Related Experiment Video
Updated: Aug 11, 2026
11:53
Spatial Multiobjective Optimization of Agricultural Conservation Practices using a SWAT Model and an Evolutionary Algorithm
Published on: December 9, 2012
Automating SWMM-based stormwater modelling and analysis through a tool-augmented single-agent system
Jian Wang1, Chenyue Sun1, Dragan Savic2
1Centre for Water Systems, University of Exeter, Exeter, EX4 4QF, United Kingdom.
Journal of Environmental Management
|August 4, 2026
Summary
SWMM-Agentic, a large language model system, streamlines urban stormwater modelling by interpreting natural language commands for simulation and analysis. This tool enhances efficiency and accuracy in managing flood risk and water quality.
Area of Science:
- Environmental Engineering
- Computational Hydrology
- Artificial Intelligence in Environmental Science
Background:
- Urban stormwater modelling is crucial for managing flood risk and water quality but is often manual and requires specialized knowledge.
- Existing modelling workflows face inefficiencies due to manual processes and reliance on expert interpretation.
Purpose of the Study:
- To introduce SWMM-Agentic, a novel large language model (LLM)-based system for automating urban stormwater modelling, simulation, and scenario analysis.
- To enhance the efficiency, accuracy, and reproducibility of stormwater management practices through natural language interaction.
Main Methods:
- Development of SWMM-Agentic, a single-agent system augmenting the Storm Water Management Model (SWMM) with LLM capabilities.
- Utilizing an orchestration model to interpret natural-language instructions and invoke documented functions for post-configuration workflows.
- Evaluation on the Astlingen benchmark using a 60-task suite across three LLMs (DeepSeek-V3.2-Exp, Qwen3-236B, Qwen3-14B).
Main Results:
- SWMM-Agentic demonstrated high task completion rates, with DeepSeek-V3.2-Exp achieving 98.3% and Qwen3-236B achieving 96.7% accuracy.
- The system successfully handled tool call failures, implementing corrective actions within three attempts.
- SWMM-Agentic accurately reproduced network characteristics, compared control strategies, and analyzed the impact of rain gardens on combined sewer overflow.
Conclusions:
- SWMM-Agentic reliably operates SWMM models via natural language, supporting accurate and reproducible stormwater simulation and analysis.
- The system lays the foundation for natural-language-driven platforms for integrated urban planning and hypothesis-driven environmental research.
- This approach significantly reduces the manual effort and specialized knowledge required for urban stormwater modelling.
Related Concept Videos
01:17Design Example: Analyzing Capacity Contours for Flood Risk Assessment
Flood risk assessment involves careful planning and analysis to ensure the safety of communities near water retention structures. Capacity contours are a vital tool in this process, as they illustrate the potential spread of water at specific levels in a given area. In the context of building a bund across a small valley, these contours play a critical role in evaluating the safety of nearby residential areas.In this example, the bund is intended to store stormwater in the valley. The engineers...
01:12Modeling and Similitude
Scaled modeling is a fundamental technique in engineering, enabling the study of large and complex systems by creating smaller, manageable replicas that recreate critical characteristics of the original. In hydrology and civil infrastructure, for example, scaled models of dams help analyze water flow, turbulence, and pressure. This method allows for accurate predictions of real-world behavior within a controlled environment, significantly reducing the cost and time involved in full-scale...
01:30Typical Model Studies
Fluid mechanics model studies often utilize scaled-down systems to predict fluid behavior in full-scale environments, such as river flows, dam spillways, and structures interacting with open surfaces. Maintaining Froude number similarity in river models is crucial, as it replicates surface flow features like wave patterns and velocities.