{"resourceId":"joongang-daily-ai-typhoon-track-errors-vs-ecmwf-intensity-gap-champi-20261023","versions":[{"version":"external-88a57f1acb71a59982806c515abb7410e75a2b57ec6d99878f8645eda4bf4460","resource":{"id":"joongang-daily-ai-typhoon-track-errors-vs-ecmwf-intensity-gap-champi-20261023","title":"Korean analyses find AI typhoon track forecasts beat a leading numerical model, but intensity and speed forecasts lag","organization":"Korea Meteorological Administration; Jeju National University Typhoon Research Center; U.S. Joint Typhoon Warning Center; ECMWF; Google DeepMind","sector":"Disaster forecasting and early warning","geography":"South Korea and East Asia","publishedAt":"2026-10-23","publicationDate":"2026-10-23","eventDate":"2026-10-23","sourceName":"Korea JoongAng Daily","sourceLabel":"Korea JoongAng Daily: Analyses suggest that AI weather models outperform supercomputer counterparts, but gaps remain","sourceUrl":"https://www.koreajoongangdaily.com/korea/analyses-suggest-that-ai-weather-models-outperform-supercomputer-counterparts-but-gaps-remain/12935010","evidenceClass":"independent-reporting","outcomeClass":"mixed","topics":["infrastructure","operating-model","governance-procurement"],"finding":"Reporting on Typhoon Champi, the article says AI models consistently forecast a sharp northeast turn while ECMWF and other conventional models projected a more westerly track; the U.S. Joint Typhoon Warning Center and KMA largely sided with AI, while KMA said the forecast remained highly uncertain. A Jeju National University Typhoon Research Center analysis of the past two years found ECMWF IFS averaged a 205.5 km track error across one- to five-day forecasts, versus under 200 km for most AI models, with AI ahead by up to 150 km at five days. AI proved less reliable on storm strength and speed, and experts called for hybrid AI and numerical systems.","sledRelevance":"U.S. emergency managers increasingly see AI hurricane guidance alongside NWS products; this shows forecasters leaning on AI track guidance while intensity, which drives surge and evacuation decisions, remains weaker.","evidence":"Newspaper report citing a university center's two-year track-error comparison and official statements; the underlying study, sample size and per-model results are not published in the article.","architectureImplications":"Supports a hybrid setup where AI track guidance and numerical intensity guidance feed forecasters together rather than AI replacing physics models.","governanceImplications":"Warning agencies need documented rules for when AI guidance overrides conventional models and how uncertainty is communicated.","securityPrivacyImplications":"Limited relevance; dependence on vendor-run AI models such as Google DeepMind's raises continuity questions.","caveats":"Published 23 October, before the last run; included because Champi forecasts were still unfolding and no newer original with measured errors was retrievable (NPR's 26 October hurricane piece timed out). Track-error figures are secondhand; no outcome for Champi's actual path is reported. East Asian typhoon context.","streamIds":["emergency-services"],"roles":{"sales":"For sales, the framing point is that AI typhoon guidance now beats a leading numerical model on track in Korean analyses but still lags on intensity and speed. Emergency managers who act on forecasts will want to know which parts of AI guidance to trust. A bounded engagement is a briefing or decision guide on using AI guidance in evacuation planning. The source cannot support claims that AI forecasts are better overall or will reduce losses.","engineering":"For pre-sales engineering, the evidence supports hybrid use: AI track guidance alongside numerical models, especially for intensity. Prerequisites are access to AI model outputs and verification data. Constraints include secondhand error statistics, regional differences and reliance on vendor-run models. Proof of value should compare AI and conventional track and intensity errors for local storms before changing warning procedures.","delivery":"For delivery, the work is setting procedures for how emergency managers read conflicting AI and conventional forecasts and communicate uncertainty. Ownership sits with the weather service and the emergency management agency's planning lead. Acceptance should rest on season-end verification of track and intensity errors used in decisions. Risks include over-trusting AI on intensity, confusing the public with conflicting tracks and vendor discontinuity."},"roleDetails":{"sales":{"customerProblem":"Emergency managers must make evacuation and staging decisions when AI and conventional forecasts disagree.","stakeholders":["State and county emergency managers","National weather service forecasters","Coastal local governments"],"discoveryQuestions":["Do your planners see AI forecast guidance today, and how is it weighed?","How do you handle conflicting track forecasts in decisions?","Which forecast errors matter most for your evacuation triggers?"],"valueHypothesis":"Clear guidance on where AI forecasts are stronger (track) and weaker (intensity) could improve how planners use them (interpretation).","potentialEngagement":"A decision guide and tabletop exercise on using AI and conventional forecast guidance together.","unsupportedClaims":["AI forecasts are better overall","Reduced storm losses","Reliable AI intensity forecasts"]},"engineering":{"fit":"Fits agencies that consume tropical cyclone guidance for planning.","architectureIntegration":"AI and numerical model outputs presented side by side to forecasters and planners.","prerequisites":["Access to AI and numerical guidance","Historical verification data","Forecaster review process"],"constraints":["Secondhand error figures","Regional transferability","Vendor-run model availability"],"security":"Plan for continuity if a vendor AI model feed is unavailable during a storm.","proofOfValue":["Local track error comparison","Intensity error comparison","Decisions changed by AI guidance reviewed after season"]},"delivery":{"work":"Write procedures for weighing AI and conventional guidance and communicating uncertainty.","dependencies":["Weather service guidance","Verification data","Public information officers"],"ownership":"Emergency management planning lead with the weather service liaison.","skillsAdoption":"Planners learn the strengths and limits of AI forecast guidance.","governanceCheckpoints":["Pre-season procedure review","In-storm decision log","Post-season verification review"],"acceptanceCriteria":["Proposed: documented rationale whenever AI guidance drives a decision","Proposed: season-end error report for guidance used"],"risks":["Over-trust in AI intensity","Public confusion from conflicting tracks","Vendor model discontinuity"]}},"retrievedAt":"2026-10-27T22:07:35-05:00","enrichedAt":"2026-10-27T22:11:42-05:00","enrichmentBasis":"retrieved source","accessibilityWorkforceImplications":"Forecasters must weigh conflicting AI and numerical guidance, adding interpretive load.","procurementImplications":"Agencies consuming AI weather guidance should ask vendors for verified track and intensity error statistics.","operatingModelImplications":"AI has moved from supplementary to central in KMA typhoon forecasting since last year, per the article.","sourceVerification":{"responseId":"curl-jad-2026-10-27","openedUrl":"https://www.koreajoongangdaily.com/korea/analyses-suggest-that-ai-weather-models-outperform-supercomputer-counterparts-but-gaps-remain/12935010","referenceExcerpt":"But AI has proved less reliable in forecasting a typhoon’s strength and speed.","promptVersion":"sled-research-v4.0","model":null,"basis":"agent-reported inspection"}}}]}