HydroSuite-AI: a web-based LLM environment for hydrological code generation and execution for the hydrosuite open-source ecosystem

Vinay Pursnani; Carlos Erazo Ramirez; Yusuf Sermet; Ibrahim Demir

doi:10.1007/s12145-026-02222-7

Back

HydroSuite-AI: a web-based LLM environment for hydrological code generation and execution for the hydrosuite open-source ecosystem

Journal article

Open access

Peer reviewed

HydroSuite-AI: a web-based LLM environment for hydrological code generation and execution for the hydrosuite open-source ecosystem

Vinay Pursnani, Carlos Erazo Ramirez, Yusuf Sermet and Ibrahim Demir

Earth science informatics, Vol.19(11), 187

09/17/2026

DOI: 10.1007/s12145-026-02222-7

Appears in UI Libraries Support Open Access

Files and links (1)

url

https://doi.org/10.1007/s12145-026-02222-7View

Published (Version of record) Open Access

Abstract

Researchers in hydrology face technical barriers from complex models, evolving libraries, and fragmented documentation. We present HydroSuite-AI, an LLM-based assistant that integrates the open-source web hydrologic libraries HydroLang, HydroCompute, and HydroRTC for code generation, factual guidance, and in-browser execution of hydrological workflows. The system uses a Planner-Worker-Synthesizer architecture with retrieval-augmented generation (RAG) over library documentation and validates outputs in a client-side virtualized execution environment. We evaluate HydroSuite-AI through (i) a cross-library case study, (ii) a controlled benchmark measuring the assistant’s ability to retrieve and execute library functions across 60 domain-specific tasks under different LLM backends, and (iii) deployment as a code assistant in the WaterSoftHack 2024 workshop. Across the benchmark tasks, HydroSuite-AI achieves 95.0% function retrieval accuracy with 23.1 s mean latency when powered by o3-mini, while the same system reaches 71.7% under 10s with GPT-4.1-nano, showing an accuracy–speed tradeoff across model configurations. The case study demonstrates end-to-end interoperability and exposes limitations in advanced statistical workflows, and the workshop deployment confirms the system’s utility in collaborative, time-constrained settings. Documentation-grounded LLM orchestration reduces time to implementation and supports hydrological research and education.

Hydroinformatics

Multi-agent orchestration

Retrieval-augmented generation

Large language models

Web-based hydrological computing

UIOWA OA Agreement

Details

Title: Subtitle: HydroSuite-AI: a web-based LLM environment for hydrological code generation and execution for the hydrosuite open-source ecosystem
Creators: Vinay Pursnani - University of Iowa
Carlos Erazo Ramirez - Tulane University
Yusuf Sermet - Tulane University
Ibrahim Demir - Tulane University
Resource Type: Journal article
Publication Details: Earth science informatics, Vol.19(11), 187
DOI: 10.1007/s12145-026-02222-7
ISSN: 1865-0473
eISSN: 1865-0481
Publisher: Springer Nature
Grant note: NA22NWS4320003 / National Oceanic and Atmospheric Administration (https://doi.org/10.13039/100000192)
Language: English
Date published: 09/17/2026
Academic Unit: IIHR--Hydroscience and Engineering; Injury Prevention Research Center
Record Identifier: 9985231452602771

Metrics

1 Record Views