Build a calibrated, cloud-running, agent-queryable SWMM and HEC-RAS model of your own catchment — then turn it into a decision engine that forecasts flooding hours ahead, scores flood risk, and generates a grant-ready five-year capital plan.
One system — yours — carried through all sixteen modules. Each course closes with a capstone built live on the final afternoon: not a bolt-on exercise, but the accumulated work of the two days.
Rainfall-runoff and 1D/2D hydraulic fundamentals, automated model and terrain build from DEM and land cover, cloud simulation at scale, an MCP server that exposes SWMM and HEC-RAS to an AI agent, rain gauge strategy, data QA/QC, and automated calibration.
A live twin fed by radar and level sensors, hyper-local flash flood forecasting, optimal gauge placement, ML flood risk surrogates, green versus grey infrastructure optimization, and a benefit-cost justified five-year CIP aligned to grant criteria.
You will write code. Comfort with basic Python (variables, loops, functions, reading a script) is expected, along with working familiarity with SWMM, HEC-RAS, or another hydrologic and hydraulic model. New to modeling? Start with the free Stormwater Modeling Fundamentals course. Self-paced pre-work covering the Python environment, cloud workspace setup, and a refresher on rainfall-runoff and open channel hydraulics is included and must be completed before day one. No machine learning or AI background is assumed. If you lead a utility rather than model for one, the one-day Executive Program is built for you instead.
Before automating anything, be certain what the solver is doing. This module rebuilds the hydrologic and hydraulic fundamentals that every downstream automation depends on, then draws a hard line around where an AI agent may and may not operate.
A model you cannot rebuild by script is a model you cannot automate. Take the INP file and the 2D terrain apart, then construct both programmatically from your own DEM and land cover.
One run on a laptop is an exercise. Full design storm suites and long continuous records on demand is infrastructure. Containerize the solvers and drive them at scale.
The core technical skill of the program. Build a Model Context Protocol server that exposes both your hydrologic and your 2D hydraulic model to an AI agent as safe, validated tools.
Calibration and flood warning both live or die on the rainfall record. Design a monitoring network deliberately, and specify instruments that survive the field.
Every failed calibration this instructor has reviewed failed here first. Build the automated validation pipeline that stands between raw rainfall and level data and any model that informs a decision.
Move from weeks of manual parameter tuning to a repeatable, agent-driven calibration loop — validated against the flooding that people actually observed.
The final afternoon of day two. Assemble everything into one working system, built on the data you brought to class, and defend it to the room.
Connect the calibrated model to live rainfall and level data. The step from a model you run to a twin that runs itself is architectural, not algorithmic.
The flagship module for this track. Flooding is a forecasting problem before it is a hydraulics problem — build the nowcasting chain that buys your community lead time.
Where the next gauge goes is an optimization problem, not a site-visit judgement call. Quantify what an instrument is worth before installing it.
Two-dimensional models are too slow for real-time decisions. Train surrogate models that give instant depth predictions, then build the risk scores that drive capital.
Let the agent generate and test thousands of alternatives across green and grey infrastructure — then choose from the Pareto front defensibly.
The flagship planning module, and the seam with the Executive Program. Turn flood risk into a sequenced, budgeted, grant-ready capital program.
A recommendation that never reaches a work order changes nothing. Close the loop between the twin and the field crew, in both directions.
The final afternoon of day two. Wire the full decision chain together on your own data, from live rainfall through to a ranked capital program.
In Advanced Module 6 you produce a risk-based capital plan. The one-day Executive Program teaches your GM, director, or CFO to interrogate and defend that same plan — so the work you do actually gets funded.
Sign up for the Stormwater practitioner track and leave with a working agentic digital twin of your own catchment.