{
  "abstract": "We present a surrogate-accelerated Bayesian history-matching framework, demonstrated on a realistic synthetic model ($N=100{,}188$ cells). The forward map $\\mathcal{G}$ is replaced by a Fourier neural operator $\\mathcal{G}_θ$ trained in a closed loop, $\\hat{x}_{n+1}=\\mathcal{G}_θ(u,\\hat{x}_n)$, with the discrete black-oil residual $R(x_{n+1},x_n)$ as a physics-informed neural operator (PINO) penalty, truncated backpropagation and noise injection. We assimilate production data and 4-D seismic using adaptive regularised ensemble Kalman inversion (aREKI), and synthesise $ΔV_p$ inside the rollout via a closed-form Gassmann transform of the surrogate, under a two-stage schedule (aREKI on production, then an ensemble smoother with multiple data assimilation, ES-MDA, on both). To temper the ill-posedness, we invert $(\\log K,ϕ)$ not in $\\mathbb{R}^{2N}$, where $N_e\\ll 2N$ leaves a rank-deficient covariance and a null space the data never inform, but on a chart $u=Ψ(\\tilde m)$, $\\tilde m\\in\\mathbb{R}^{d}$, $d\\ll 2N$, given by a Parseval-exact truncated cosine transform or a variational auto-encoder decoder. The ensemble then spans its own search space; the directions the data cannot constrain are cut to those the chart can express, and every member decodes to a geologically plausible field. For the rollout we prove an exposure bound $W_1\\le\\sum_j L^{\\,n-1-j}\\mathbb{E}e_j$, a physics-penalty contraction $\\|D_x\\mathcal{G}_θ\\|\\leα<1$ under a small residual defect, and an $\\mathcal{O}(ρ^K)$ truncation bias. A Loewner-order inequality $\\mathcal{I}_p\\preceq\\mathcal{I}_p+\\mathcal{I}_s$ explains why joint assimilation is no less informative. On held-out data, $\\mathcal{G}_θ$ attains $R^2>0.999$ on pressure and saturation and rolls out in $0.579$ s, a $\\sim2500\\times$ speed-up, bringing an $N_e=190$-member, $N_a=10$-iteration joint inversion within one GPU-hour.",
  "abstract_shown": true,
  "affiliations": [],
  "article_type": null,
  "arxiv": "2610.31677",
  "author_total": 10,
  "authors": [
    {
      "name": "Clement Etienam"
    },
    {
      "name": "David Blom"
    },
    {
      "name": "Hari Pattathil"
    },
    {
      "name": "Tsubasa Onishi"
    },
    {
      "name": "Harpreet Sethi"
    },
    {
      "name": "Lalson Vincent"
    },
    {
      "name": "Suraj Pawar"
    },
    {
      "name": "Kishan Ramesh Kumar"
    },
    {
      "name": "Pandu Devarakota"
    },
    {
      "name": "Faruk O. Alpak"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/513t04pw5pv39.bib",
  "cited_by": 0,
  "doi": "10.48550/arxiv.2610.31677",
  "fulltext_url": null,
  "id": "513t04pw5pv39",
  "issns": [],
  "landing_url": "https://arxiv.org/abs/2610.31677",
  "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",
      "cs.LG"
    ],
    [
      "arxiv",
      "stat.ML"
    ],
    [
      "openalex",
      "2212|Reservoir Engineering and Simulation Methods"
    ]
  ],
  "openalex": "W7223678221",
  "pdf_url": "https://arxiv.org/pdf/2610.31677",
  "pmcid": null,
  "pmid": null,
  "published": "2026-10-01",
  "publisher": null,
  "ris": "https://research.draconitic.com/paper/513t04pw5pv39.ris",
  "sources": [
    {
      "first_seen": "2026-10-30T12:35:25Z",
      "native_id": "2610.31677",
      "source": "arxiv",
      "url": "https://arxiv.org/abs/2610.31677"
    }
  ],
  "subjects": [
    {
      "field": "mathematics",
      "origin": "arxiv:stat.ML",
      "subfield": "statistics"
    }
  ],
  "title": "Autoregressive Physics-Informed Neural Operator Surrogates and Joint 4-D Seismic-Production Bayesian History Matching",
  "title_text": "Autoregressive Physics-Informed Neural Operator Surrogates and Joint 4-D Seismic-Production Bayesian History Matching",
  "type": "preprint",
  "updated_at": "2026-10-30T12:35:25Z",
  "url": "https://research.draconitic.com/paper/513t04pw5pv39",
  "venue": "arXiv",
  "versions": []
}