{
  "abstract": "Exploration seismic processing underpins subsurface imaging and resource exploration, but learning-based methods remain difficult to compare across studies. Our survey of 368 papers finds widespread reliance on private or difficult-to-reproduce datasets, with only 25 providing public code. This obscures whether reported gains arise from model design or experimental settings. We introduce the Seismic Processing Benchmark (SPBench), covering six tasks: random noise attenuation, trace interpolation, ground-roll suppression, multiple suppression, deblending, and first-arrival picking. We reproduce 24 supervised methods on 10 datasets under 43 standardized settings and release datasets, implementations, configurations, evaluation scripts, and results. To complement global scores and per-trace pick errors, we introduce signal-component-resolved evaluation (SCoRE) for reconstruction and a reference-free ridge-curvature score (RC_norm) for first-arrival picking. Our analyses show that synthetic rankings do not reliably predict field rankings, with task-dependent agreement when models train within each setting. As degradation strengthens, rankings reorder more under coherent ground roll than under random-like interference. The ridge score agrees with MAE-based model rankings in the evaluated settings, with a mean Kendall correlation of 0.881 across three field surveys, while SCoRE reveals frequency- and energy-dependent differences hidden by global scores. SPBench provides a reproducible basis for comparing learning-based seismic processing methods and characterizes how their relative advantages vary across data settings, degradation strengths, and evaluation criteria.",
  "abstract_shown": true,
  "affiliations": [],
  "article_type": null,
  "arxiv": "2609.28925",
  "author_total": 7,
  "authors": [
    {
      "name": "Qi Liu"
    },
    {
      "name": "Tianxiang Gao"
    },
    {
      "name": "Zhitong Cheng"
    },
    {
      "name": "Chen Zhang"
    },
    {
      "name": "Peng Hu"
    },
    {
      "name": "Wei Gao"
    },
    {
      "name": "Jianwei Ma"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/bheygjfphefee.bib",
  "cited_by": 0,
  "doi": "10.48550/arxiv.2609.28925",
  "fulltext_url": null,
  "id": "bheygjfphefee",
  "issns": [],
  "landing_url": "https://arxiv.org/abs/2609.28925",
  "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": null,
  "pdf_url": "https://arxiv.org/pdf/2609.28925",
  "pmcid": null,
  "pmid": null,
  "published": "2026-09-24",
  "publisher": null,
  "ris": "https://research.draconitic.com/paper/bheygjfphefee.ris",
  "sources": [
    {
      "first_seen": "2026-10-30T12:24:11Z",
      "native_id": "2609.28925",
      "source": "arxiv",
      "url": "https://arxiv.org/abs/2609.28925"
    }
  ],
  "subjects": [
    {
      "field": "earth",
      "origin": "arxiv:physics.geo-ph",
      "subfield": "geophysics"
    }
  ],
  "title": "SPBench: A Multi-Task Evaluation Benchmark for Exploration Seismic Processing",
  "title_text": "SPBench: A Multi-Task Evaluation Benchmark for Exploration Seismic Processing",
  "type": "preprint",
  "updated_at": "2026-10-30T12:24:11Z",
  "url": "https://research.draconitic.com/paper/bheygjfphefee",
  "venue": "arXiv",
  "versions": []
}