{
  "abstract": "The El Niño–Southern Oscillation (ENSO) exerts profound influence on global climate variability, yet its prediction remains a grand challenge. Recent advances in deep learning have significantly improved forecasting skill, but the opacity of these models hampers scientific trust and operational deployment. Here, we introduce a mathematically grounded interpretability framework based on bounded variation function. By rescuing the “dead” neurons from the saturation zone of the activation function, we enhance the model’s expressive capacity. Our analysis reveals that ENSO predictability emerges dominantly from the tropical Pacific, with contributions from the Indian and Atlantic Oceans, consistent with physical understanding. Controlled experiments affirm the robustness of our method and its alignment with established predictors. Notably, we probe the persistent Spring Predictability Barrier (SPB), finding that despite expanded sensitivity during spring, predictive performance declines–likely due to suboptimal variable selection. These results suggest that incorporating additional ocean–atmosphere variables may help transcend SPB limitations and advance long-range ENSO prediction.",
  "abstract_shown": true,
  "affiliations": [
    "State Key Laboratory of Physical Oceanography, Ocean University of China",
    "Frontier Science Center for Deep Ocean Multispheres and Earth System, Ocean University of China"
  ],
  "article_type": null,
  "arxiv": null,
  "author_total": 6,
  "authors": [
    {
      "affs": [
        0
      ],
      "name": "Yanhai Gan"
    },
    {
      "affs": [
        1
      ],
      "name": "Yipeng Chen"
    },
    {
      "affs": [
        0
      ],
      "name": "Ning Li"
    },
    {
      "affs": [
        0
      ],
      "name": "Xingguo Liu"
    },
    {
      "affs": [
        0
      ],
      "name": "Junyu Dong"
    },
    {
      "affs": [
        1
      ],
      "name": "Xianyao Chen"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/a2c9pvcfspc7r.bib",
  "cited_by": 0,
  "doi": "10.1186/s40562-026-00504-y",
  "fulltext_url": "https://doi.org/10.1186/s40562-026-00504-y",
  "id": "a2c9pvcfspc7r",
  "issns": [
    "2196-4092"
  ],
  "landing_url": "https://doi.org/10.1186/s40562-026-00504-y",
  "language": "en",
  "licence": "CC-BY",
  "licence_label": "CC BY",
  "licence_source": "journal",
  "licence_url": "https://creativecommons.org/licenses/by/4.0/",
  "metadata_licence": null,
  "native_subjects": [
    [
      "lcc",
      "Q"
    ],
    [
      "lcc",
      "QE1-996.5"
    ],
    [
      "openalex",
      "2306|Climate variability and models"
    ]
  ],
  "openalex": "W7119062488",
  "pdf_url": "https://link.springer.com/content/pdf/10.1186/s40562-026-00504-y.pdf",
  "pmcid": null,
  "pmid": null,
  "published": "2026-10-25",
  "publisher": "SpringerOpen",
  "ris": "https://research.draconitic.com/paper/a2c9pvcfspc7r.ris",
  "sources": [
    {
      "first_seen": "2026-10-30T13:46:02Z",
      "native_id": "5baba85262b24bf0a1c05864634419f6",
      "source": "doaj",
      "url": "https://doi.org/10.1186/s40562-026-00504-y"
    }
  ],
  "subjects": [
    {
      "field": "earth",
      "origin": "openalex:2306|Climate variability and models",
      "subfield": "climate"
    }
  ],
  "title": "Explore the ideology of deep learning in ENSO forecasts",
  "title_text": "Explore the ideology of deep learning in ENSO forecasts",
  "type": "peer-reviewed",
  "updated_at": "2026-10-30T13:46:02Z",
  "url": "https://research.draconitic.com/paper/a2c9pvcfspc7r",
  "venue": "Geoscience Letters",
  "versions": []
}