{"resourceId":"utep-el-paso-water-nasa-ai-flood-mapping-2026","versions":[{"version":"external-a106a41c63c67636c4ba5aae3dc573426758512db41e0ffe7747489cf14e38fd","resource":{"id":"utep-el-paso-water-nasa-ai-flood-mapping-2026","title":"UTEP and El Paso Water: NASA-funded project to map urban flooding with satellite data and an AI foundation model","organization":"University of Texas at El Paso (UTEP) with El Paso Water as research partner; funded by NASA","sector":"Municipal water and stormwater utility; university research","geography":"El Paso, Texas, United States","publishedAt":"UTEP news release, 8 Oct 2026","publicationDate":"2026-10-08","eventDate":null,"sourceName":"UTEP Newsfeed","sourceLabel":"University research announcement","sourceUrl":"https://www.utep.edu/newsfeed/2026/october/from-space-to-the-streets-nasa-funded-research-takes-aim-at-el-paso-flooding.html","evidenceClass":"academic-research","outcomeClass":"emerging","topics":["infrastructure","data-security","operating-model"],"finding":"A UTEP team received nearly $500,000 from NASA for a two-year project, due June 2028, that combines optical satellite imagery, Sentinel-1 radar and the Prithvi-EO Earth observation foundation model to map flooded areas after storms. El Paso Water is research partner and intended end user. The aim is a dashboard combining flood maps, confidence information and infrastructure overlays so utility staff can prioritize inspections. The team notes that wet pavement, building shadows and swimming pools can resemble floodwater in imagery, and says the tool is not meant to replace crews or emergency procedures.","sledRelevance":"A U.S. public water utility partnering with a university on AI for post-storm stormwater and infrastructure assessment, with explicit confidence reporting and human field verification built into the design.","evidence":"University announcement of a funded project; no results yet. Funding amount, data sources, model and timeline are stated. Accuracy targets and evaluation methods are not described.","architectureImplications":"Fusing optical and radar imagery with a foundation model and overlaying utility asset layers requires GIS integration and handling of cloud cover and revisit times.","governanceImplications":"Design keeps humans and existing emergency procedures in charge and publishes confidence information, a useful model for decision-support AI.","securityPrivacyImplications":"Infrastructure overlays on flood maps are sensitive; dashboard access should be controlled.","caveats":"Pre-results announcement; benefits are aspirations. Satellite revisit and resolution may limit timeliness for flash floods. Published 8 Oct, before the stream's first edition, and not archived; included now to address the recorded U.S. stormwater gap with a current, utility-partnered project.","streamIds":["utility-management"],"roles":{"sales":"Sales framing: this is a research partnership to watch, not a product to sell. El Paso Water is the intended end user of an AI flood-mapping dashboard funded through 2028. For other arid-city utilities with monsoon flooding, it opens a conversation about how post-storm inspections are prioritized today. A bounded engagement is a post-storm inspection workflow review that identifies where remote flood maps could help. Avoid suggesting the tool exists, is accurate or reduces inspection costs yet.","engineering":"Engineering framing: the hard part is false positives in cities. The team names wet pavement, shadows and pools as look-alikes and plans to combine radar with optical data and a foundation model that uses surrounding context. A proof of value would compare AI flood maps with crew-verified flood locations after real storms and test timeliness given satellite revisit intervals. Asset overlays require clean GIS data and controlled access.","delivery":"Delivery framing: the owner on the utility side is the stormwater or emergency operations lead working with GIS. Work in the research period is supplying ground truth, defining dashboard needs and agreeing how confidence scores will be used. Acceptance should be proposed agreement rates between AI maps and field observations. Risks include slow satellite revisits, project delays, and treating confidence-scored maps as definitive in emergencies."},"roleDetails":{"sales":{"customerProblem":"After storms, utility crews must find where flooding occurred and which assets need inspection, often without good situational data.","stakeholders":["Utility stormwater manager","Emergency operations lead","GIS manager","University research partner"],"discoveryQuestions":["How are post-storm inspections prioritized today?","What ground-truth flood observations do crews record?","Would confidence-scored flood maps change dispatch decisions?"],"valueHypothesis":"Remote flood maps with confidence scores may help prioritize inspections, if validated against field observations.","potentialEngagement":"A review of post-storm inspection workflows and ground-truth data readiness ahead of research results.","unsupportedClaims":["That the tool works today","Mapping accuracy","Inspection time or cost savings","Real-time flash-flood coverage"]},"engineering":{"fit":"Research-stage fit for utilities in cities with episodic urban flooding and good GIS asset data.","architectureIntegration":"Optical and radar imagery processed by a foundation model, with flood maps and confidence layers overlaid on utility assets in a dashboard.","prerequisites":["Utility GIS asset layers","Field-verified flood observations for validation","Access to satellite data feeds"],"constraints":["Satellite revisit timing","Urban look-alike features","Project not complete until June 2028"],"security":"Restrict dashboard access because it overlays infrastructure on hazard maps.","proofOfValue":["Compare AI flood extents with crew observations for several storms","Measure time from storm to map availability","Check false positives from pavement, shadows and pools"]},"delivery":{"work":"Supply ground truth, co-design dashboard, agree confidence thresholds for operational use.","dependencies":["University team","Utility field crews","GIS staff","Satellite data availability"],"ownership":"Utility stormwater or emergency operations lead.","skillsAdoption":"Staff need to interpret confidence scores and keep field verification as the deciding step.","governanceCheckpoints":["Data sharing agreement for asset layers","Validation review before operational use","Emergency procedure update only after validation"],"acceptanceCriteria":["Proposed: agreed agreement rate between AI maps and field observations","Proposed: maps available within an agreed time after storms","Proposed: documented false-positive review"],"risks":["Research delays","False positives in urban settings","Overreliance on maps in emergencies"]}},"retrievedAt":"2026-10-31T22:09:25-05:00","enrichedAt":"2026-10-31T22:14:58-05:00","enrichmentBasis":"retrieved source","accessibilityWorkforceImplications":"Intended to support, not replace, field crews; staff need training on confidence information.","procurementImplications":"University partnerships can de-risk early AI evaluation before a utility procures a tool.","operatingModelImplications":"Positions AI as a triage layer ahead of field verification within existing emergency procedures.","sourceVerification":{"openedUrl":"https://www.utep.edu/newsfeed/2026/october/from-space-to-the-streets-nasa-funded-research-takes-aim-at-el-paso-flooding.html","referenceExcerpt":"The technology is not intended to replace crews on the ground or existing emergency response procedures, the team said.","promptVersion":"sled-research-v4.0","model":null,"basis":"agent-reported inspection"}}}]}