{ "id": "AIBD-0341", "title": "A GraphCast live run on ECMWF charts may have forecast Hurricane Lee's Nova Scotia landfall about nine days ahead", "summary": "DeepMind says a live GraphCast run on ECMWF's site forecast Lee's Nova Scotia landfall about nine days ahead; NHC records landfall 16 September 2023; no forecaster use of the run is documented.", "date_observed": "2023-09-16", "date_basis": "unassessed", "date_precision": "unassessed", "benefit_status": null, "source_collection": null, "source_entry": null, "account": "Google DeepMind's blog post of 14 November 2023 describes a live version of its publicly available GraphCast model, deployed on the ECMWF website. In September 2023 it predicted about nine days in advance that Hurricane Lee would make landfall in Nova Scotia. MIT Technology Review (14 November 2023) relayed the claim from DeepMind staff research scientist Rémi Lam. It added that traditional forecasting models pinpointed Nova Scotia only six days in advance. The article quotes no ECMWF staff on Lee. ECMWF's Newsletter 177 editorial (Autumn 2023) confirms that GraphCast, Pangu-Weather and FourCastNet were made available on ECMWF's public charts pages from ECMWF's own initial conditions. The NHC tropical cyclone report on Lee (21 March 2024) records the landfall. Lee, by then post-tropical, made landfall on Long Island in southwestern Nova Scotia around 2000 UTC on 16 September 2023. Maximum sustained winds were about 55 kt. NHC official track errors were exceptionally low through 72 h and below five-year means through 120 h. The report mentions no AI model. No ECMWF document recording the Lee forecast is on record, and the NHC 2023 verification report contains no AI-model entry. It found only an intensity-structure mention of Lee in the independent CIRA preprint. The forecast itself is dated only as “September” by the vendor. No cited source documents a forecaster or authority acting on the GraphCast Lee run.", "category": "general benefit", "unexpected": false, "purpose": "Machine-learning global medium-range weather forecasting (10 days, 0.25 degree), including severe-event prediction such as tropical cyclone tracks. This forecast was that purpose.", "system": "GraphCast (Google DeepMind graph neural network weather model), experimental live run on ECMWF public charts", "model_version": "GraphCast (live version deployed on the ECMWF website)", "developer": "DeepMind", "deployer": "ECMWF (experimental data-driven forecasts on its public charts pages)", "location": "Long Island, southwestern Nova Scotia, Canada (landfall)", "domain": "Weather forecasting / tropical cyclones", "segment": "Public-sector meteorological service; AI research laboratory", "benefit_type": "Improved Task Accuracy", "taxonomy_note": "The nine-day claim is vendor-sourced and no forecaster use of the run is documented.", "registry_ids": {}, "ratings": [ { "group": "personal", "depth": null, "reason": "No individual outcome is documented." }, { "group": "organizational", "depth": null, "reason": "General benefit. No cited source documents a forecast office using the GraphCast Lee run in its products." }, { "group": "societal", "depth": null, "reason": "General benefit. No public-safety decision is linked to the run in any cited source." } ], "ai_role": { "status": "assessed", "statement": "The only sources for the nine-day Lee forecast are the maker's own blog and a news report quoting the maker's scientist. ECMWF's editorial confirms only that GraphCast ran experimentally on its charts. NHC's Lee report records exceptionally low official track errors without mentioning AI guidance. The AI output is therefore documented as a forecast, not as an input to any decision." }, "evidence": [ { "kind": "press release", "citation": "Google DeepMind (2023). GraphCast: AI model for faster and more accurate global weather forecasting. DeepMind blog, 14 Nov 2023.", "title": "GraphCast: AI model for faster and more accurate global weather forecasting", "url": "https://deepmind.google/discover/blog/graphcast-ai-model-for-faster-and-more-accurate-global-weather-forecasting/", "date": "2023-11-14", "written_by": "makers", "quote": "a live version of our publicly available GraphCast model, deployed on the ECMWF website, accurately predicted about nine days in advance that Hurricane Lee would make landfall in Nova Scotia" }, { "kind": "news report", "citation": "Heikkilä, M. (2023). Google DeepMind's weather AI can forecast extreme weather faster and more accurately. MIT Technology Review, 14 Nov 2023.", "title": "Google DeepMind's weather AI can forecast extreme weather faster and more accurately", "url": "https://web.archive.org/web/20231114164801/https://www.technologyreview.com/2023/11/14/1083366/google-deepminds-weather-ai-can-forecast-extreme-weather-quicker-and-more-accurately/", "date": "2023-11-14", "written_by": "independent", "quote": "In September, GraphCast accurately predicted that Hurricane Lee would make landfall in Nova Scotia nine days in advance, says Rémi Lam, a staff research scientist at Google DeepMind." }, { "kind": "news report", "citation": "Heikkilä, M. (2023). Same article, comparison with conventional models.", "title": "Google DeepMind's weather AI can forecast extreme weather faster and more accurately (conventional-model comparison)", "url": "https://web.archive.org/web/20231114164801/https://www.technologyreview.com/2023/11/14/1083366/google-deepminds-weather-ai-can-forecast-extreme-weather-quicker-and-more-accurately/", "date": "2023-11-14", "written_by": "independent", "quote": "Traditional weather forecasting models pinpointed the hurricane to Nova Scotia only six days in advance." }, { "kind": "report", "citation": "Blake, E. and Nepaul, H. (2024). National Hurricane Center Tropical Cyclone Report: Hurricane Lee (AL132023), 5-16 September 2023. NOAA/NWS, 21 Mar 2024.", "title": "Tropical Cyclone Report: Hurricane Lee (AL132023)", "url": "https://www.nhc.noaa.gov/data/tcr/AL132023_Lee.pdf", "date": "2024-03-21", "written_by": "independent", "quote": "making landfall on Long Island, in southwestern Nova Scotia, later that day around 2000 UTC with maximum sustained winds of about 55 kt well east of the center" }, { "kind": "report", "citation": "Blake, E. and Nepaul, H. (2024). Same report, forecast verification section (no AI model is mentioned anywhere in the report).", "title": "Tropical Cyclone Report: Hurricane Lee (track verification)", "url": "https://www.nhc.noaa.gov/data/tcr/AL132023_Lee.pdf", "date": "2024-03-21", "written_by": "independent", "quote": "Official track forecast errors were exceptionally low through 72 h, and below the previous 5-year period means through 120 h." }, { "kind": "press release", "citation": "Rabier, F. (2023). The AIFS is launched (editorial). ECMWF Newsletter No. 177, Autumn 2023.", "title": "The AIFS is launched", "url": "https://www.ecmwf.int/en/newsletter/177/editorial/aifs-launched", "date": null, "written_by": "deployer", "quote": "We have made these systems available on ECMWF's public charts pages, based on our own initial conditions." }, { "kind": "preprint", "citation": "Lam, R., Sanchez-Gonzalez, A., Willson, M., et al. (2022/2023). GraphCast: Learning skillful medium-range global weather forecasting. arXiv:2212.12794 (published in Science, Nov 2023).", "title": "GraphCast: Learning