{
  "abstract": "Frequency continuation does not improve every neural representation, and better velocity recovery need not imply better prediction of unseen waveforms. We compare a velocity grid with total-variation regularization, an adapted sinusoidal coordinate network (SIREN), and a frozen image generator with a full-grid residual in two-dimensional acoustic full-waveform inversion. All methods use the same frozen SWEEP discretization, acquisition, observations, background, and budget of 1,500 shot--model gradient evaluations. Three exposed synthetic targets represent inclined layering, curved layering, and a high-contrast curved interface drawn from a fault-labelled family. With 2-to-10 Hz continuation, the generative-residual model attains velocity RMSEs of 218.7, 108.0, and 341.9 m/s, compared with 232.5, 100.3, and 412.9 m/s for Grid+TV. Thus the latter wins on curved layering, while the former improves model RMSE by 5.9% and 17.2% on the other targets. Grid+TV nevertheless predicts held-out 10 Hz shots better on all three. SIREN is worse than the common background in every cell; continuation worsens two targets but improves one. A five-weight TV sensitivity study preserves the CurveFault model-error ranking. An equal-budget variational extension fails both recovery and interval coverage. These results establish conditional rankings, not universal superiority or an isolated spectral-bias mechanism. Full-grid residuals also prevent attributing gains uniquely to the generator. We advocate joint reporting of model recovery, unseen-shot prediction, optimization cost, and negative outcomes when auditing neural FWI.",
  "abstract_shown": true,
  "affiliations": [],
  "article_type": null,
  "arxiv": "2609.31251",
  "author_total": 3,
  "authors": [
    {
      "name": "Ziye Yu"
    },
    {
      "name": "Xin Liu"
    },
    {
      "name": "Yuqi Cai"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/8ts5srp77h7vg.bib",
  "cited_by": 0,
  "doi": "10.48550/arxiv.2609.31251",
  "fulltext_url": null,
  "id": "8ts5srp77h7vg",
  "issns": [],
  "landing_url": "https://arxiv.org/abs/2609.31251",
  "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.geo-ph"
    ],
    [
      "openalex",
      "1908|Seismic Imaging and Inversion Techniques"
    ]
  ],
  "openalex": "W7214680156",
  "pdf_url": "https://arxiv.org/pdf/2609.31251",
  "pmcid": null,
  "pmid": null,
  "published": "2026-09-25",
  "publisher": null,
  "ris": "https://research.draconitic.com/paper/8ts5srp77h7vg.ris",
  "sources": [
    {
      "first_seen": "2026-10-30T12:24:52Z",
      "native_id": "2609.31251",
      "source": "arxiv",
      "url": "https://arxiv.org/abs/2609.31251"
    }
  ],
  "subjects": [
    {
      "field": "earth",
      "origin": "arxiv:physics.geo-ph",
      "subfield": "geophysics"
    }
  ],
  "title": "Structure-dependent failure modes of neural priors in acoustic full-waveform inversion",
  "title_text": "Structure-dependent failure modes of neural priors in acoustic full-waveform inversion",
  "type": "preprint",
  "updated_at": "2026-10-30T12:24:52Z",
  "url": "https://research.draconitic.com/paper/8ts5srp77h7vg",
  "venue": "arXiv",
  "versions": []
}