{"resourceId":"houston-stormwater-master-plan-ai-surrogate-model-2026","versions":[{"version":"external-a106a41c63c67636c4ba5aae3dc573426758512db41e0ffe7747489cf14e38fd","resource":{"id":"houston-stormwater-master-plan-ai-surrogate-model-2026","title":"Houston Public Works builds a living stormwater master plan, testing an AI surrogate model that cuts model runs from six hours to three seconds","organization":"City of Houston, Houston Public Works (reported by Autodesk)","sector":"Municipal stormwater and flood resilience","geography":"Houston, Texas, United States","publishedAt":"Autodesk One Water Blog, 23 Oct 2026","publicationDate":"2026-10-23","eventDate":null,"sourceName":"Autodesk One Water Blog","sourceLabel":"Vendor customer story quoting city officials","sourceUrl":"https://www.autodesk.com/blogs/water/2026/10/23/houston-public-works-living-master-plan/","evidenceClass":"vendor-claim","outcomeClass":"emerging","topics":["infrastructure","operating-model","governance-procurement"],"finding":"Houston Public Works chose InfoWorks ICM after a documented evaluation of 50 criteria and 20 providers. It built an $11 million citywide Stormwater Master Plan with an interactive public flood-risk map and a planned three-year update cycle. A managing engineer reports that the AI surrogate model returns results in three seconds versus six hours for a full hydraulic run. Autodesk's footnote says surrogate modeling is AI functionality still under development and being tested by customers such as Houston. A separate WEFTEC 2026 session abstract (29 Sep) co-authored by the same Houston engineer describes a wastewater data lake and a hydraulically informed machine-learning model ranking dry-weather sanitary sewer overflow risk to move cleaning from calendar to risk-based schedules, without reporting outcome figures.","sledRelevance":"One of the few current U.S. municipal stormwater AI examples: a large city using an AI emulator to make citywide flood modeling fast enough for frequent updates and operational use. Stormwater was a recorded gap in both earlier editions.","evidence":"Vendor-published customer story with direct quotes from the Director of Public Works, City Engineer and a Managing Engineer. The six-hours-to-three-seconds figure is a practitioner statement with no stated accuracy comparison against the full model. The feature is pre-release. The WEFTEC abstract is a conference summary without results.","architectureImplications":"A surrogate model trained on many full hydraulic runs can stand in for the solver for rapid scenarios, but must be retrained when the network model changes. Houston feeds model results into an asset management platform and a public map.","governanceImplications":"A documented 50-criterion software evaluation and a three-year update cycle provide a defensible procurement and maintenance record. Validating surrogate results against the full model should be part of model governance.","securityPrivacyImplications":"Limited direct security content. Houston's City Engineer has elsewhere stressed keeping utility data in house; detailed flood and asset models are sensitive infrastructure information.","caveats":"Vendor marketing with no independent check; surrogate accuracy versus full model is not reported; the feature is under development. Published 23 Oct, before the 2026-10-29 edition, and not archived; included now because U.S. stormwater AI evidence was missing from both prior editions and this is the most recent U.S. municipal example found.","streamIds":["utility-management"],"roles":{"sales":"Sales framing: speed of flood modeling is the hook, accuracy is the question. Houston's engineers say an AI surrogate turns a six-hour hydraulic run into three seconds, which matters for storm-day scenarios and frequent plan updates. Use it to open a conversation with stormwater managers about which decisions are slowed by model run time. A bounded engagement is a surrogate validation study on one watershed. Do not claim the surrogate is accurate, production-ready or transferable without validation.","engineering":"Engineering framing: a surrogate is only as good as the full-model runs it learns from. Houston's setup depends on a calibrated citywide hydraulic model, then trains an emulator on many runs. A proof of value should compare surrogate and full-model flood depths and extents across design storms and historical events, and check behavior outside the training range. Integration points are the asset management platform and public flood map, so versioning and retraining after network changes must be planned.","delivery":"Delivery framing: the owner is the stormwater planning or modeling lead with GIS and emergency management. Work includes maintaining the base hydraulic model, retraining the surrogate on each update cycle and publishing uncertainty with results. Acceptance should be proposed error tolerances against the full model. Risks include treating fast surrogate output as truth in storms, a pre-release vendor feature changing, and the public map overstating precision."},"roleDetails":{"sales":{"customerProblem":"Citywide hydraulic flood models take hours per run, limiting scenario testing and frequent updates.","stakeholders":["Director of public works","City engineer","Stormwater modeling manager","Emergency management coordinator","GIS manager"],"discoveryQuestions":["Which decisions wait on hydraulic model runs today?","How often is the stormwater model updated and recalibrated?","How would you validate a faster approximate model?"],"valueHypothesis":"An AI surrogate could make flood scenarios fast enough for frequent planning and storm-day use, if validated against the full model.","potentialEngagement":"A validation study comparing surrogate and full-model results for one watershed across design and historical storms.","unsupportedClaims":["Surrogate accuracy equal to the full model","Production readiness","Reduced flood damage","Cost savings"]},"engineering":{"fit":"Fits cities with a calibrated, citywide 1D/2D hydraulic model and capacity to generate training runs.","architectureIntegration":"Surrogate trained on full-model runs, results feeding asset management and public flood-risk maps.","prerequisites":["Calibrated citywide hydraulic model","Library of full-model runs for training","Asset and GIS integration"],"constraints":["Feature is pre-release","Accuracy outside training range unknown","Retraining needed after network changes"],"security":"Treat detailed flood and asset models as sensitive infrastructure data and control external sharing.","proofOfValue":["Compare surrogate and full-model depth and extent for at least five storms","Test an out-of-range storm","Measure run time and retraining effort"]},"delivery":{"work":"Model maintenance, surrogate retraining each update cycle, validation reporting and public map uncertainty notes.","dependencies":["Modeling staff","Vendor software roadmap","GIS team","Emergency management"],"ownership":"Stormwater modeling manager under the city engineer.","skillsAdoption":"Modelers need skills in emulator validation; operations staff need guidance on when surrogate output is decision-grade.","governanceCheckpoints":["Validation sign-off before operational use","Retraining after each base-model update","Review of public map communications"],"acceptanceCriteria":["Proposed: surrogate depth error within an agreed tolerance for validated storms","Proposed: retraining completed within each three-year update","Proposed: uncertainty statement published with public results"],"risks":["Overreliance on fast output during storms","Vendor feature changes","Overstated precision in public maps"]}},"retrievedAt":"2026-10-31T22:06:00-05:00","enrichedAt":"2026-10-31T22:14:58-05:00","enrichmentBasis":"retrieved source","accessibilityWorkforceImplications":"Public flood-risk map is meant to let every resident see their own risk; modeling staff need new validation skills.","procurementImplications":"Houston's documented 50-criterion, 20-provider evaluation is a model for defensible software selection; pre-release AI features should carry contract terms on validation and support.","operatingModelImplications":"Treats the master plan as a living model with a three-year update cycle rather than a one-time report.","sourceVerification":{"openedUrl":"https://www.autodesk.com/blogs/water/2026/10/23/houston-public-works-living-master-plan/","referenceExcerpt":"With a surrogate model, it takes three seconds to get the same results.","promptVersion":"sled-research-v4.0","model":null,"basis":"agent-reported inspection"}}}]}