skillful medium-range global weather forecasting", "url": "https://arxiv.org/abs/2212.12794", "date": "2022-12-24", "written_by": "makers", "quote": "its forecasts support better severe event prediction, including tropical cyclones, atmospheric rivers, and extreme temperatures" }, { "kind": "peer-reviewed study", "citation": "Olivetti L, Messori G (2024). Do data-driven models beat numerical models in forecasting weather extremes? A comparison of IFS HRES, Pangu-Weather, and GraphCast. Geoscientific Model Development 17:7915-7962, doi:10.5194/gmd-17-7915-2024.", "title": "Do data-driven models beat numerical models in forecasting weather extremes? A comparison of IFS HRES, Pangu-Weather, and GraphCast", "url": "https://gmd.copernicus.org/articles/17/7915/2024/", "date": "2024-11-07", "written_by": "independent", "quote": null } ], "replication": { "produced_by": [ "GraphCast trained on decades of ERA5 reanalysis and run live from ECMWF initial conditions on ECMWF's experimental charts", "A long-lived Cabo Verde hurricane whose track was, per NHC, easier than normal to forecast (low climatology-persistence errors)", "Vendor retrospective comparison of its own run against conventional models" ], "must_hold": [ "Independent verification of the specific nine-day run against the official track record (not found in any ECMWF or NHC document among the sources)", "Access to ECMWF initial conditions for the live run", "A forecaster or authority actually consulting the AI run for it to become an attributable benefit" ], "echoes": [ { "date": null, "setting": "2023 season verification by CIRA of GraphCast and peer AI models against operational cyclone track guidance (existing record AIBD-0090)", "model_version": null, "outcome": "recurred", "source": "AIBD-0090 (DeMaria et al. 2024 preprint cited there)" } ] }, "paired_incident": null, "headline": "GraphCast may have forecast Lee's landfall nine days ahead", "metric": "forecast Lee's Nova Scotia landfall about nine days ahead", "comparator": { "against": "traditional physics-based forecasts of Hurricane Lee's landfall (DeepMind's own account)", "before": "only locked in on Nova Scotia about six days in advance", "after": "about nine days in advance", "basis": "assumed", "quote": "In September, a live version of our publicly available GraphCast model, deployed on the ECMWF website, accurately predicted about nine days in advance that Hurricane Lee would make landfall in Nova Scotia. By contrast, traditional forecasts had greater variability in where and when landfall would occur, and only locked in on Nova Scotia about six days in advance.", "url": "https://deepmind.google/discover/blog/graphcast-ai-model-for-faster-and-more-accurate-global-weather-forecasting/" }, "later": { "status": "persisted", "date": "2024-11-07", "note": "An independent Uppsala University evaluation published 7 November 2024 confirmed GraphCast's general advantage over ECMWF's IFS HRES, including on near-surface temperature and wind extremes; it does not examine the Hurricane Lee forecast, and the NHC's March 2024 report on Lee names no AI model.", "quote": "Both data-driven models perform significantly better than ECMWF's IFS HRES globally and in most regions. Most impressively, GraphCast significantly outperforms IFS HRES across all regions and lead times.", "url": "https://gmd.copernicus.org/articles/17/7915/2024/" }, "value": null, "developer_country": "United Kingdom", "deployer_country": "United Kingdom", "unrated_because": null, "brief_notes": null, "brief": null, "revisions": [ { "date": "2026-10-20", "change": "Record drafted from the cited sources.", "source": null, "editor": "AIBD" }, { "date": "2026-10-21", "change": "Headline reworded to state the event without naming who claims it.", "source": null, "editor": "AIBD" }, { "date": "2026-10-21", "change": "Title reworded to state the event without naming who claims it.", "source": null, "editor": "AIBD" }, { "date": "2026-10-21", "change": "Added what the benefit is measured against, what happened since, the model version from the cited sources.", "source": "https://deepmind.google/discover/blog/graphcast-ai-model-for-faster-and-more-accurate-global-weather-forecasting/; https://gmd.copernicus.org/articles/17/7915/2024/; https://deepmind.google/discover/blog/graphcast-ai-model-for-faster-and-more-accurate-global-weather-forecasting/", "editor": "AIBD" }, { "date": "2026-10-21", "change": "Benefit type set to Improved Task Accuracy under Trustible's full taxonomy of 23 types; it was Improved Knowledge Discovery among the six first used.", "source": "https://trustible.ai/post/a-framework-for-measuring-the-benefits-of-ai/", "editor": "AIBD" }, { "date": "2026-10-21", "change": "Country of the developer and the deployer added from the organization's own site or a registry.", "source": "https://en.wikipedia.org/wiki/Google_DeepMind; https://en.wikipedia.org/wiki/European_Centre_for_Medium-Range_Weather_Forecasts", "editor": "AIBD" }, { "date": "2026-10-21", "change": "Prose pass: a rating reason, account, purpose, the system's part rewritten in shorter sentences with abbreviations expanded; facts, figures and quotations unchanged.", "source": null, "editor": "AIBD" }, { "date": "2026-10-21", "change": "Notes about which sources could be read were reworded for readers; facts, figures and quotations unchanged.", "source": null, "editor": "AIBD" }, { "date": "2026-10-22", "change": "Organization name standardized to DeepMind.", "source": null, "editor": "AIBD" } ], "confidence": "studied", "shade": "high", "claim_status": "Independently studied", "claim_basis": "Sources: one independent peer-reviewed study, one independent report, one independent news report, the makers' preprint, the makers' press release and the deployer's press release. The cited evidence includes no finding by a regulator or court.", "profile": { "case_id": "AIBD-0341", "catalog_version": "1.0.0", "source_fingerprint": "9911fcda891b59bf2c4d643ddd69e62d178eee161f30fd0f122f939e02fca957", "collection_refs": [ { "collection_id": "aibd", "version": "snapshot-8bf7cfec9cb185aa" }, { "collection_id": "aibd", "version": "2026-10-25" }, { "collection_id": "viator", "version": "2026-10-25" }, { "collection_id": "chanticleer", "version": "2026-10-25" } ], "source_ids": [ "AIBD-0341-source-0001", "AIBD-0341-source-0002", "AIBD-0341-source-0003", "AIBD-0341-source-0004", "AIBD-0341-source-0005", "AIBD-0341-source-0006", "AIBD-0341-source-0007", "AIBD-0341-source-0008" ], "families": { "strategic assessments": { "state": "not_assessed", "review_state": "not_assessed", "coverage": "partial", "record_ids": [] }, "evaluations": { "state": "not_assessed", "review_state": "not_assessed", "coverage": "partial", "record_ids": [] }, "monetary observations": { "state": "not_assessed", "review_state": "not_assessed", "coverage": "partial", "record_ids": [] }, "institutional decisions": { "state": "not_assessed", "review_state": "not_assessed", "coverage": "partial", "record_ids": [] } }, "fields": { "actors[]": { "state": "value_present", "value": { "kind": "record_fields", "fields": { "developer": "DeepMind", "deployer": "ECMWF (experimental data-driven forecasts on its public charts pages)" } }, "provenance": { "kind": "legacy_record", "basis": "Preserved from the existing AIBD record; external sources were not