{
  "abstract": "Hydrologic modeling supports flood forecasting and water resources management, but complex preprocessing, parameterization, and configuration limit broader use. This study defines a six‐level framework for artificial intelligence (AI)‐agent autonomy in hydrologic modeling and develops a Level‐4 agent, powered by large language models, that translates natural‐language requests into data retrieval, model execution, diagnostics, and reports with human oversight. In a proof‐of‐concept application to the July 2025 Texas flash flood, the agent reproduced key flood dynamics in the tested basin and reduced manual workflow effort. Observation‐driven simulations aligned with streamflow records, whereas a forecast‐driven run missed the flood response because the deterministic rainfall forecast displaced the storm core. These results suggest the feasibility of AI‐agent‐assisted hydrologic modeling in the tested case, while robustness and generalization across broader basins and events remain to be established through systematic validation, probabilistic meteorological forcing, and expert review of automated outputs.",
  "abstract_shown": true,
  "affiliations": [
    "School of Civil Engineering and Environmental Science University of Oklahoma Norman OK USA",
    "Department of Civil, Environmental, and Architectural Engineering University of Colorado Boulder Boulder CO USA",
    "Institute of Arctic and Alpine Research University of Colorado Boulder Boulder CO USA",
    "Department of Geography University of Florida Gainesville FL USA",
    "Civil and Environmental Engineering Stanford University Stanford CA USA",
    "Center for Spatial Analysis University of Oklahoma Norman OK USA",
    "School of Computer Science University of Oklahoma Norman OK USA",
    "School of Meteorology University of Oklahoma Norman OK USA",
    "Department of Geography and Environmental Sustainability University of Oklahoma Norman OK USA"
  ],
  "article_type": null,
  "arxiv": null,
  "author_total": 12,
  "authors": [
    {
      "affs": [
        0
      ],
      "name": "Songkun Yan",
      "orcid": "0009-0008-3820-104X"
    },
    {
      "affs": [
        0
      ],
      "name": "Mengye Chen",
      "orcid": "0000-0003-2135-1670"
    },
    {
      "affs": [
        1,
        2
      ],
      "name": "Zhi Li",
      "orcid": "0000-0003-4760-842X"
    },
    {
      "affs": [
        3
      ],
      "name": "Yixin Wen",
      "orcid": "0000-0003-1618-1208"
    },
    {
      "affs": [
        0
      ],
      "name": "Siyu Zhu",
      "orcid": "0000-0003-0273-1336"
    },
    {
      "affs": [
        4
      ],
      "name": "Mofan Zhang",
      "orcid": "0000-0001-8839-1808"
    },
    {
      "affs": [
        5
      ],
      "name": "Di Liu",
      "orcid": "0000-0002-7510-5646"
    },
    {
      "affs": [
        6
      ],
      "name": "Jie Cao",
      "orcid": "0000-0001-8268-954X"
    },
    {
      "affs": [
        0,
        7
      ],
      "name": "Xiaodong Chen",
      "orcid": "0000-0002-3089-2260"
    },
    {
      "affs": [
        5,
        8
      ],
      "name": "Chengbin Deng",
      "orcid": "0000-0002-5459-5586"
    },
    {
      "affs": [
        0
      ],
      "name": "Tiantian Yang",
      "orcid": "0000-0002-0148-396X"
    },
    {
      "affs": [
        0
      ],
      "name": "Yang E. Hong",
      "orcid": "0000-0001-8720-242X"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/a0rkc7qq820w1.bib",
  "cited_by": 8,
  "doi": "10.1029/2025gl119814",
  "fulltext_url": null,
  "id": "a0rkc7qq820w1",
  "issns": [
    "0094-8276",
    "1944-8007"
  ],
  "landing_url": "https://doi.org/10.1029/2025gl119814",
  "language": "en",
  "licence": "CC-BY-NC-ND",
  "licence_label": "CC BY-NC-ND",
  "licence_source": "journal",
  "licence_url": "https://creativecommons.org/licenses/by-nc-nd/4.0/",
  "metadata_licence": null,
  "native_subjects": [
    [
      "openalex",
      "2305|Hydrological Forecasting Using AI"
    ]
  ],
  "openalex": "W7167355651",
  "pdf_url": null,
  "pmcid": null,
  "pmid": null,
  "published": "2026-07-04",
  "publisher": "American Geophysical Union",
  "ris": "https://research.draconitic.com/paper/a0rkc7qq820w1.ris",
  "sources": [
    {
      "first_seen": "2026-11-07T13:21:02Z",
      "native_id": "W7167355651",
      "source": "openalex",
      "url": "https://doi.org/10.1029/2025gl119814"
    }
  ],
  "subjects": [
    {
      "field": "earth",
      "origin": "openalex:2305|Hydrological Forecasting Using AI",
      "subfield": "environmental-science"
    }
  ],
  "title": "AI Agent for Hydrologic Modeling: Definition, Development, and Application",
  "title_text": "AI Agent for Hydrologic Modeling: Definition, Development, and Application",
  "type": "peer-reviewed",
  "updated_at": "2026-11-08T13:20:54Z",
  "url": "https://research.draconitic.com/paper/a0rkc7qq820w1",
  "venue": "Geophysical Research Letters",
  "versions": []
}