{
  "abstract": "Direct simulation Monte Carlo (DSMC) resolves rarefied-gas dynamics without a constitutive closure, but finite-sample estimates of macroscopic moments converge at markedly different rates. We develop a non-intrusive, geometry-native machine learning reconstruction of the retained two-dimensional moment hierarchy: number density, two velocity components, translational temperature, three pressure-tensor components, and two heat-flux components. From three sampling blocks, the estimator corrects a structured prior learned from development data with a bounded term computed from the current observation, while preserving additive-moment consistency and the measured zero-frequency content. In cavity development tests, the final observation-conditioned estimator, whose prior is a trained MambaIR restoration network, reduces transverse-heat-flux error to 0.658 and 0.672 times that of a ten-block direct average at two rarefied conditions. For a hypersonic cylinder, a cylinder-centred estimator is fixed before evaluation on six new observation/reference pairs. It improves both global transverse heat flux and near-wall normal heat flux in every pair; the ratios of arithmetic-mean normalised root-mean-square errors (NRMSEs) are 0.846 and 0.793, and the Holm-adjusted one-sided exact probabilities are 0.03125.",
  "abstract_shown": true,
  "affiliations": [],
  "article_type": null,
  "arxiv": "2609.01637",
  "author_total": 1,
  "authors": [
    {
      "name": "Ehsan Roohi"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/1fdywzdznykke.bib",
  "cited_by": 0,
  "doi": "10.48550/arxiv.2609.01637",
  "fulltext_url": null,
  "id": "1fdywzdznykke",
  "issns": [],
  "landing_url": "https://arxiv.org/abs/2609.01637",
  "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.data-an"
    ],
    [
      "arxiv",
      "physics.flu-dyn"
    ],
    [
      "openalex",
      "2604|Gas Dynamics and Kinetic Theory"
    ]
  ],
  "openalex": "W7207751283",
  "pdf_url": "https://arxiv.org/pdf/2609.01637",
  "pmcid": null,
  "pmid": null,
  "published": "2026-09-01",
  "publisher": null,
  "ris": "https://research.draconitic.com/paper/1fdywzdznykke.ris",
  "sources": [
    {
      "first_seen": "2026-10-30T12:18:16Z",
      "native_id": "2609.01637",
      "source": "arxiv",
      "url": "https://arxiv.org/abs/2609.01637"
    }
  ],
  "subjects": [
    {
      "field": "physics",
      "origin": "arxiv:physics.data-an",
      "subfield": "computational"
    },
    {
      "field": "physics",
      "origin": "arxiv:physics.flu-dyn",
      "subfield": "fluid-dynamics"
    }
  ],
  "title": "Geometry-native machine learning reconstruction of DSMC moment fields with support monitoring",
  "title_text": "Geometry-native machine learning reconstruction of DSMC moment fields with support monitoring",
  "type": "preprint",
  "updated_at": "2026-10-30T12:18:16Z",
  "url": "https://research.draconitic.com/paper/1fdywzdznykke",
  "venue": "arXiv",
  "versions": []
}