{
  "abstract": "Earthquake sequence forecasting requires models that can learn nonlinear history dependence while retaining robust statistical structure. We develop a scaling-law-informed neural marked point process, termed Fusion, that combines neural representations of catalog history with temporal features derived from the Epidemic-Type Aftershock Sequence model and magnitude information derived from the Gutenberg--Richter law. The model separates the magnitude cutoff applied to the input catalog from the fixed target-event threshold, allowing lower-magnitude earthquakes to inform forecasts without changing the target-event set. For the 2016--2017 Amatrice--Visso--Norcia sequence, Fusion achieves the highest target-event temporal likelihood when lower-magnitude events are retained, outperforming both ETAS and a purely neural point-process baseline. Event-wise and cumulative analyses show sustained timing gains through substantial portions of the Visso and Norcia sequences. Across five benchmark catalogs, catalog-specific neural training with a fixed ETAS prior yields the highest temporal likelihood at the minimum evaluated magnitude cutoff. Magnitude likelihood shows no consistent predictive gain beyond the Gutenberg--Richter-based ETAS reference, indicating that the additional information captured by Fusion is primarily temporal. These results show that lower-magnitude catalog histories and empirical scaling-law information complement neural sequence learning for target-event timing.",
  "abstract_shown": true,
  "affiliations": [],
  "article_type": null,
  "arxiv": "2608.18791",
  "author_total": 6,
  "authors": [
    {
      "name": "Tianlu Xiong"
    },
    {
      "name": "Zaibo Zhao"
    },
    {
      "name": "Yunrui Li"
    },
    {
      "name": "Wenqi Liu"
    },
    {
      "name": "Yosef Ashkenazy"
    },
    {
      "name": "Yongwen Zhang"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/9ex74czmn7jj4.bib",
  "cited_by": 0,
  "doi": "10.48550/arxiv.2608.18791",
  "fulltext_url": null,
  "id": "9ex74czmn7jj4",
  "issns": [],
  "landing_url": "https://arxiv.org/abs/2608.18791",
  "language": null,
  "licence": "LicenseRef-arXiv-nonexclusive-1.0",
  "licence_label": "arXiv licence",
  "licence_source": "article",
  "licence_url": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
  "metadata_licence": "CC0-1.0",
  "native_subjects": [
    [
      "arxiv",
      "physics.data-an"
    ],
    [
      "arxiv",
      "physics.geo-ph"
    ],
    [
      "arxiv",
      "physics.soc-ph"
    ],
    [
      "openalex",
      "1908|earthquake and tectonic studies"
    ]
  ],
  "openalex": "W7203892800",
  "pdf_url": "https://arxiv.org/pdf/2608.18791",
  "pmcid": null,
  "pmid": null,
  "published": "2026-11-05",
  "publisher": null,
  "ris": "https://research.draconitic.com/paper/9ex74czmn7jj4.ris",
  "sources": [
    {
      "first_seen": "2026-11-06T18:21:30Z",
      "native_id": "2608.18791",
      "source": "arxiv",
      "url": "https://arxiv.org/abs/2608.18791"
    }
  ],
  "subjects": [
    {
      "field": "earth",
      "origin": "arxiv:physics.geo-ph",
      "subfield": "geophysics"
    },
    {
      "field": "physics",
      "origin": "arxiv:physics.data-an",
      "subfield": "computational"
    },
    {
      "field": "physics",
      "origin": "arxiv:physics.soc-ph",
      "subfield": "statistical-nonlinear"
    }
  ],
  "title": "Scaling-law-informed neural point processes for earthquake sequence forecasting",
  "title_text": "Scaling-law-informed neural point processes for earthquake sequence forecasting",
  "type": "preprint",
  "updated_at": "2026-11-09T00:20:34Z",
  "url": "https://research.draconitic.com/paper/9ex74czmn7jj4",
  "venue": "arXiv",
  "versions": []
}