{
  "abstract": "This study conducts a systematic hyperparameter search across five deep learning architectures, DLinear, LSTM, PatchTST, ResAttLstm, and Mamba2, and nine context lengths (1-168 h) for single-station significant wave height (Hs) forecasting on NDBC buoy 41009, followed by re-evaluation of the best configurations on a 47-buoy, 37-year corpus. The five families converge to a common performance level on the multi-buoy evaluation (between-family SD = 0.0014 m^2, 0.8% of the grand mean), a spread dwarfed by the 4.83x cross-dataset MSE shift between buoy corpora. All multi-buoy trials beat persistence (mean skill +0.062), but no architecture consistently outperforms the others. On the single-buoy experiment, skill peaks at 12-24 h where five trials fall below persistence, per-family Q4/Q3 test MSE ratios range from 2.4 to 2.6, and deep models underperform persistence for the most extreme 1% of waves. These findings are consistent with the interpretation that persistence already captures the dominant linear-inertial signal in univariate Hs, and that architecture engineering under this univariate input setting has reached diminishing returns: cross-buoy variance, not model class, dominates forecast error. Future work should prioritise atmospheric covariates, zero-shot cross-buoy transfer, and decomposition of Hs into swell and wind-sea components. By establishing a rigorous reference baseline for what univariate Hs models can and cannot achieve, this study provides a benchmark against which future multivariate and physics-informed approaches can be calibrated, and offers practical guidance for lightweight buoy-level forecasting in mid-latitude storm-dominated and swell-mixed environments.",
  "abstract_shown": true,
  "affiliations": [],
  "article_type": "Journal reference: Ocean Engineering 365 (2026) 127187",
  "arxiv": "2609.30688",
  "author_total": 3,
  "authors": [
    {
      "name": "Yilin Zhai"
    },
    {
      "name": "Hongyuan Shi"
    },
    {
      "name": "Zaijin You"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/bc89r3m5kazk9.bib",
  "cited_by": 0,
  "doi": "10.48550/arxiv.2609.30688",
  "fulltext_url": null,
  "id": "bc89r3m5kazk9",
  "issns": [],
  "landing_url": "https://arxiv.org/abs/2609.30688",
  "language": null,
  "licence": "CC-BY-NC-ND-4.0",
  "licence_label": "CC BY-NC-ND 4.0",
  "licence_source": "article",
  "licence_url": "http://creativecommons.org/licenses/by-nc-nd/4.0/",
  "metadata_licence": "CC0-1.0",
  "native_subjects": [
    [
      "arxiv",
      "cs.LG"
    ],
    [
      "arxiv",
      "physics.ao-ph"
    ],
    [
      "arxiv",
      "physics.comp-ph"
    ]
  ],
  "openalex": null,
  "pdf_url": "https://arxiv.org/pdf/2609.30688",
  "pmcid": null,
  "pmid": null,
  "published": "2026-09-25",
  "publisher": null,
  "ris": "https://research.draconitic.com/paper/bc89r3m5kazk9.ris",
  "sources": [
    {
      "first_seen": "2026-10-30T12:24:52Z",
      "native_id": "2609.30688",
      "source": "arxiv",
      "url": "https://arxiv.org/abs/2609.30688"
    }
  ],
  "subjects": [
    {
      "field": "earth",
      "origin": "arxiv:physics.ao-ph",
      "subfield": "atmospheric"
    },
    {
      "field": "physics",
      "origin": "arxiv:physics.comp-ph",
      "subfield": "computational"
    }
  ],
  "title": "On the Limits of Univariate Deep Learning for Significant Wave Height Forecasting",
  "title_text": "On the Limits of Univariate Deep Learning for Significant Wave Height Forecasting",
  "type": "preprint",
  "updated_at": "2026-10-30T12:24:52Z",
  "url": "https://research.draconitic.com/paper/bc89r3m5kazk9",
  "venue": "arXiv",
  "versions": [
    {
      "doi": "10.1016/j.oceaneng.2026.127187",
      "pid": null,
      "relation": "published-as",
      "title": null,
      "venue": null
    }
  ]
}