{"resourceId":"mcti-cemaden-floodcastingxai-flash-flood-nowcast-20261106","versions":[{"version":"external-5f5ae6830456d5605b96c76816b10ac933c06ed3573c05dd875941349bbb45b0","resource":{"id":"mcti-cemaden-floodcastingxai-flash-flood-nowcast-20261106","title":"Brazil’s Cemaden says FloodcastingXAI operational tests improved 1-to-4-hour flood forecasts by about 40%","organization":"Cemaden / Ministério da Ciência, Tecnologia e Inovação (MCTI)","sector":"Disaster early warning / civil-defense flash-flood forecasting","geography":"Brazil (collaboration including the City of São Paulo)","publishedAt":"2026-11-06","publicationDate":"2026-11-06","eventDate":null,"sourceName":"Ministério da Ciência, Tecnologia e Inovação","sourceLabel":"Brazilian science ministry news release on Cemaden’s FloodcastingXAI platform","sourceUrl":"https://www.gov.br/mcti/pt-br/acompanhe-o-mcti/noticias/2026/11/inteligencia-artificial-desenvolvida-pelo-mcti-ajuda-a-prever-enxurradas-com-ate-quatro-horas-de-antecedencia","evidenceClass":"government-evaluation","outcomeClass":"emerging","topics":["infrastructure","governance-procurement","operating-model"],"finding":"On 6 November 2026 (18h16), Brazil’s science ministry reported that Cemaden researchers developed FloodcastingXAI, an explainable-AI platform that ingests rain-gauge and river-level observations updated every 10 minutes to forecast water-level rise one to four hours ahead for civil-defense decision support. The ministry says the system does not replace monitoring staff or alert issuers; it adds information to technical analysis and can show which inputs most influenced a forecast. Operational tests reportedly showed gains of approximately 40% in forecast performance for one- to four-hour lead times; the release does not name the skill score or baseline behind that figure. FloodcastingXAI is a product of the iFast project (more than 60 researchers at 15 Brazilian and foreign institutions) with collaborators including Inpe, Unesp, Unifesp, and the City of São Paulo. Development used open source without external contracting. The tool is a finalist in the 30th Enap Public Sector Innovation contest (AI for the Public Good category; more than 700 entries; competing with five other projects in that category; popular vote open until 11 November; initiative no. 983), led by Leonardo Bacelar with Cemaden teammates named in the release. It previously received an AI4GOOD prize at Brazil Conference 2025. The same article mentions Cemaden’s separate GeoRisk landslide tool (up to 72-hour risk forecasts) as a related but distinct system.","sledRelevance":"Transferable to U.S. emergency-management and flood-prone local governments that already operate gauge networks and need short-fuse nowcasts for evacuation or road-closure decisions. Limits: Brazilian hydrology, sensor density, and an unspecified 40% performance metric in a ministry news release rather than a peer-reviewed skill-score table. Why now: published 6 November 2026 and confirmed not in the archive.","evidence":"MCTI news page stamped Publicado em 06/11/2026 18h16. Direct statements on 10-minute gauge updates, 1–4 hour lead times, explainability, non-replacement of alert staff, approximately 40% operational-test gains, iFast partnership counts, open-source development, and Enap finalist status.","architectureImplications":"Fuse existing pluviometer and river-level feeds on a short (here, 10-minute) cycle into an explainable nowcast service that outputs lead-time water-level risk to human monitors, rather than standing up a separate sensor network or an autonomous public-alert bot.","governanceImplications":"Keep alert authority with trained monitoring and civil-defense staff. Require the vendor or lab to disclose the exact skill metric, baseline, sites, and false-alarm behavior behind any “approximately 40%” claim before using forecasts for evacuation orders.","securityPrivacyImplications":"Gauge and forecast systems are operational critical infrastructure; open-source code aids review but expands the attack surface. Protect write access to official alert channels so a compromised model cannot issue or suppress public warnings.","caveats":"Ministry self-report of its research unit’s tests; the 40% figure has no named metric, geography, or independent audit in this article; hydrologic transfer to U.S. basins is unproven here; Enap finalist status is not a performance evaluation.","streamIds":["emergency-services"],"roles":{"sales":"Sales framing: Brazil’s science ministry says Cemaden’s FloodcastingXAI used existing rain and river gauges, updated every 10 minutes, to forecast flash-flood rise one to four hours ahead, with operational tests showing about 40% better forecast performance—and with explainable-AI traces so staff can see which inputs drove a prediction. For U.S. emergency managers the bounded conversation is a human-supervised nowcast on networks they already own, not an autonomous warning system. Do not treat “approximately 40%” as a portable accuracy guarantee; the release does not name the metric or baseline.","engineering":"Engineering framing: ingest existing precipitation and stage sensors on a 10-minute cycle, train models to estimate near-term water-level rise, and expose feature-influence explanations to hydrologists and EOC analysts. Do not wire the model to public alert activation. Reproduce the claimed operational-test gain against a named skill score and baseline on local basins before any operational dashboard is trusted.","delivery":"Delivery framing: inventory gauge telemetry, agree a skill metric and false-alarm budget with emergency management and the NWS or local hydrology partner, and run a shadowed nowcast period in which humans still issue alerts. Acceptance is a documented improvement on the agreed metric plus usable explanations—not contest placement or a generic 40% claim copied from this release."