Agentic SWMM: Auditable and Reproducible Stormwater Modelling Workflow with Agent Skills and Model Context Protocol
- 1Department of Mechanical Engineering, University of Victoria, P.O. Box 1700, STN CSC, Victoria, BC V8W 2Y2, Canada
Abstract
Configuring urban hydrological models, such as the Storm Water Management Model (SWMM), for operational use remains onerous for many modellers. We propose aiswmm, a SWMM-specialized agentic runtime, together with an Agentic SWMM workflow that embeds (Agent) Skills and Model Context Protocol (MCP) tools to automate QGIS preprocessing, SWMM configuration, execution, and postprocessing. We demonstrate this natural-language triggered workflow on the Tod Creek watershed (located on the Saanich Peninsula, British Columbia). We also validate the proposed Agentic SWMM workflow at three levels: (i) a QGIS-based watershed-pour-point detection that agrees with the commercial PCSWMM® method to within 0.88% of the watershed perimeter (approximately 7.5 pixels in the digital elevation model); (ii) byte-identical SWMM output files (Secure Hash Algorithm 256-bit identical) between the command-line execution and the MCP paths across 60 paired simulations, and (iii) peak inflow at the watershed outlet matching to three significant digits between the manual SWMM interface and Agentic SWMM workflows. The results confirm that Agentic SWMM workflow can produce the same outputs with the manual SWMM interface, as they are designed to use the same computational engine. We also propose a verification-first contract and byte-level audit chain that record the inputs, parameters, and outputs of each run, thereby supporting the auditability and reproducibility. The aiswmm runtime, Skills, MCP servers, and byte-level audit chain are released as open source and remain compatible with mainstream agentic runtimes (Codex, Claude Code, Hermes, and OpenClaw) to support reproducible SWMM modelling driven by natural language.
Related
- Development and Evaluation of a Low-Cost Bio-Adsorptive Filter Insert (DrainGuard) for Stormwater Microplastic Remediation
- Synergistic effects of biochar and vegetation on microplastic and nanoplastic removal from stormwater runoff in bioretention systems
- Evaluating the hydrological processes governing microplastic contamination in stormwater runoff from an industrial catchment discharging into a detention basin in Lyon (France)
- Indicator-based hydrological resilience framework for urban stormwater management systems
- Impervious cover is associated with culture-based morphotype diversity in urban stormwater runoff
BibTeX
@article{zhang2026agentic,
title = {{Agentic SWMM: Auditable and Reproducible Stormwater Modelling Workflow with Agent Skills and Model Context Protocol}},
author = {Zhonghao Zhang and Caterina Valeo},
journal = {AI for Engineering},
year = {2026},
month = jun,
doi = {10.3390/aieng1010005},
url = {https://doi.org/10.3390/aieng1010005},
note = {CC BY},
}
RIS
TY - JOUR
TI - Agentic SWMM: Auditable and Reproducible Stormwater Modelling Workflow with Agent Skills and Model Context Protocol
AU - Zhonghao Zhang
AU - Caterina Valeo
PY - 2026
DA - 2026/06/09
JO - AI for Engineering
DO - 10.3390/aieng1010005
UR - https://doi.org/10.3390/aieng1010005
AB - Configuring urban hydrological models, such as the Storm Water Management Model (SWMM), for operational use remains onerous for many modellers. We propose aiswmm, a SWMM-specialized agentic runtime, together with an Agentic SWMM workflow that embeds (Agent) Skills and Model Context Protocol (MCP) tools to automate QGIS preprocessing, SWMM configuration, execution, and postprocessing. We demonstrate this natural-language triggered workflow on the Tod Creek watershed (located on the Saanich Peninsula, British Columbia). We also validate the proposed Agentic SWMM workflow at three levels: (i) a QGIS-based watershed-pour-point detection that agrees with the commercial PCSWMM® method to within 0.88% of the watershed perimeter (approximately 7.5 pixels in the digital elevation model); (ii) byte-identical SWMM output files (Secure Hash Algorithm 256-bit identical) between the command-line execution and the MCP paths across 60 paired simulations, and (iii) peak inflow at the watershed outlet matching to three significant digits between the manual SWMM interface and Agentic SWMM workflows. The results confirm that Agentic SWMM workflow can produce the same outputs with the manual SWMM interface, as they are designed to use the same computational engine. We also propose a verification-first contract and byte-level audit chain that record the inputs, parameters, and outputs of each run, thereby supporting the auditability and reproducibility. The aiswmm runtime, Skills, MCP servers, and byte-level audit chain are released as open source and remain compatible with mainstream agentic runtimes (Codex, Claude Code, Hermes, and OpenClaw) to support reproducible SWMM modelling driven by natural language.
SN - 3042-8831
ER -