arxiv": "2610.37986",
  "author_total": 4,
  "authors": [
    {
      "name": "Brener Ramos"
    },
    {
      "name": "William R. Wolf"
    },
    {
      "name": "Tarcísio C. D. Oliveira"
    },
    {
      "name": "Scott T. M. Dawson"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/fwgcr4gtwqwr9.bib",
  "cited_by": 0,
  "doi": "10.48550/arxiv.2610.37986",
  "fulltext_url": null,
  "id": "fwgcr4gtwqwr9",
  "issns": [],
  "landing_url": "https://arxiv.org/abs/2610.37986",
  "language": null,
  "licence": "LicenseRef-arXiv-nonexclusive-1.0",
  "licence_label": "arXiv licence",
  "licence_source": "article",
  "licence_url": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
  "metadata_licence": "CC0-1.0",
  "native_subjects": [
    [
      "arxiv",
      "cs.LG"
    ],
    [
      "arxiv",
      "physics.flu-dyn"
    ]
  ],
  "openalex": null,
  "pdf_url": "https://arxiv.org/pdf/2610.37986",
  "pmcid": null,
  "pmid": null,
  "published": "2026-10-27",
  "publisher": null,
  "ris": "https://research.draconitic.com/paper/fwgcr4gtwqwr9.ris",
  "sources": [
    {
      "first_seen": "2026-10-30T12:36:23Z",
      "native_id": "2610.37986",
      "source": "arxiv",
      "url": "https://arxiv.org/abs/2610.37986"
    }
  ],
  "subjects": [
    {
      "field": "physics",
      "origin": "arxiv:physics.flu-dyn",
      "subfield": "fluid-dynamics"
    }
  ],
  "title": "Predicting Sparse Observables in Parameterized Unsteady Flows Using Coarse-Mesh Graph Neural Networks",
  "title_text": "Predicting Sparse Observables in Parameterized Unsteady Flows Using Coarse-Mesh Graph Neural Networks",
  "type": "preprint",
  "updated_at": "2026-11-01T12:20:44Z",
  "url": "https://research.draconitic.com/paper/fwgcr4gtwqwr9",
  "venue": "arXiv",
  "versions": []
}