},"roleDetails":{"sales":{"customerProblem":"Urban flash floods can rise faster than agencies can interpret raw gauge data, leaving little time to warn or move people.","stakeholders":["Emergency management director","Civil-defense / floodplain manager","Warning coordination meteorologist","Public works / stormwater","Municipal IT","Elected officials in flood-prone districts"],"discoveryQuestions":["Which rain and stage sensors already report at about 10-minute intervals?","Who is legally authorized to issue flood warnings?","What skill score and false-alarm rate would change an evacuation or road-closure decision?","Can explanations of model drivers be shown to on-duty hydrologists?"],"valueHypothesis":"If an explainable model on existing gauges can improve short-fuse water-level forecasts, monitors may gain one to four hours to warn or evacuate—value depends on a named local skill metric, not the ministry’s unspecified 40% figure.","potentialEngagement":"Shadow nowcast pilot on a single basin using existing telemetry, with human alert authority retained.","unsupportedClaims":["A portable 40% accuracy improvement for any U.S. watershed","That the system has independently audited operational skill","Autonomous public alerting","Equivalence to Cemaden’s separate GeoRisk landslide product"]},"engineering":{"fit":"Fits agencies that already collect frequent rain-gauge and river-level telemetry and have human flood-watch desks.","architectureIntegration":"Telemetry store to nowcast models to explainability layer to analyst dashboard; no automated write to IPAWS/WEA or outdoor-warning controllers.","prerequisites":["Reliable 10-minute-class gauge feeds","Historic event archive for local training/validation","Named skill metric and baseline","Human alert workflow"],"constraints":["Unspecified 40% metric in the source","Brazilian basins and sensor siting","Ministry self-evaluation"],"security":"Harden telemetry ingestion and dashboard accounts; separate model inference from systems that can issue public warnings.","proofOfValue":["Local hindcast skill versus the agreed baseline at 1–4 hour leads","False-alarm and miss rates on held-out events","Analyst review that explanations match physical drivers"]},"delivery":{"work":"Pilot a shadowed flash-flood nowcast desk using existing gauges, with documented skill tests before any change to warning practice.","dependencies":["Sensor network operators","Forecast office or contract hydrologist","EOC warning authority","Open-source maintainers if code is reused"],"ownership":"Emergency management owns warning decisions; science/hydrology owns model validation; IT owns telemetry security.","skillsAdoption":"Watch-desk staff need training to read explanations and to ignore the model when gauges or reconnaissance disagree.","governanceCheckpoints":["Metric and baseline approval","Independent review of test design","Decision that the model will not auto-alert","After-action on first flood season"],"acceptanceCriteria":["Published local skill table, not a copied 40% headline","Zero automated public alerts from the model","Documented human override on test events"],"risks":["Over-trust in an unexplained percentage","Missed events if gauges fail","Public confusion if unofficial nowcasts leak"]}},"retrievedAt":"2026-11-08T04:04:50Z","enrichedAt":"2026-11-08T04:11:11Z","enrichmentBasis":"retrieved source","accessibilityWorkforceImplications":"The release emphasizes added lead time so authorities can guide residents and organize removal from threatened areas, but it does not report how warnings would reach people with disabilities, limited connectivity, or languages other than Portuguese. Human monitors remain the workforce that interprets and issues alerts.","procurementImplications":"Prefer open, reviewable nowcast code and contracts that require disclosure of skill metrics, sites, and false-alarm performance. Contest finalist status (Enap, AI4GOOD) is recognition, not a substitute for local acceptance testing.","operatingModelImplications":"Position AI as an extra input on an existing flood-watch desk: gauges continue to report, specialists still issue alerts, and the model’s role is earlier, explained estimates of rapid water-level rise.","peerReview":"unknown","sourceVerification":{"openedUrl":"https://www.gov.br/mcti/pt-br/acompanhe-o-mcti/noticias/2026/11/inteligencia-artificial-desenvolvida-pelo-mcti-ajuda-a-prever-enxurradas-com-ate-quatro-horas-de-antecedencia","referenceExcerpt":"Os testes operacionais feitos com a ferramenta apontaram ganhos de aproximadamente 40% no desempenho das previsões para períodos de uma a quatro horas de antecedência.","promptVersion":"sled-research-v4.0","model":null,"basis":"agent-reported inspection"}}}]}