rechecked.", "record_fields": [ "developer", "deployer" ], "source_refs": [] }, "review_state": "record_mapped", "coverage": "partial" }, "actors[].ownership_control": { "state": "not_assessed", "review_state": "not_assessed", "coverage": "partial" }, "ai_contribution": { "state": "value_present", "value": { "kind": "record_fields", "fields": { "ai_role": { "status": "assessed", "statement": "The only sources for the nine-day Lee forecast are the maker's own blog and a news report quoting the maker's scientist. ECMWF's editorial confirms only that GraphCast ran experimentally on its charts. NHC's Lee report records exceptionally low official track errors without mentioning AI guidance. The AI output is therefore documented as a forecast, not as an input to any decision." } } }, "provenance": { "kind": "legacy_record", "basis": "Preserved from the existing AIBD record; external sources were not rechecked.", "record_fields": [ "ai_role" ], "source_refs": [] }, "review_state": "record_mapped", "coverage": "partial" }, "ai_relationship": { "state": "value_present", "value": { "kind": "record_fields", "fields": { "category": "general benefit", "ai_role": { "status": "assessed", "statement": "The only sources for the nine-day Lee forecast are the maker's own blog and a news report quoting the maker's scientist. ECMWF's editorial confirms only that GraphCast ran experimentally on its charts. NHC's Lee report records exceptionally low official track errors without mentioning AI guidance. The AI output is therefore documented as a forecast, not as an input to any decision." } } }, "provenance": { "kind": "legacy_record", "basis": "Preserved from the existing AIBD record; external sources were not rechecked.", "record_fields": [ "ai_role", "category" ], "source_refs": [] }, "review_state": "record_mapped", "coverage": "partial" }, "assessments[].alternatives": { "state": "not_assessed", "review_state": "not_assessed", "coverage": "partial" }, "assessments[].assessor_date": { "state": "not_assessed", "review_state": "not_assessed", "coverage": "partial" }, "assessments[].depth": { "state": "not_assessed", "review_state": "not_assessed", "coverage": "partial" }, "assessments[].display_confidence": { "state": "value_present", "value": { "kind": "structured", "data": { "confidence": "high", "evidence_word": "studied", "claim_status": "Independently studied", "basis": "Sources: one independent peer-reviewed study, one independent report, one independent news report, the makers' preprint, the makers' press release and the deployer's press release. The cited evidence includes no finding by a regulator or court.", "interpretation": "Existing display rule preserved; the richer outcome-specific confidence question still needs review." } }, "provenance": { "kind": "curatorial", "basis": "Derived from the existing case display properties; not a new evidentiary judgment.", "record_fields": [], "source_refs": [] }, "review_state": "record_mapped", "coverage": "partial" }, "assessments[].rationale": { "state": "value_present", "value": { "kind": "record_fields", "fields": { "ratings": [ { "group": "personal", "reason": "No individual outcome is documented." }, { "group": "organizational", "reason": "General benefit. No cited source documents a forecast office using the GraphCast Lee run in its products." }, { "group": "societal", "reason": "General benefit. No public-safety decision is linked to the run in any cited source." } ] } }, "provenance": { "kind": "legacy_record", "basis": "Preserved from the existing AIBD record; external sources were not rechecked.", "record_fields": [ "ratings" ], "source_refs": [] }, "review_state": "record_mapped", "coverage": "partial" }, "assessments[].rubric_version": { "state": "not_assessed", "review_state": "not_assessed", "coverage": "partial" }, "assessments[].status_basis": { "state": "not_assessed", "review_state": "not_assessed", "coverage": "partial" }, "assessments[].target": { "state": "value_present", "value": { "kind": "record_fields", "fields": { "ratings": [ { "group": "personal", "reason": "No individual outcome is documented." }, { "group": "organizational", "reason": "General benefit. No cited source documents a forecast office using the GraphCast Lee run in its products." }, { "group": "societal", "reason": "General benefit. No public-safety decision is linked to the run in any cited source." } ] } }, "provenance": { "kind": "legacy_record", "basis": "Preserved from the existing AIBD record; external sources were not rechecked.", "record_fields": [ "ratings" ], "source_refs": [] }, "review_state": "record_mapped", "coverage": "partial" }, "availability": { "state": "not_assessed", "review_state": "not_assessed", "coverage": "partial" }, "brief": { "state": "not_assessed", "review_state": "not_assessed", "coverage": "partial" }, "case_kind": { "state": "not_assessed", "review_state": "not_assessed", "coverage": "partial" }, "case_links[]": { "state": "not_assessed", "review_state": "not_assessed", "coverage": "partial" }, "claims[].evidence_links": { "state": "not_assessed", "review_state": "not_assessed", "coverage": "partial" }, "claims[].evidence_strength": { "state": "not_assessed", "review_state": "not_assessed", "coverage": "partial" }, "claims[].missingness": { "state": "not_assessed", "review_state": "not_assessed", "coverage": "partial" }, "claims[].proposition": { "state": "not_assessed", "review_state": "not_assessed", "coverage": "partial" }, "cross_border_flows[]": { "state": "not_assessed", "review_state": "not_assessed", "coverage": "partial" }, "decisions[].action_outcome": { "state": "not_assessed", "review_state": "not_assessed", "coverage": "partial", "family": "institutional decisions" }, "decisions[].grounds": { "state": "not_assessed", "review_state": "not_assessed", "coverage": "partial", "family": "institutional decisions" }, "decisions[].institution_task": { "state": "not_assessed", "review_state": "not_assessed", "coverage": "partial", "family": "institutional decisions" }, "decisions[].success_criterion": { "state": "not_assessed", "review_state": "not_assessed", "coverage": "partial", "family": "institutional decisions" }, "deployment_stage": { "state": "not_assessed", "review_state": "not_assessed", "coverage": "partial" }, "economics[].amount": { "state": "not_assessed", "review_state": "not_assessed", "coverage": "partial", "family": "monetary observations" }, "economics[].costs[]": { "state": "not_assessed", "review_state": "not_assessed", "coverage": "partial", "family": "monetary observations" }, "economics[].counterfactual": { "state": "not_assessed", "review_state": "not_assessed", "coverage": "partial", "family": "monetary observations" }, "economics[].currency_price_basis": { "state": "not_assessed", "review_state": "not_assessed", "coverage": "partial", "family": "monetary observations" }, "economics[].gross_net": { "state": "not_assessed", "review_state": "not_assessed", "coverage": "partial", "family": "monetary observations" }, "economics[].measure_type": { "state": "not_assessed", "review_state": "not_assessed", "coverage": "partial", "family": "monetary observations" }, "economics[].period_unit": { "state": "not_assessed", "review_state": "not_assessed", "coverage": "partial", "family": "monetary observations" }, "economics[].realization": { "state": "not_assessed", "review_state": "not_assessed", "coverage": "partial", "family": "monetary