{
  "abstract": "Predicting lake thermal dynamics is crucial for lake management, particularly under increasing anthropogenic pressures and climate change. Current methods rely either on physics-based models, which are often complex and difficult to calibrate, or on purely data-driven approaches, which may lack interpretability and physical consistency while offering only short-term predictions. We show how Universal Differential Equations (UDEs), hybrid models that add neural networks to existing, even approximate, physics-based equations, can enhance forecasting. On Lake Créteil (Paris region, France), we build a UDE from minimal physics to predict water temperature at five depths and benchmark it against physics-based and data-driven models. For 7-day forecasting, the UDE is the most accurate, and for long-term prediction it is on par with the physics-based model while best reproducing stratification---all with $\\sim 90\\times$ fewer parameters than a purely data-driven model. We also provide guidelines on UDE architecture and training, transferable to other aquatic variables and systems.",
  "abstract_shown": true,
  "affiliations": [],
  "article_type": null,
  "arxiv": null,
  "author_total": 5,
  "authors": [
    {
      "name": "David Métivier"
    },
    {
      "name": "Ali Elhishi"
    },
    {
      "name": "Mathieu Le Séac'H"
    },
    {
      "name": "Céline Casenave"
    },
    {
      "name": "Brigitte Vinçon-Leite"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/5ce6s3kbmddw4.bib",
  "cited_by": 0,
  "doi": null,
  "fulltext_url": null,
  "id": "5ce6s3kbmddw4",
  "issns": [],
  "landing_url": "https://hal.science/hal-05853811v1",
  "language": "en",
  "licence": "CC-BY-4.0",
  "licence_label": "CC BY 4.0",
  "licence_source": "article",
  "licence_url": "https://creativecommons.org/licenses/by/4.0/",
  "metadata_licence": null,
  "native_subjects": [
    [
      "hal",
      "0.math"
    ],
    [
      "hal",
      "0.stat"
    ],
    [
      "hal",
      "1.math.math-ds"
    ],
    [
      "hal",
      "1.stat.ap"
    ],
    [
      "hal",
      "1.stat.ml"
    ]
  ],
  "openalex": null,
  "pdf_url": "https://hal.science/hal-05853811/document",
  "pmcid": null,
  "pmid": null,
  "published": "2026-11-03",
  "publisher": null,
  "ris": "https://research.draconitic.com/paper/5ce6s3kbmddw4.ris",
  "sources": [
    {
      "first_seen": "2026-11-07T12:20:25Z",
      "native_id": "hal-05853811",
      "source": "hal",
      "url": "https://hal.science/hal-05853811v1"
    }
  ],
  "subjects": [
    {
      "field": "mathematics",
      "origin": "hal:1.math.math-ds",
      "subfield": "dynamical-systems"
    },
    {
      "field": "mathematics",
      "origin": "hal:0.stat",
      "subfield": "statistics"
    }
  ],
  "title": "Universal Differential Equations for aquatic sciences: application to forecasting lake thermal stratification",
  "title_text": "Universal Differential Equations for aquatic sciences: application to forecasting lake thermal stratification",
  "type": "preprint",
  "updated_at": "2026-11-08T12:20:49Z",
  "url": "https://research.draconitic.com/paper/5ce6s3kbmddw4",
  "venue": "HAL",
  "versions": []
}