{
  "abstract": "Three-dimensional (3D) chlorophyll-a (Chl-a) distributions provide a foundation for understanding upper-ocean ecosystem dynamics and biogeochemical variability. We developed the source-target coupled network (ST-CoupleNet), a physics-guided transfer learning framework that combines Earth system model simulations with observation-constrained reconstructions to estimate subsurface Chl-a in the Northwest Pacific Ocean. The framework first learns large-scale spatiotemporal vertical representations from long-term CMIP6 simulations and then adapts them using reconstructed fields constrained by BioGeoChemical-Argo (BGC-Argo) observations, reducing simulation biases while preserving regional variability. By integrating dual-attention, residual learning, and convolutional long short-term memory (ConvLSTM) architectures, ST-CoupleNet substantially improves reconstruction accuracy over a conventional convolutional neural network (CNN). This framework demonstrates how transferable knowledge from climate simulations can be combined with autonomous observations to generate continuous 3D Chl-a fields, enabling large-scale investigations of subsurface marine ecosystems and biogeochemical change.",
  "abstract_shown": true,
  "affiliations": [],
  "article_type": "Article",
  "arxiv": null,
  "author_total": 8,
  "authors": [
    {
      "name": "Xiang Gong"
    },
    {
      "name": "Xiaoling Li"
    },
    {
      "name": "Xiaoyu Liu"
    },
    {
      "name": "Jinxuan Wan"
    },
    {
      "name": "Tao Zou"
    },
    {
      "name": "Xun Gong"
    },
    {
      "name": "Xinyu Guo"
    },
    {
      "name": "Wenming Yin"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/1rm1xzbjv7vg4.bib",
  "cited_by": 0,
  "doi": "10.1016/j.isci.2026.117109",
  "fulltext_url": "https://europepmc.org/articles/PMC13682479",
  "id": "1rm1xzbjv7vg4",
  "issns": [
    "2589-0042"
  ],
  "landing_url": "https://www.cell.com/iscience/fulltext/S2589-0042(26)02487-9",
  "language": "eng",
  "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": null,
  "native_subjects": [
    [
      "heading",
      "Biogeoscience"
    ],
    [
      "heading",
      "Environmental science"
    ],
    [
      "heading",
      "Oceanography"
    ],
    [
      "openalex",
      "1910|Marine and coastal ecosystems"
    ]
  ],
  "openalex": "W7221546805",
  "pdf_url": "https://europepmc.org/articles/PMC13682479?pdf=render",
  "pmcid": "PMC13682479",
  "pmid": "42903909",
  "published": "2026-10-12",
  "publisher": "Elsevier BV",
  "ris": "https://research.draconitic.com/paper/1rm1xzbjv7vg4.ris",
  "sources": [
    {
      "first_seen": "2026-10-30T12:17:16Z",
      "native_id": "10.1016/j.isci.2026.117109",
      "source": "feed-cell",
      "url": "https://www.cell.com/iscience/fulltext/S2589-0042(26)02487-9"
    },
    {
      "first_seen": "2026-10-30T12:17:49Z",
      "native_id": "10.1016/j.isci.2026.117109",
      "source": "crossref",
      "url": "https://linkinghub.elsevier.com/retrieve/pii/S2589004226024879"
    },
    {
      "first_seen": "2026-10-30T12:19:53Z",
      "native_id": "MED:42903909",
      "source": "europepmc",
      "url": "https://europepmc.org/article/MED/42903909"
    }
  ],
  "subjects": [
    {
      "field": "earth",
      "origin": "heading:Oceanography",
      "subfield": "oceanography"
    }
  ],
  "title": "A source-target transfer learning framework with physics priors for subsurface chlorophyll reconstruction in the Northwest Pacific Ocean",
  "title_text": "A source-target transfer learning framework with physics priors for subsurface chlorophyll reconstruction in the Northwest Pacific Ocean",
  "type": "peer-reviewed",
  "updated_at": "2026-10-30T12:19:53Z",
  "url": "https://research.draconitic.com/paper/1rm1xzbjv7vg4",
  "venue": "iScience",
  "versions": []
}