observations" }, "economics[].recipient_payer": { "state": "not_assessed", "review_state": "not_assessed", "coverage": "partial", "family": "monetary observations" }, "economics[].return_payback": { "state": "not_assessed", "review_state": "not_assessed", "coverage": "partial", "family": "monetary observations" }, "economics[].valuation_method": { "state": "not_assessed", "review_state": "not_assessed", "coverage": "partial", "family": "monetary observations" }, "evaluations[].ai_uplift": { "state": "not_assessed", "review_state": "not_assessed", "coverage": "partial", "family": "evaluations" }, "evaluations[].comparator": { "state": "not_assessed", "review_state": "not_assessed", "coverage": "partial", "family": "evaluations" }, "evaluations[].design": { "state": "not_assessed", "review_state": "not_assessed", "coverage": "partial", "family": "evaluations" }, "evaluations[].effect": { "state": "not_assessed", "review_state": "not_assessed", "coverage": "partial", "family": "evaluations" }, "evaluations[].exposure": { "state": "not_assessed", "review_state": "not_assessed", "coverage": "partial", "family": "evaluations" }, "evaluations[].id": { "state": "not_assessed", "review_state": "not_assessed", "coverage": "partial", "family": "evaluations" }, "evaluations[].measurement_method": { "state": "not_assessed", "review_state": "not_assessed", "coverage": "partial", "family": "evaluations" }, "evaluations[].metric": { "state": "not_assessed", "provenance": { "kind": "legacy_record", "basis": "Mapped from the existing case description without a new external source review.", "record_fields": [ "metric" ], "source_refs": [] }, "review_state": "not_assessed", "coverage": "partial", "family": "evaluations", "display": { "answer": "forecast Lee's Nova Scotia landfall about nine days ahead", "editor_note": "" } }, "evaluations[].reproduction_materials": { "state": "not_assessed", "review_state": "not_assessed", "coverage": "partial", "family": "evaluations" }, "evaluations[].setting_sample": { "state": "not_assessed", "review_state": "not_assessed", "coverage": "partial", "family": "evaluations" }, "evaluations[].uncertainty_limitations": { "state": "not_assessed", "review_state": "not_assessed", "coverage": "partial", "family": "evaluations" }, "external_references[]": { "state": "not_assessed", "review_state": "not_assessed", "coverage": "partial" }, "follow_up[]": { "state": "value_present", "value": { "kind": "record_fields", "fields": { "later": { "status": "persisted", "date": "2024-11-07", "note": "An independent Uppsala University evaluation published 7 November 2024 confirmed GraphCast's general advantage over ECMWF's IFS HRES, including on near-surface temperature and wind extremes; it does not examine the Hurricane Lee forecast, and the NHC's March 2024 report on Lee names no AI model.", "quote": "Both data-driven models perform significantly better than ECMWF's IFS HRES globally and in most regions. Most impressively, GraphCast significantly outperforms IFS HRES across all regions and lead times.", "url": "https://gmd.copernicus.org/articles/17/7915/2024/" } } }, "provenance": { "kind": "legacy_record", "basis": "Preserved from the existing AIBD record; external sources were not rechecked.", "record_fields": [ "later" ], "source_refs": [] }, "review_state": "record_mapped", "coverage": "partial" }, "human_oversight": { "state": "not_assessed", "review_state": "not_assessed", "coverage": "partial" }, "id": { "state": "value_present", "value": { "kind": "record_fields", "fields": { "id": "AIBD-0341" } }, "provenance": { "kind": "legacy_record", "basis": "Preserved from the existing AIBD record; external sources were not rechecked.", "record_fields": [ "id" ], "source_refs": [] }, "review_state": "record_mapped", "coverage": "partial" }, "infrastructure_dependencies[]": { "state": "not_assessed", "review_state": "not_assessed", "coverage": "partial" }, "outcomes[].beneficiaries": { "state": "not_assessed", "review_state": "not_assessed", "coverage": "partial" }, "outcomes[].beneficiary_count": { "state": "not_assessed", "review_state": "not_assessed", "coverage": "partial" }, "outcomes[].benefit_type": { "state": "value_present", "value": { "kind": "record_fields", "fields": { "benefit_type": "Improved Task Accuracy", "taxonomy_note": "The nine-day claim is vendor-sourced and no forecaster use of the run is documented." } }, "provenance": { "kind": "legacy_record", "basis": "Preserved from the existing AIBD record; external sources were not rechecked.", "record_fields": [ "benefit_type", "taxonomy_note" ], "source_refs": [] }, "review_state": "record_mapped", "coverage": "partial" }, "outcomes[].claim": { "state": "value_present", "value": { "kind": "record_fields", "fields": { "account": "Google DeepMind's blog post of 14 November 2023 describes a live version of its publicly available GraphCast model, deployed on the ECMWF website. In September 2023 it predicted about nine days in advance that Hurricane Lee would make landfall in Nova Scotia. MIT Technology Review (14 November 2023) relayed the claim from DeepMind staff research scientist Rémi Lam. It added that traditional forecasting models pinpointed Nova Scotia only six days in advance. The article quotes no ECMWF staff on Lee. ECMWF's Newsletter 177 editorial (Autumn 2023) confirms that GraphCast, Pangu-Weather and FourCastNet were made available on ECMWF's public charts pages from ECMWF's own initial conditions. The NHC tropical cyclone report on Lee (21 March 2024) records the landfall. Lee, by then post-tropical, made landfall on Long Island in southwestern Nova Scotia around 2000 UTC on 16 September 2023. Maximum sustained winds were about 55 kt. NHC official track errors were exceptionally low through 72 h and below five-year means through 120 h. The report mentions no AI model. No ECMWF document recording the Lee forecast is on record, and the NHC 2023 verification report contains no AI-model entry. It found only an intensity-structure mention of Lee in the independent CIRA preprint. The forecast itself is dated only as “September” by the vendor. No cited source documents a forecaster or authority acting on the GraphCast Lee run.", "benefit_type": "Improved Task Accuracy" } }, "provenance": { "kind": "legacy_record", "basis": "Preserved from the existing AIBD record; external sources were not rechecked.", "record_fields": [ "account", "benefit_type" ], "source_refs": [] }, "review_state": "record_mapped", "coverage": "partial" }, "outcomes[].distribution": { "state": "not_assessed", "review_state": "not_assessed", "coverage": "partial" }, "outcomes[].duration": { "state": "not_assessed", "review_state": "not_assessed", "coverage": "partial" }, "outcomes[].id": { "state": "not_assessed", "review_state": "not_assessed", "coverage": "partial" }, "outcomes[].stakeholder_group": { "state": "value_present", "value": { "kind": "record_fields", "fields": { "ratings": [ { "group": "personal", "reason": "No individual outcome is documented." }, { "group": "organizational", "reason": "General benefit. No cited source documents a forecast office using the GraphCast Lee run in its products." }, { "group": "societal", "reason": "General benefit. No public-safety decision is linked to the run in any cited