{
  "abstract": "Nuclear reaction networks are a major computational bottleneck in astrophysical simulations when large isotope sets are required, because of the stiffness of the network equations and the repeated calls to Jacobian-based solvers required by implicit methods. In this work, we develop a deep learning surrogate solver for a large 690 isotope nuclear reaction network over a broad range of thermodynamic conditions relevant to Type I X-ray bursts using a graph neural network, NuGNN. Unlike conventional fully connected or convolutional neural networks, NuGNN directly reflects the structure of the reaction network through heterogeneous isotope and reaction nodes and message-passing along reaction connections. The model is trained on data spanning many orders of magnitude in stellar temperature and density, as well as in simulation time-step size. We compare NuGNN with a Res-U-Net and fully connected neural network, and find that NuGNN consistently achieves significantly better accuracy with errors of only a few percent. More importantly, when implemented in the network evolution code in place of the original solver, NuGNN successfully reproduces the final abundance patterns, whereas the other architectures fail to do so. We also show that the trained model has a potential to improve computational speed. These results show that graph neural networks can provide a robust and promising framework for accurate surrogate modeling of large nuclear reaction networks.",
  "abstract_shown": true,
  "affiliations": [
    "Sungkyunkwan University",
    "Obsidian Research",
    "University of Notre Dame",
    "Stellar Science Solutions"
  ],
  "article_type": null,
  "arxiv": null,
  "author_total": 5,
  "authors": [
    {
      "affs": [
        0
      ],
      "name": "C. H. Kim",
      "orcid": "0000-0002-4614-4793"
    },
    {
      "affs": [
        0
      ],
      "name": "K. Y. Chae",
      "orcid": "0000-0003-1819-079X"
    },
    {
      "affs": [
        0
      ],
      "name": "S. Ko",
      "orcid": "0009-0004-1407-8420"
    },
    {
      "affs": [
        1,
        2
      ],
      "name": "M. R. Mumpower",
      "orcid": "0000-0002-9950-9688"
    },
    {
      "affs": [
        3
      ],
      "name": "M. S. Smith",
      "orcid": "0000-0002-4737-4099"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/cd5rvccj2vx2p.bib",
  "cited_by": 0,
  "doi": "10.3847/1538-4365/aeaa46",
  "fulltext_url": null,
  "id": "cd5rvccj2vx2p",
  "issns": [
    "0067-0049",
    "1538-4365"
  ],
  "landing_url": "https://iopscience.iop.org/article/10.3847/1538-4365/aeaa46",
  "language": null,
  "licence": "CC-BY-4.0",
  "licence_label": "CC BY 4.0",
  "licence_source": "journal",
  "licence_url": "https://creativecommons.org/licenses/by/4.0/",
  "metadata_licence": null,
  "native_subjects": [],
  "openalex": null,
  "pdf_url": "https://iopscience.iop.org/article/10.3847/1538-4365/aeaa46/pdf",
  "pmcid": null,
  "pmid": null,
  "published": "2026-11-04",
  "publisher": "American Astronomical Society",
  "ris": "https://research.draconitic.com/paper/cd5rvccj2vx2p.ris",
  "sources": [
    {
      "first_seen": "2026-11-04T12:20:55Z",
      "native_id": "10.3847/1538-4365/aeaa46",
      "source": "crossref",
      "url": "https://iopscience.iop.org/article/10.3847/1538-4365/aeaa46"
    }
  ],
  "subjects": [
    {
      "field": "astronomy",
      "origin": "journal-openalex:3103|Stellar, planetary, and galactic studies",
      "subfield": "stellar"
    }
  ],
  "title": "NuGNN: A Graph Neural Network for Nuclear Reaction Network Equations",
  "title_text": "NuGNN: A Graph Neural Network for Nuclear Reaction Network Equations",
  "type": "peer-reviewed",
  "updated_at": "2026-11-05T00:20:45Z",
  "url": "https://research.draconitic.com/paper/cd5rvccj2vx2p",
  "venue": "The Astrophysical Journal Supplement Series",
  "versions": []
}