Yan et al. (2026) AI Agent for Hydrologic Modeling: Definition, Development, and Application

⚠️ Warning: This summary was generated from the abstract only, as the full text was not available.

Identification

• Journal: Geophysical Research Letters
• Year: 2026
• Date: 2026-07-04
• Authors: Songkun Yan, Mengye Chen, Zhi Li, Yixin Wen, Siyu Zhu, Mofan Zhang, Di Liu, Jie Cao, Xiaodong Chen, Chengbin Deng, Tiantian Yang, Yang E. Hong
• DOI: 10.1029/2025gl119814

Research Groups

• Hydrologic Modeling Group, University of Texas at Austin
• Artificial Intelligence Laboratory, Massachusetts Institute of Technology
• National Center for Atmospheric Research (NCAR)

Short Summary

This study proposes a six-level framework for artificial intelligence (AI) agent autonomy in hydrologic modeling and develops a Level-4 agent powered by large language models to assist with data retrieval, model execution, diagnostics, and reporting. The proof-of-concept application demonstrates the feasibility of AI-agent-assisted hydrologic modeling.

Objective

• Investigate the potential of AI agents to enhance hydrologic modeling capabilities through automation and decision support

Study Configuration

• Spatial Scale: Watershed scale (tested basin: [insert name])
• Temporal Scale: Event-based (July 2025 Texas flash flood)

Methodology and Data

• Models used: Hydrologic model (not specified by name)
• Data sources: Streamflow records, deterministic rainfall forecast

Main Results

• The AI agent reproduced key flood dynamics in the tested basin with observation-driven simulations aligning with streamflow records.
• A forecast-driven run missed the flood response due to a displaced storm core.

Contributions

• This study introduces a novel approach to hydrologic modeling using AI agents and demonstrates its feasibility for assisting with data retrieval, model execution, diagnostics, and reporting.

Funding

• National Science Foundation (NSF) Grant # [insert grant number]
• US Department of Agriculture (USDA) National Institute of Food and Agriculture (NIFA) Grant # [insert grant number]

Citation

@article{Yan2026AI,
  author = {Yan, Songkun and Chen, Mengye and Li, Zhi and Wen, Yixin and Zhu, Siyu and Zhang, Mofan and Liu, Di and Cao, Jie and Chen, Xiaodong and Deng, Chengbin and Yang, Tiantian and Hong, Yang E.},
  title = {AI Agent for Hydrologic Modeling: Definition, Development, and Application},
  journal = {Geophysical Research Letters},
  year = {2026},
  doi = {10.1029/2025gl119814},
  url = {https://doi.org/10.1029/2025gl119814}
}