{
  "abstract": "In this paper we build upon a previous study in which we demonstrated, using XGBoost and earthquake catalogue data from Japan and Chile, that a set of 60 seismic statistical features (SSFs) had much greater predictive value than a set of 428 generic time series features from the tsfresh package. We here extend this previous work in two key ways, focusing on data from Japan as a large dataset is necessary in order to allow for the training of a deep learning (autoencoder) model. First, we move from whole-region prediction (considering, for each candidate event, the likelihood of an event M $\\geq$ 5.0 anywhere in the region in the next 15 days) to localised predictions in which both the region of feature computation and the region of prediction are restricted to a circle of radius 24 km around the candidate event, and we show that performance remains excellent, similar to our previous whole-region study for the same area. Second, we here couple this proven set of SSFs, based on one-dimensional (catalogue) data, with a novel feature based on magnitude-stratified two-dimensional seismic maps, obtained by training a VQ-VAE model to reproduce such maps as output and identifying a measure of its error in doing so with anomalies in magnitude distribution reflecting a localised build-up of crustal stress. We show that while localised prediction based only on a set of SSFs can be effective, with test AUC values as high as those obtained in the case of Japan in our previous whole-region study, the inclusion of the new natively-spatial VQ-VAE-derived feature, top-ranked by SHAP analysis, both improves prediction and points toward a new approach that might allow computationally time-demanding traditional seismic features to be entirely set aside.",
  "abstract_shown": true,
  "affiliations": [],
  "article_type": null,
  "arxiv": "2606.10069",
  "author_total": 2,
  "authors": [
    {
      "name": "Wei Quan"
    },
    {
      "name": "Denise Gorse"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/0hj5kc2gvdaet.bib",
  "cited_by": 0,
  "doi": "10.48550/arxiv.2606.10069",
  "fulltext_url": null,
  "id": "0hj5kc2gvdaet",
  "issns": [],
  "landing_url": "https://arxiv.org/abs/2606.10069",
  "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",
      "cs.LG"
    ],
    [
      "arxiv",
      "physics.geo-ph"
    ],
    [
      "openalex",
      "1702|Seismology and Earthquake Studies"
    ]
  ],
  "openalex": "W7164176905",
  "pdf_url": "https://arxiv.org/pdf/2606.10069",
  "pmcid": null,
  "pmid": null,
  "published": "2026-09-09",
  "publisher": null,
  "ris": "https://research.draconitic.com/paper/0hj5kc2gvdaet.ris",
  "sources": [
    {
      "first_seen": "2026-10-30T12:20:26Z",
      "native_id": "2606.10069",
      "source": "arxiv",
      "url": "https://arxiv.org/abs/2606.10069"
    }
  ],
  "subjects": [
    {
      "field": "earth",
      "origin": "arxiv:physics.geo-ph",
      "subfield": "geophysics"
    }
  ],
  "title": "Using Seismic Statistical Features and VQ-VAE to Improve Spatiotemporal Seismicity Predictability",
  "title_text": "Using Seismic Statistical Features and VQ-VAE to Improve Spatiotemporal Seismicity Predictability",
  "type": "preprint",
  "updated_at": "2026-10-30T12:20:26Z",
  "url": "https://research.draconitic.com/paper/0hj5kc2gvdaet",
  "venue": "arXiv",
  "versions": []
}