source." } ] } }, "provenance": { "kind": "legacy_record", "basis": "Preserved from the existing AIBD record; external sources were not rechecked.", "record_fields": [ "ratings" ], "source_refs": [] }, "review_state": "record_mapped", "coverage": "partial" }, "outcomes[].status": { "state": "not_assessed", "review_state": "not_assessed", "coverage": "partial" }, "outcomes[].tradeoffs": { "state": "not_assessed", "review_state": "not_assessed", "coverage": "partial" }, "outcomes[].unexpected": { "state": "value_present", "value": { "kind": "record_fields", "fields": { "unexpected": false, "purpose": "Machine-learning global medium-range weather forecasting (10 days, 0.25 degree), including severe-event prediction such as tropical cyclone tracks. This forecast was that purpose." } }, "provenance": { "kind": "legacy_record", "basis": "Preserved from the existing AIBD record; external sources were not rechecked.", "record_fields": [ "unexpected", "purpose" ], "source_refs": [] }, "review_state": "record_mapped", "coverage": "partial" }, "places[]": { "state": "value_present", "value": { "kind": "record_fields", "fields": { "location": "Long Island, southwestern Nova Scotia, Canada (landfall)", "developer_country": "United Kingdom", "deployer_country": "United Kingdom" } }, "provenance": { "kind": "legacy_record", "basis": "Preserved from the existing AIBD record; external sources were not rechecked.", "record_fields": [ "location", "developer_country", "deployer_country" ], "source_refs": [] }, "review_state": "record_mapped", "coverage": "partial" }, "purpose": { "state": "value_present", "value": { "kind": "record_fields", "fields": { "purpose": "Machine-learning global medium-range weather forecasting (10 days, 0.25 degree), including severe-event prediction such as tropical cyclone tracks. This forecast was that purpose." } }, "provenance": { "kind": "legacy_record", "basis": "Preserved from the existing AIBD record; external sources were not rechecked.", "record_fields": [ "purpose" ], "source_refs": [] }, "review_state": "record_mapped", "coverage": "partial" }, "record_dates": { "state": "value_present", "value": { "kind": "record_fields", "fields": { "date_observed": "2023-09-16", "revisions": [ { "date": "2026-10-20", "change": "Record drafted from the cited sources.", "editor": "AIBD" }, { "date": "2026-10-21", "change": "Headline reworded to state the event without naming who claims it.", "editor": "AIBD" }, { "date": "2026-10-21", "change": "Title reworded to state the event without naming who claims it.", "editor": "AIBD" }, { "date": "2026-10-21", "change": "Added what the benefit is measured against, what happened since, the model version from the cited sources.", "source": "https://deepmind.google/discover/blog/graphcast-ai-model-for-faster-and-more-accurate-global-weather-forecasting/; https://gmd.copernicus.org/articles/17/7915/2024/; https://deepmind.google/discover/blog/graphcast-ai-model-for-faster-and-more-accurate-global-weather-forecasting/", "editor": "AIBD" }, { "date": "2026-10-21", "change": "Benefit type set to Improved Task Accuracy under Trustible's full taxonomy of 23 types; it was Improved Knowledge Discovery among the six first used.", "source": "https://trustible.ai/post/a-framework-for-measuring-the-benefits-of-ai/", "editor": "AIBD" }, { "date": "2026-10-21", "change": "Country of the developer and the deployer added from the organization's own site or a registry.", "source": "https://en.wikipedia.org/wiki/Google_DeepMind; https://en.wikipedia.org/wiki/European_Centre_for_Medium-Range_Weather_Forecasts", "editor": "AIBD" }, { "date": "2026-10-21", "change": "Prose pass: a rating reason, account, purpose, the system's part rewritten in shorter sentences with abbreviations expanded; facts, figures and quotations unchanged.", "editor": "AIBD" }, { "date": "2026-10-21", "change": "Notes about which sources could be read were reworded for readers; facts, figures and quotations unchanged.", "editor": "AIBD" }, { "date": "2026-10-22", "change": "Organization name standardized to DeepMind.", "editor": "AIBD" } ] } }, "provenance": { "kind": "legacy_record", "basis": "Preserved from the existing AIBD record; external sources were not rechecked.", "record_fields": [ "date_observed", "revisions" ], "source_refs": [] }, "review_state": "record_mapped", "coverage": "partial" }, "replication.attempts[]": { "state": "value_present", "value": { "kind": "record_fields", "fields": { "replication": { "produced_by": [ "GraphCast trained on decades of ERA5 reanalysis and run live from ECMWF initial conditions on ECMWF's experimental charts", "A long-lived Cabo Verde hurricane whose track was, per NHC, easier than normal to forecast (low climatology-persistence errors)", "Vendor retrospective comparison of its own run against conventional models" ], "must_hold": [ "Independent verification of the specific nine-day run against the official track record (not found in any ECMWF or NHC document among the sources)", "Access to ECMWF initial conditions for the live run", "A forecaster or authority actually consulting the AI run for it to become an attributable benefit" ], "echoes": [ { "setting": "2023 season verification by CIRA of GraphCast and peer AI models against operational cyclone track guidance (existing record AIBD-0090)", "outcome": "recurred", "source": "AIBD-0090 (DeMaria et al. 2024 preprint cited there)" } ] } } }, "provenance": { "kind": "legacy_record", "basis": "Preserved from the existing AIBD record; external sources were not rechecked.", "record_fields": [ "replication" ], "source_refs": [] }, "review_state": "record_mapped", "coverage": "partial" }, "replication.conditions": { "state": "value_present", "value": { "kind": "record_fields", "fields": { "replication": { "produced_by": [ "GraphCast trained on decades of ERA5 reanalysis and run live from ECMWF initial conditions on ECMWF's experimental charts", "A long-lived Cabo Verde hurricane whose track was, per NHC, easier than normal to forecast (low climatology-persistence errors)", "Vendor retrospective comparison of its own run against conventional models" ], "must_hold": [ "Independent verification of the specific nine-day run against the official track record (not found in any ECMWF or NHC document among the sources)", "Access to ECMWF initial conditions for the live run", "A forecaster or authority actually consulting the AI run for it to become an attributable benefit" ], "echoes": [ { "setting": "2023 season verification by CIRA of GraphCast and peer AI models against operational cyclone track guidance (existing record AIBD-0090)", "outcome": "recurred", "source": "AIBD-0090 (DeMaria et al. 2024 preprint cited there)" } ] } } }, "provenance": { "kind": "legacy_record", "basis": "Preserved from the existing AIBD record; external sources were not rechecked.", "record_fields": [ "replication" ], "source_refs": [] }, "review_state": "record_mapped", "coverage": "partial" }, "revision_history[]": { "state": "value_present", "value": { "kind": "record_fields", "fields": { "revisions": [ { "date": "2026-10-20", "change": "Record drafted from the cited sources.", "editor": "AIBD" }, { "date": "2026-10-21", "change": "Headline reworded to state the event without naming who claims it.", "editor": "AIBD" }, { "date": "2026-10-21", "change": "Title reworded to state