Skip to content
DraconiticResearch
Search Sources API
197,768 studies31 sourcesUpdated 2 min ago
Peer-reviewedCC BY-NC-NDGeophysical Research Letters

AI Agent for Hydrologic Modeling: Definition, Development, and Application

  • Songkun Yan1
  • Mengye Chen1
  • Zhi Li2,3
  • Yixin Wen4
  • Siyu Zhu1
  • Mofan Zhang5
  • Di Liu6
  • Jie Cao7
  • Xiaodong Chen1,8
  • Chengbin Deng6,9
  • Tiantian Yang1
  • Yang E. Hong1
9 affiliations
  1. 1School of Civil Engineering and Environmental Science University of Oklahoma Norman OK USA
  2. 2Department of Civil, Environmental, and Architectural Engineering University of Colorado Boulder Boulder CO USA
  3. 3Institute of Arctic and Alpine Research University of Colorado Boulder Boulder CO USA
  4. 4Department of Geography University of Florida Gainesville FL USA
  5. 5Civil and Environmental Engineering Stanford University Stanford CA USA
  6. 6Center for Spatial Analysis University of Oklahoma Norman OK USA
  7. 7School of Computer Science University of Oklahoma Norman OK USA
  8. 8School of Meteorology University of Oklahoma Norman OK USA
  9. 9Department of Geography and Environmental Sustainability University of Oklahoma Norman OK USA
Open at sourceDOICite

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.

Related

  1. Non-dendritic hydrologic networks: foundational patterns, algorithms, and a global empirical demonstration
    David Blodgett, Taher Chegini, Ryan Gillespie +1
    EGUspherePreprintCC BY 4.0General earth scienceEGUsphere
  2. HydroCraft: an efficient online platform for hydrological modeling integrated with a large language model agent
    Mahmut Tudaji, Fuqiang Tian, Xiannan Wu
    Journal of HydrologyPeer-reviewedCC BY-NC-ND8 citedEnvironmental science & pollutionGeology & geochemistryOpenAlex
  3. Modeling resource conflict and inequality in fragile systems: A spatial agent-based framework with a Uganda case study
    Ronald Katende
    PLOS OnePeer-reviewedCC BY 4.0Full textNeuroscienceGeology & geochemistryPLOS
  4. Catchment hydrologic function is widely time-variant
    Ying Yan, Hamed Sharif, Ali A. Ameli
    Communications Earth & EnvironmentPeer-reviewedCC BY 4.0Full textHydrology & soilsCrossref
  5. Estimation of eruption source parameters based on field data and numerical modeling: application to the 1993 eruption of Lascar volcano, Chile
    Alfredo Esquivel, Alvaro Aravena, Felipe Aguilera
    Scientific ReportsPeer-reviewedCC BY-NC-ND 4.0Full textGeology & geochemistryCrossref

Cite

BibTeXRIS
BibTeX
@article{yan2026agent,
  title = {{AI Agent for Hydrologic Modeling: Definition, Development, and Application}},
  author = {Songkun Yan and Mengye Chen and Zhi Li and Yixin Wen and Siyu Zhu and Mofan Zhang and Di Liu and Jie Cao and Xiaodong Chen and Chengbin Deng and Tiantian Yang and Yang E. Hong},
  journal = {Geophysical Research Letters},
  year = {2026},
  month = jul,
  doi = {10.1029/2025gl119814},
  url = {https://doi.org/10.1029/2025gl119814},
  note = {CC BY-NC-ND},
}
RIS
TY  - JOUR
TI  - AI Agent for Hydrologic Modeling: Definition, Development, and Application
AU  - Songkun Yan
AU  - Mengye Chen
AU  - Zhi Li
AU  - Yixin Wen
AU  - Siyu Zhu
AU  - Mofan Zhang
AU  - Di Liu
AU  - Jie Cao
AU  - Xiaodong Chen
AU  - Chengbin Deng
AU  - Tiantian Yang
AU  - Yang E. Hong
PY  - 2026
DA  - 2026/07/04
JO  - Geophysical Research Letters
DO  - 10.1029/2025gl119814
UR  - https://doi.org/10.1029/2025gl119814
AB  - 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.
SN  - 0094-8276
SN  - 1944-8007
ER  -