{
  "abstract": "Inverting point-source emissions from sparse atmospheric observations is difficult because emission rate, release height, wind speed, turbulence, and plume morphology can compensate for one another. We present NeuPlume, a neural-physical framework that formulates inversion as observation-guided generation and selection of complete three-dimensional concentration fields. A Lagrangian stochastic model builds a scenario-specific forward library, a conditional neural field compresses the simulated fields, and a latent diffusion model learns their conditional distribution. During inversion, diffusion posterior sampling generates candidate fields on a coarse-to-fine parameter grid, and NeuPlume returns the parameters and field that best match the observations. Across 30 synthetic cases, the selected fields achieve a mean spatial correlation of 0.942 and a mean emission-rate error of 13.6 %. Matched stress tests show that both observation geometry and transport-model fidelity govern inversion quality: trajectory-concentrated sampling weakens full-field reconstruction, while unrepresented transport alters parameter identification and, for effective plume rise, also degrades field reconstruction. Applied to four UAV methane transects above a coal-mine ventilation shaft, NeuPlume yields known- U minimum-loss emission estimates of 5.27–15.85 kt yr ⁻¹ and exposes wind-speed and height-boundary sensitivities under model mismatch. NeuPlume thus provides an extensible methodology for jointly estimating source parameters and concentration fields: additional transport regimes can be incorporated through regime-specific simulation ensembles and neural-model retraining.",
  "abstract_shown": true,
  "affiliations": [
    "State Key Laboratory of Information Engineering in Surveying Mapping and Remote Sensing (Wuhan, China)"
  ],
  "article_type": null,
  "arxiv": null,
  "author_total": 2,
  "authors": [
    {
      "name": "Lei Wang",
      "orcid": "0009-0004-9851-2895"
    },
    {
      "affs": [
        0
      ],
      "name": "Xin Ma"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/f6kgr2xtx4ggw.bib",
  "cited_by": 0,
  "doi": "10.5194/acp-26-14185-2026",
  "fulltext_url": null,
  "id": "f6kgr2xtx4ggw",
  "issns": [
    "1680-7324"
  ],
  "landing_url": "https://acp.copernicus.org/articles/26/14185/2026/",
  "language": null,
  "licence": "CC-BY-4.0",
  "licence_label": "CC BY 4.0",
  "licence_source": "article",
  "licence_url": "https://creativecommons.org/licenses/by/4.0/",
  "metadata_licence": null,
  "native_subjects": [
    [
      "openalex",
      "2306|Atmospheric and Environmental Gas Dynamics"
    ]
  ],
  "openalex": "W7164358106",
  "pdf_url": "https://acp.copernicus.org/articles/26/14185/2026/acp-26-14185-2026.pdf",
  "pmcid": null,
  "pmid": null,
  "published": "2026-10-09",
  "publisher": "Copernicus GmbH",
  "ris": "https://research.draconitic.com/paper/f6kgr2xtx4ggw.ris",
  "sources": [
    {
      "first_seen": "2026-10-30T12:20:34Z",
      "native_id": "10.5194/acp-26-14185-2026",
      "source": "crossref",
      "url": "https://acp.copernicus.org/articles/26/14185/2026/"
    }
  ],
  "subjects": [
    {
      "field": "earth",
      "origin": "openalex:2306|Atmospheric and Environmental Gas Dynamics",
      "subfield": "climate"
    }
  ],
  "title": "NeuPlume: generative inversion of atmospheric point-source emissions from sparse observations",
  "title_text": "NeuPlume: generative inversion of atmospheric point-source emissions from sparse observations",
  "type": "peer-reviewed",
  "updated_at": "2026-10-30T12:20:34Z",
  "url": "https://research.draconitic.com/paper/f6kgr2xtx4ggw",
  "venue": "Atmospheric Chemistry and Physics",
  "versions": [
    {
      "doi": "10.5194/egusphere-2026-2769",
      "pid": null,
      "relation": "preprint",
      "title": null,
      "venue": null
    }
  ]
}