the event without naming who claims it.", "editor": "AIBD" }, { "date": "2026-10-21", "change": "Added what the benefit is measured against, what happened since, the model version from the cited sources.", "source": "https://deepmind.google/discover/blog/graphcast-ai-model-for-faster-and-more-accurate-global-weather-forecasting/; https://gmd.copernicus.org/articles/17/7915/2024/; https://deepmind.google/discover/blog/graphcast-ai-model-for-faster-and-more-accurate-global-weather-forecasting/", "editor": "AIBD" }, { "date": "2026-10-21", "change": "Benefit type set to Improved Task Accuracy under Trustible's full taxonomy of 23 types; it was Improved Knowledge Discovery among the six first used.", "source": "https://trustible.ai/post/a-framework-for-measuring-the-benefits-of-ai/", "editor": "AIBD" }, { "date": "2026-10-21", "change": "Country of the developer and the deployer added from the organization's own site or a registry.", "source": "https://en.wikipedia.org/wiki/Google_DeepMind; https://en.wikipedia.org/wiki/European_Centre_for_Medium-Range_Weather_Forecasts", "editor": "AIBD" }, { "date": "2026-10-21", "change": "Prose pass: a rating reason, account, purpose, the system's part rewritten in shorter sentences with abbreviations expanded; facts, figures and quotations unchanged.", "editor": "AIBD" }, { "date": "2026-10-21", "change": "Notes about which sources could be read were reworded for readers; facts, figures and quotations unchanged.", "editor": "AIBD" }, { "date": "2026-10-22", "change": "Organization name standardized to DeepMind.", "editor": "AIBD" } ] } }, "provenance": { "kind": "legacy_record", "basis": "Preserved from the existing AIBD record; external sources were not rechecked.", "record_fields": [ "revisions" ], "source_refs": [] }, "review_state": "record_mapped", "coverage": "partial" }, "sector": { "state": "value_present", "value": { "kind": "record_fields", "fields": { "domain": "Weather forecasting / tropical cyclones", "segment": "Public-sector meteorological service; AI research laboratory" } }, "provenance": { "kind": "legacy_record", "basis": "Preserved from the existing AIBD record; external sources were not rechecked.", "record_fields": [ "domain", "segment" ], "source_refs": [] }, "review_state": "record_mapped", "coverage": "partial" }, "sources[].access_version": { "state": "not_assessed", "review_state": "not_assessed", "coverage": "partial" }, "sources[].citation_locator": { "state": "value_present", "value": { "kind": "record_fields", "fields": { "evidence": [ { "kind": "press release", "citation": "Google DeepMind (2023). GraphCast: AI model for faster and more accurate global weather forecasting. DeepMind blog, 14 Nov 2023.", "title": "GraphCast: AI model for faster and more accurate global weather forecasting", "url": "https://deepmind.google/discover/blog/graphcast-ai-model-for-faster-and-more-accurate-global-weather-forecasting/", "date": "2023-11-14", "written_by": "makers", "quote": "a live version of our publicly available GraphCast model, deployed on the ECMWF website, accurately predicted about nine days in advance that Hurricane Lee would make landfall in Nova Scotia" }, { "kind": "news report", "citation": "Heikkilä, M. (2023). Google DeepMind's weather AI can forecast extreme weather faster and more accurately. MIT Technology Review, 14 Nov 2023.", "title": "Google DeepMind's weather AI can forecast extreme weather faster and more accurately", "url": "https://web.archive.org/web/20231114164801/https://www.technologyreview.com/2023/11/14/1083366/google-deepminds-weather-ai-can-forecast-extreme-weather-quicker-and-more-accurately/", "date": "2023-11-14", "written_by": "independent", "quote": "In September, GraphCast accurately predicted that Hurricane Lee would make landfall in Nova Scotia nine days in advance, says Rémi Lam, a staff research scientist at Google DeepMind." }, { "kind": "news report", "citation": "Heikkilä, M. (2023). Same article, comparison with conventional models.", "title": "Google DeepMind's weather AI can forecast extreme weather faster and more accurately (conventional-model comparison)", "url": "https://web.archive.org/web/20231114164801/https://www.technologyreview.com/2023/11/14/1083366/google-deepminds-weather-ai-can-forecast-extreme-weather-quicker-and-more-accurately/", "date": "2023-11-14", "written_by": "independent", "quote": "Traditional weather forecasting models pinpointed the hurricane to Nova Scotia only six days in advance." }, { "kind": "report", "citation": "Blake, E. and Nepaul, H. (2024). National Hurricane Center Tropical Cyclone Report: Hurricane Lee (AL132023), 5-16 September 2023. NOAA/NWS, 21 Mar 2024.", "title": "Tropical Cyclone Report: Hurricane Lee (AL132023)", "url": "https://www.nhc.noaa.gov/data/tcr/AL132023_Lee.pdf", "date": "2024-03-21", "written_by": "independent", "quote": "making landfall on Long Island, in southwestern Nova Scotia, later that day around 2000 UTC with maximum sustained winds of about 55 kt well east of the center" }, { "kind": "report", "citation": "Blake, E. and Nepaul, H. (2024). Same report, forecast verification section (no AI model is mentioned anywhere in the report).", "title": "Tropical Cyclone Report: Hurricane Lee (track verification)", "url": "https://www.nhc.noaa.gov/data/tcr/AL132023_Lee.pdf", "date": "2024-03-21", "written_by": "independent", "quote": "Official track forecast errors were exceptionally low through 72 h, and below the previous 5-year period means through 120 h." }, { "kind": "press release", "citation": "Rabier, F. (2023). The AIFS is launched (editorial). ECMWF Newsletter No. 177, Autumn 2023.", "title": "The AIFS is launched", "url": "https://www.ecmwf.int/en/newsletter/177/editorial/aifs-launched", "written_by": "deployer", "quote": "We have made these systems available on ECMWF's public charts pages, based on our own initial conditions." }, { "kind": "preprint", "citation": "Lam, R., Sanchez-Gonzalez, A., Willson, M., et al. (2022/2023). GraphCast: Learning skillful medium-range global weather forecasting. arXiv:2212.12794 (published in Science, Nov 2023).", "title": "GraphCast: Learning skillful medium-range global weather forecasting", "url": "https://arxiv.org/abs/2212.12794", "date": "2022-12-24", "written_by": "makers", "quote": "its forecasts support better severe event prediction, including tropical cyclones, atmospheric rivers, and extreme temperatures" }, { "kind": "peer-reviewed study", "citation": "Olivetti L, Messori G (2024). Do data-driven models beat numerical models in forecasting weather extremes? A comparison of IFS HRES, Pangu-Weather, and GraphCast. Geoscientific Model Development 17:7915-7962, doi:10.5194/gmd-17-7915-2024.", "title": "Do data-driven models beat numerical models in forecasting weather extremes? A comparison of IFS HRES, Pangu-Weather, and GraphCast", "url": "https://gmd.copernicus.org/articles/17/7915/2024/", "date": "2024-11-07", "written_by": "independent" } ] } }, "provenance": { "kind": "legacy_record", "basis": "Preserved from the existing AIBD record; external sources were not rechecked.", "record_fields": [ "evidence" ], "source_refs": [] }, "review_state": "record_mapped", "coverage": "partial" }, "sources[].id": { "state": "value_present", "value": { "kind": "identifiers", "identifiers": [ "AIBD-0341-source-0001", "AIBD-0341-source-0002", "AIBD-0341-source-0003", "AIBD-0341-source-0004", "AIBD-0341-source-0005", "AIBD-0341-source-0006", "AIBD-0341-source-0007", "AIBD-0341-source-0008" ], "role": "Existing evidence items, in their original order" }, "provenance": { "kind": "curatorial", "basis": "Stable within the fingerprinted record version; no source content or source review has been added.", "record_fields": [], "source_refs": [] }, "review_state": "record_mapped", "coverage": "complete" }, "sources[].language": { "state": "not_assessed", "review_state": "not_assessed", "coverage": "partial" }, "sources[].relationship": { "state": "value_present", "value": { "kind": "record_fields", "fields": { "evidence": [ { "kind": "press release", "citation": "Google DeepMind (2023). GraphCast: AI model for faster and more accurate global weather forecasting. DeepMind blog, 14 Nov 2023.", "title": "GraphCast: AI model for faster and more accurate global weather forecasting", "url": "https://deepmind.google/discover/blog/graphcast-ai-model-for-faster-and-more-accurate-global-weather-forecasting/", "date": "2023-11-14", "written_by": "makers", "quote": "a live version of our publicly available GraphCast model, deployed on the ECMWF website, accurately predicted about nine days in advance that Hurricane Lee would make landfall in Nova Scotia" }, { "kind": "news report", "citation": "Heikkilä, M. (2023). Google DeepMind's weather AI can forecast extreme weather faster and more accurately. MIT Technology Review, 14 Nov 2023.", "title": "Google DeepMind's weather AI can forecast extreme weather faster and more accurately", "url": "https://web.archive.org/web/20231114164801/https://www.technologyreview.com/2023/11/14/1083366/google-deepminds-weather-ai-can-forecast-extreme-weather-quicker-and-more-accurately/", "date": "2023-11-14", "written_by": "independent", "quote": "In September, GraphCast accurately predicted that Hurricane Lee would make landfall in Nova Scotia nine days in advance, says Rémi Lam, a staff research scientist at Google DeepMind." }, { "kind": "news report", "citation": "Heikkilä, M. (2023). Same article, comparison with conventional models.", "title": "Google DeepMind's weather AI can forecast extreme weather faster and more accurately (conventional-model comparison)", "url": "https://web.archive.org/web/20231114164801/https://www.technologyreview.com/2023/11/14/1083366/google-deepminds-weather-ai-can-forecast-extreme-weather-quicker-and-more-accurately/", "date": "2023-11-14", "written_by": "independent", "quote": "Traditional weather forecasting models pinpointed the hurricane to Nova Scotia only six days in advance." }, { "kind": "report", "citation": "Blake, E. and Nepaul, H. (2024). National Hurricane Center Tropical Cyclone Report: Hurricane Lee (AL132023), 5-16 September 2023. NOAA/NWS, 21 Mar 2024.", "title": "Tropical Cyclone Report: Hurricane Lee (AL132023)", "url": "https://www.nhc.noaa.gov/data/tcr/AL132023_Lee.pdf", "date": "2024-03-21", "written_by": "independent", "quote": "making landfall on Long Island, in southwestern Nova Scotia, later that day around 2000 UTC with maximum sustained winds of about 55 kt well east of the center" }, { "kind": "report", "citation": "Blake, E. and Nepaul, H. (2024). Same report, forecast verification section (no AI model is mentioned anywhere in the report).", "title": "Tropical Cyclone Report: Hurricane Lee (track verification)", "url": "https://www.nhc.noaa.gov/data/tcr/AL132023_Lee.pdf", "date": "2024-03-21", "written_by": "independent", "quote": "Official track forecast errors were exceptionally low through 72 h, and below the previous 5-year period means through 120 h." }, { "kind": "press release", "citation": "Rabier, F. (2023). The AIFS is launched (editorial). ECMWF Newsletter No. 177, Autumn 2023.", "title": "The AIFS is launched", "url": "https://www.ecmwf.int/en/newsletter/177/editorial/aifs-launched", "written_by": "deployer", "quote": "We have made these systems available on ECMWF's public charts pages, based on our own initial conditions." }, { "kind": "preprint", "citation": "Lam, R., Sanchez-Gonzalez, A., Willson, M., et al. (2022/2023). GraphCast: Learning skillful medium-range global weather forecasting. arXiv:2212.12794 (published in Science, Nov 2023).", "title": "GraphCast: Learning skillful medium-range global weather forecasting", "url": "https://arxiv.org/abs/2212.12794", "date": "2022-12-24", "written_by": "makers", "quote": "its forecasts support better severe event prediction, including tropical cyclones, atmospheric rivers, and extreme temperatures" }, { "kind": "peer-reviewed study", "citation": "Olivetti L, Messori G (2024). Do data-driven models beat numerical models in forecasting weather extremes? A comparison of IFS HRES, Pangu-Weather, and GraphCast. Geoscientific Model Development 17:7915-7962, doi:10.5194/gmd-17-7915-2024.", "title": "Do data-driven models beat numerical models in forecasting weather extremes? A comparison of IFS HRES, Pangu-Weather, and GraphCast", "url": "https://gmd.copernicus.org/articles/17/7915/2024/", "date": "2024-11-07", "written_by": "independent" } ] } }, "provenance": { "kind": "legacy_record", "basis": "Preserved from the existing AIBD record; external sources were not rechecked.", "record_fields": [ "evidence" ], "source_refs": [] }, "review_state": "record_mapped", "coverage": "partial" }, "sources[].upstream_sources": { "state": "not_assessed", "review_state": "not_assessed", "coverage": "partial" }, "strategic_assessments[]": { "state": "not_assessed", "review_state": "not_assessed", "coverage": "partial", "family": "strategic assessments" }, "summary": { "state": "value_present", "value": { "kind": "record_fields", "fields": { "summary": "DeepMind says a live GraphCast run on ECMWF's site forecast Lee's Nova Scotia landfall about nine days ahead; NHC records landfall 16 September 2023; no forecaster use of the run is documented.", "account": "Google DeepMind's blog post of 14 November 2023 describes a live version of its publicly available GraphCast model, deployed on the ECMWF website. In September 2023 it predicted about nine days in advance that Hurricane Lee would make landfall in Nova Scotia. MIT Technology Review (14 November 2023) relayed the claim from DeepMind staff research scientist Rémi Lam. It added that traditional forecasting models pinpointed Nova Scotia only six days in advance. The article quotes no ECMWF staff on Lee. ECMWF's Newsletter 177 editorial (Autumn 2023) confirms that GraphCast, Pangu-Weather and FourCastNet were made available on ECMWF's public charts pages from ECMWF's own initial conditions. The NHC tropical cyclone report on Lee (21 March 2024) records the landfall. Lee, by then post-tropical, made landfall on Long Island in southwestern Nova Scotia around 2000 UTC on 16 September 2023. Maximum sustained winds were about 55 kt. NHC official track errors were exceptionally low through 72 h and below five-year means through 120 h. The report mentions no AI model. No ECMWF document recording the Lee forecast is on record, and the NHC 2023 verification report contains no AI-model entry. It found only an intensity-structure mention of Lee in the independent CIRA preprint. The forecast itself is dated only as “September” by the vendor. No cited source documents a forecaster or authority acting on the GraphCast