{"resourceId":"dhi-opti-site-stormwater-ai-nature-based-solutions-2026","versions":[{"version":"external-32a67e06b4ee63f9bdd4f59e2d74ce2f56ee63835b51a214951cef746c0a3c7d","resource":{"id":"dhi-opti-site-stormwater-ai-nature-based-solutions-2026","title":"Opti-SITE: Danish and Swedish utilities train ML and radar nowcasting for stormwater and nature-based siting","organization":"DHI (with HOFOR, NSVA and Interreg ÖKS partners)","sector":"Municipal stormwater and combined sewer management","geography":"Denmark and Sweden (Copenhagen and Landskrona case areas)","publishedAt":"DHI project page (accessed 5 Nov 2026; undated body)","publicationDate":null,"eventDate":null,"sourceName":"DHI","sourceLabel":"Technology provider project description","sourceUrl":"https://www.dhigroup.com/projects/optimising-stormwater-planning-with-ai-and-data-driven-decision-support","evidenceClass":"vendor-claim","outcomeClass":"emerging","topics":["infrastructure","operating-model","developers-agents"],"finding":"The Interreg Öresund-Kattegat-Skagerrak Opti-SITE project, described on DHI's site, is building decision-support tools that combine machine learning (including graph neural networks), multi-objective optimisation and real-time radar rainfall to site nature-based solutions (rain gardens, basins, ponds) and to nowcast combined sewer overflows. A prototype ML model with benchmarking and training-data workflows is reported done; final optimisation tooling and radar-hydrodynamic integration remain next steps. Testing is with utilities HOFOR and NSVA in Copenhagen and Landskrona. Results are expected to feed DHI's CityFlow Live product.","sledRelevance":"US municipal stormwater and CSO programs face the same siting and nowcast problems; transfer requires caution on EU funding context, climate, and the vendor-hosted roadmap, but the ML-plus-radar pattern is relevant where radar and sewer models exist.","evidence":"Vendor project page without a clear publication date. Prototype status is self-reported; no published overflow-reduction percentages on this page. Treated as vendor-claim.","architectureImplications":"Graph ML and optimisation over catchment features plus radar-driven fast sewer models for planning and event nowcasting, eventually productised in CityFlow Live.","governanceImplications":"Multi-utility research collaboration under Interreg; US analogues would need clear ownership of models and procurement boundaries if a vendor productises results.","securityPrivacyImplications":"Not discussed; radar and network models are operationally sensitive if exposed.","caveats":"Vendor page; incomplete tooling; European pilots; no US measured results; publicationDate unknown.","streamIds":["utility-management"],"roles":{"sales":"Sales framing: US stormwater teams lack AI siting evidence; Opti-SITE shows EU utilities prototyping ML and radar nowcasting for NBS placement and CSO prediction. Ask whether radar feeds and calibrated sewer models exist. A bounded offer is a stormwater data-and-model readiness review. Do not claim overflow cuts from this page; none are published.","engineering":"Engineering framing: the Opti-SITE pattern needs catchment feature layers for graph ML, reliable radar or gauge rainfall, and a fast surrogate or calibrated hydrodynamic sewer model. Keep any nowcast alerts recommendation-only until operators accept them. Proof of value should benchmark nowcast skill against a naive baseline and compare optimised nature-based portfolios with engineer baselines on cost and overflow metrics.","delivery":"Delivery framing: stormwater utility planning and operations share ownership with a modelling partner. Keep research prototypes separate from SCADA write paths. Proposed acceptance criteria are documented model skill scores and a pilot catchment plan. Risks are vendor lock-in, uncalibrated models and transferring EU results blindly."},"roleDetails":{"sales":{"customerProblem":"Cities struggle to site nature-based stormwater controls and anticipate CSOs under heavier rain.","stakeholders":["Stormwater utility planner","Wastewater operations","Modelling consultant","City climate adaptation lead"],"discoveryQuestions":["Do you have radar or gauge rainfall feeds?","Is there a calibrated sewer model?","Which CSO outfalls are priority?"],"valueHypothesis":"ML siting plus radar nowcasting may improve NBS placement and overflow warning; local proof required.","potentialEngagement":"Stormwater analytics readiness and pilot catchment design.","unsupportedClaims":["Specific overflow reduction","US performance parity","Finished commercial readiness"]},"engineering":{"fit":"Municipalities with sewer models and rainfall data willing to pilot decision support.","architectureIntegration":"Offline/planning ML optimisation plus radar nowcast models; careful boundary before any real-time control writes.","prerequisites":["Rainfall data","Sewer network model","Catchment GIS features"],"constraints":["EU project context","Vendor product roadmap","No US results here"],"security":"Protect network models and operational radar pipelines; no unverified automated gate control.","proofOfValue":["Nowcast skill vs baseline","Optimised vs manual NBS portfolio metrics","Operator-accepted alert lead time"]},"delivery":{"work":"Assemble data, pilot one catchment, validate with operators, decide build-vs-buy.","dependencies":["Radar provider","Modelling platform","Capital planning cycle"],"ownership":"Stormwater planning lead with operations.","skillsAdoption":"Train planners to interpret ML siting outputs.","governanceCheckpoints":["Data-sharing agreements","Pilot success criteria","Procurement decision gate"],"acceptanceCriteria":["Proposed: published pilot skill scores","Proposed: operator sign-off on alert workflow","Proposed: clear separation from autonomous control"],"risks":["Overfit EU pilots","Vendor lock-in","Acting on unvalidated nowcasts"]}},"retrievedAt":"2026-11-05T22:08:39-06:00","enrichedAt":"2026-11-05T22:14:19-06:00","enrichmentBasis":"retrieved source","accessibilityWorkforceImplications":"Aimed at utilities and consultants needing decision support rather than in-house ML teams.","procurementImplications":"Expect research-to-product path into a commercial platform; US buyers should separate research claims from product SLAs.","operatingModelImplications":"Supports both long-term NBS capital planning and real-time overflow response workflows.","sourceVerification":{"responseId":"p10.html","openedUrl":"https://www.dhigroup.com/projects/optimising-stormwater-planning-with-ai-and-data-driven-decision-support","referenceExcerpt":"By combining machine learning, optimisation and real-time radar data, the project helps utilities","promptVersion":"sled-research-v4.0","model":null,"basis":"agent-reported inspection"}}}]}