Lee run." } }, "provenance": { "kind": "legacy_record", "basis": "Preserved from the existing AIBD record; external sources were not rechecked.", "record_fields": [ "summary", "account" ], "source_refs": [] }, "review_state": "record_mapped", "coverage": "partial" }, "systems[].autonomy_permissions": { "state": "not_assessed", "review_state": "not_assessed", "coverage": "partial" }, "systems[].component_role": { "state": "value_present", "value": { "kind": "text", "text": "GraphCast generated weather forecasts, including the projected path of Hurricane Lee." }, "provenance": { "kind": "legacy_record", "basis": "Restated the mechanical task already described in the existing system and AI-role fields. No new source review is claimed.", "record_fields": [ "system", "ai_role" ], "source_refs": [] }, "review_state": "record_mapped", "coverage": "partial" }, "systems[].deployment_configuration": { "state": "value_present", "value": { "kind": "text", "text": "Researchers used the live GraphCast forecasts available through ECMWF." }, "provenance": { "kind": "legacy_record", "basis": "Separated the model, software, hardware, or operation already described in the existing record. No new source review is claimed.", "record_fields": [ "model_version", "system", "ai_role" ], "source_refs": [] }, "review_state": "record_mapped", "coverage": "partial" }, "systems[].inputs_outputs": { "state": "not_assessed", "review_state": "not_assessed", "coverage": "partial" }, "systems[].model_name": { "state": "value_present", "value": { "kind": "text", "text": "GraphCast." }, "provenance": { "kind": "legacy_record", "basis": "Separated the model, software, hardware, or operation already described in the existing record. No new source review is claimed.", "record_fields": [ "model_version", "system", "ai_role" ], "source_refs": [] }, "review_state": "record_mapped", "coverage": "partial" }, "systems[].model_version": { "state": "value_present", "value": { "kind": "record_fields", "fields": { "model_version": "GraphCast (live version deployed on the ECMWF website)" } }, "provenance": { "kind": "legacy_record", "basis": "Preserved from the existing AIBD record; external sources were not rechecked.", "record_fields": [ "model_version" ], "source_refs": [] }, "review_state": "record_mapped", "coverage": "partial", "display": { "answer": "Exact release not established.", "editor_note": "" } }, "systems[].product_name": { "state": "value_present", "value": { "kind": "record_fields", "fields": { "system": "GraphCast (Google DeepMind graph neural network weather model), experimental live run on ECMWF public charts" } }, "provenance": { "kind": "legacy_record", "basis": "Preserved from the existing AIBD record; external sources were not rechecked.", "record_fields": [ "system" ], "source_refs": [] }, "review_state": "record_mapped", "coverage": "partial" }, "systems[].provider": { "state": "value_present", "value": { "kind": "structured", "data": { "application_developer": "DeepMind" } }, "provenance": { "kind": "legacy_record", "basis": "Mapped from the existing case description without a new external source review.", "record_fields": [ "developer" ], "source_refs": [] }, "review_state": "record_mapped", "coverage": "partial" }, "taxonomy_crosswalks[]": { "state": "not_assessed", "review_state": "not_assessed", "coverage": "partial" }, "title": { "state": "value_present", "value": { "kind": "record_fields", "fields": { "title": "A GraphCast live run on ECMWF charts may have forecast Hurricane Lee's Nova Scotia landfall about nine days ahead", "headline": "GraphCast may have forecast Lee's landfall nine days ahead" } }, "provenance": { "kind": "legacy_record", "basis": "Preserved from the existing AIBD record; external sources were not rechecked.", "record_fields": [ "title", "headline" ], "source_refs": [] }, "review_state": "record_mapped", "coverage": "partial" }, "version": { "state": "value_present", "value": { "kind": "identifiers", "identifiers": [ "9911fcda891b59bf2c4d643ddd69e62d178eee161f30fd0f122f939e02fca957" ], "role": "SHA-256 of normalized original case data" }, "provenance": { "kind": "curatorial", "basis": "Deterministic content version assigned by the local migration.", "record_fields": [], "source_refs": [] }, "review_state": "record_mapped", "coverage": "complete" }, "workflow": { "state": "value_present", "value": { "kind": "record_fields", "fields": { "account": "Google DeepMind's blog post of 14 November 2023 describes a live version of its publicly available GraphCast model, deployed on the ECMWF website. In September 2023 it predicted about nine days in advance that Hurricane Lee would make landfall in Nova Scotia. MIT Technology Review (14 November 2023) relayed the claim from DeepMind staff research scientist Rémi Lam. It added that traditional forecasting models pinpointed Nova Scotia only six days in advance. The article quotes no ECMWF staff on Lee. ECMWF's Newsletter 177 editorial (Autumn 2023) confirms that GraphCast, Pangu-Weather and FourCastNet were made available on ECMWF's public charts pages from ECMWF's own initial conditions. The NHC tropical cyclone report on Lee (21 March 2024) records the landfall. Lee, by then post-tropical, made landfall on Long Island in southwestern Nova Scotia around 2000 UTC on 16 September 2023. Maximum sustained winds were about 55 kt. NHC official track errors were exceptionally low through 72 h and below five-year means through 120 h. The report mentions no AI model. No ECMWF document recording the Lee forecast is on record, and the NHC 2023 verification report contains no AI-model entry. It found only an intensity-structure mention of Lee in the independent CIRA preprint. The forecast itself is dated only as “September” by the vendor. No cited source documents a forecaster or authority acting on the GraphCast Lee run.", "replication": { "produced_by": [ "GraphCast trained on decades of ERA5 reanalysis and run live from ECMWF initial conditions on ECMWF's experimental charts", "A long-lived Cabo Verde hurricane whose track was, per NHC, easier than normal to forecast (low climatology-persistence errors)", "Vendor retrospective comparison of its own run against conventional models" ], "must_hold": [ "Independent verification of the specific nine-day run against the official track record (not found in any ECMWF or NHC document among the sources)", "Access to ECMWF initial conditions for the live run", "A forecaster or authority actually consulting the AI run for it to become an attributable benefit" ], "echoes": [ { "setting": "2023 season verification by CIRA of GraphCast and peer AI models against operational cyclone track guidance (existing record AIBD-0090)", "outcome": "recurred", "source": "AIBD-0090 (DeMaria et al. 2024 preprint cited there)" } ] } } }, "provenance": { "kind": "legacy_record", "basis": "Preserved from the existing AIBD record; external sources were not rechecked.", "record_fields": [ "account", "replication" ], "source_refs": [] }, "review_state": "record_mapped", "coverage": "partial" } }, "summary": { "total": 91, "addressed": 91, "known": 32, "reviewed": 0, "record_mapped": 32, "not_assessed": 59, "complete": false, "by_state": { "value_present": 32, "not_reported": 0, "unresolved": 0, "not_assessed": 59, "not_applicable": 0, "withheld": 0, "source_unavailable": 0 } } } }