{ "id": "AIBD-0090", "title": "Independent 2023-season verification finds GraphCast and three peer AI models match the best operational cyclone track models", "summary": "CIRA/Colorado State evaluation: GraphCast and three AI models match top operational cyclone track models in 2023; adding all four cut consensus error 11% at 120 h.", "date_observed": "2024-09-08", "date_basis": "unassessed", "date_precision": "unassessed", "benefit_status": null, "source_collection": null, "source_entry": null, "account": "Google DeepMind's GraphCast was run live on ECMWF's public charts from 2023. DeepMind's blog of 14 November 2023 says the live model predicted Hurricane Lee's landfall in Nova Scotia in September 2023 about nine days in advance. The blog says only “In September”, so the year is implied by its 14 November 2023 post date. The ECMWF publications read do not document the case. MIT Technology Review quoted ECMWF's Peter Dueben saying the models are so good they cannot be avoided. An independent CIRA/Colorado State evaluation applied NHC verification to May-November 2023 cyclones. It found GraphCast-operational and three other AI models' track errors comparable to the best operational models. Adding all four improved the NHC track consensus by 11% at 120 h.", "category": "general benefit", "unexpected": false, "purpose": "Medium-range global weather forecasting by machine learning, including severe-event prediction such as tropical cyclone tracks.", "system": "GraphCast (graph neural network global weather model)", "model_version": "GraphCast live experimental run on ECMWF charts (2023); GraphCast-operational in the CIRA evaluation", "developer": "DeepMind", "deployer": "ECMWF (experimental live runs on public charts); CIRA/Colorado State University (evaluation)", "location": null, "domain": "Weather forecasting / tropical cyclones", "segment": "Meteorological research and operational forecast centers", "benefit_type": "Improved Task Accuracy", "taxonomy_note": null, "registry_ids": {}, "ratings": [ { "group": "personal", "depth": null, "reason": "Skill evaluation, no verified discrete event." }, { "group": "organizational", "depth": null, "reason": "Skill evaluation, no verified discrete event." }, { "group": "societal", "depth": null, "reason": "Skill evaluation, no verified discrete event." } ], "ai_role": { "status": "assessed", "statement": "The CIRA preprint isolates the AI models' contribution via NHC verification and consensus experiments. The nine-day Hurricane Lee landfall forecast rests on vendor statements and press quotes of ECMWF staff. ECMWF documents read (Newsletters 177 and 178, science blog, Severe Event Catalog) do not record it." }, "evidence": [ { "kind": "preprint", "citation": "DeMaria, M., Franklin, J. L., Chirokova, G., Radford, J., DeMaria, R., Musgrave, K. D., Ebert-Uphoff, I. (2024). Evaluation of Tropical Cyclone Track and Intensity Forecasts from Artificial Intelligence Weather Prediction (AIWP) Models. arXiv:2409.06735, submitted 8 Sep 2024; the preprint's disclaimer reads 'This work has been submitted to the Artificial Intelligence in the Earth Sciences American Meteorological Society journal'. The quote is on p. 23 of the full PDF, not on the abstract page.", "title": "Evaluation of Tropical Cyclone Track and Intensity Forecasts from AIWP Models", "url": "https://arxiv.org/abs/2409.06735", "date": "2024-09-08", "written_by": "independent", "quote": "When all four were added the track consensus improved by 11% at 120 h, with improvements that were statistically significant at 72-120 h." }, { "kind": "press release", "citation": "Google DeepMind (2023). GraphCast: AI model for faster and more accurate global weather forecasting. DeepMind blog, 14 November 2023.", "title": "GraphCast: AI model for faster and more accurate global weather forecasting", "url": "https://deepmind.google/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": "preprint", "citation": "Lam, R., Sanchez-Gonzalez, A., Willson, M., et al. (2023). GraphCast: Learning skillful medium-range global weather forecasting. arXiv:2212.12794 (published in Science, 2023).", "title": "GraphCast: Learning skillful medium-range global weather forecasting", "url": "https://arxiv.org/abs/2212.12794", "date": "2023-08-04", "written_by": "makers", "quote": "GraphCast significantly outperforms the most accurate operational deterministic systems on 90% of 1380 verification targets" }, { "kind": "news report", "citation": "MIT Technology Review (2023). Google DeepMind's weather AI can forecast extreme weather faster and more accurately. 14 November 2023.", "title": "Google DeepMind's weather AI can forecast extreme weather faster and more accurately", "url": "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": "It showed that these models are so good that we cannot avoid them anymore." }, { "kind": "press release", "citation": "Rabier, F. (2023). The AIFS is launched (editorial). ECMWF Newsletter No. 177, Autumn 2023; the page states 'Published in October 2023' and its metadata dates it 16 October 2023.", "title": "The AIFS is launched", "url": "https://www.ecmwf.int/en/newsletter/177/editorial/aifs-launched", "date": "2023-10-16", "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": "Charlton-Perez, A. J., Dacre, H. F., Driscoll, S., et al. (2024). Do AI models produce better weather forecasts than physics-based models? A quantitative evaluation case study of Storm Ciaran. arXiv:2312.02658 (University of Reading).", "title": "Do AI models produce better weather forecasts than physics-based models? A quantitative evaluation case study of Storm Ciaran", "url": "https://arxiv.org/abs/2312.02658", "date": "2024-02-19", "written_by": "independent", "quote": "accurately capture the synoptic-scale structure of the cyclone" }, { "kind": "report", "citation": "Cangialosi, J. P., Martinez, J., Reinhart, B., Papin, P. (2026). National Hurricane Center Forecast Verification Report: 2025 Hurricane Season. NOAA/NHC, 30 March 2026.", "title": "NHC Forecast Verification Report, 2025 Hurricane Season", "url": "https://www.nhc.noaa.gov/verification/pdfs/Verification_2025.pdf", "date": "2026-03-30", "written_by": "independent", "quote": null } ], "replication": { "produced_by": [ "AI models initialized from operational NWP analyses and run alongside physics-based models", "Verification using the NHC procedure, including early-model conversion and consensus experiments" ], "must_hold": [ "Track skill does not extend to intensity: the CIRA preprint reports a substantial low intensity bias", "Independent case evaluation (Storm Ciaran) found peak winds underestimated by all AI models tested" ], "echoes": [ { "date": "2023-11-02", "setting": "Storm Ciaran, northern Europe: AI models captured synoptic structure but underestimated peak winds (independent evaluation)", "model_version": "GraphCast, Pangu-Weather, FourCastNet, FourCastNet-v2", "outcome": "unknown", "source": "https://arxiv.org/abs/2312.02658" }, { "date": "2026-03-30", "setting": "NHC 2025 verification: a newer Google DeepMind ensemble (GDMI) outperformed official Atlantic track forecasts at 12–72 h", "model_version": null, "outcome": "recurred", "source": "https://www.nhc.noaa.gov/verification/pdfs/Verification_2025.pdf" } ] }, "paired_incident": { "database": "AI Incident Database", "identifier": "1546", "title": "Google Android Earthquake Alerts System Reportedly Underestimated Kahramanmaraş Earthquake and Failed to Send Urgent Warnings to Millions", "url": "https://incidentdatabase.ai/cite/1546", "severity": null, "group": "societal", "basis": "Google's AI-based earthquake alert system underestimated hazard magnitude; same developer family and hazard-prediction task as DeepMind's GraphCast cyclone forecasts, harming the exposed public." }, "headline": "GraphCast matches best operational cyclone track models in 2023", "metric": "adding all four improved the NHC track consensus by 11% at 120 h", "comparator": { "against": "the NHC track consensus without the four AI models, benchmarked against the long-term improvement of official forecasts", "before": "consensus track errors without the AIWP models; official five-day track forecasts improving by about 2% per year since 2001", "after": "consensus track errors reduced by up to 11% at the longer time periods", "basis": "measured", "quote": "The consensus track errors are reduced by up to 11% at the longer time periods. The five-day NHC official track forecasts have improved by about 2% per year since 2001, so this represents more than a five-year gain in accuracy.", "url": "https://arxiv.org/abs/2409.06735" }, "later": { "status": "scaled", "date": "2026-03-30", "note": "By the 2025 season NHC had brought AI-based models, including a newer Google DeepMind ensemble, into real-time operations, per its verification report.", "quote": "The 2025 season marked the first time that NHC incorporated AI-based models into real-time operations.", "url": "https://www.nhc.noaa.gov/verification/pdfs/Verification_2025.pdf" }, "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": "2026-10-20", "change": "Paired with AI Incident Database incident 1546 (medium confidence); severity not given by the source.", "source": "https://incidentdatabase.ai/cite/1546", "editor": "AIBD" }, { "date": "2026-10-20", "change": "Dated the ECMWF Newsletter editorial 16 October 2023 from the page metadata because the page gives only “October 2023”, replaced the account's “1 September is used” parenthetical, which contradicted the date observed, with the blog's own “In September” wording, and quoted the CIRA preprint's disclaimer on the journal it was submitted to, locating the quote on p. 23 of the PDF, in place of the misnamed journal.", "source": "https://www.ecmwf.int/en/newsletter/177/editorial/aifs-launched; https://deepmind.google/blog/graphcast-ai-model-for-faster-and-more-accurate-global-weather-forecasting/; https://arxiv.org/abs/2409.06735", "editor": "AIBD" }, { "date": "2026-10-21", "change": "Added what the benefit is measured against, what happened since from the cited sources.", "source": "https://arxiv.org/abs/2409.06735; https://www.nhc.noaa.gov/verification/pdfs/Verification_2025.pdf", "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: account, the replication conditions, the system's part rewritten in shorter sentences with abbreviations expanded; 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 report, one independent news report, two independent preprints, 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-0090", "catalog_version": "1.0.0", "source_fingerprint": "bb38f03334646e6b0f7f149482e370293906d58328dbd4d492e74f7d7631f631", "collection_refs": [ { "collection_id": "aibd", "version": "snapshot-8bf7cfec9cb185aa" }, { "collection_id": "aibd", "version": "2026-10-25" }, { "collection_id": "chanticleer", "version": "2026-10-25" } ], "source_ids": [ "AIBD-0090-source-0001", "AIBD-0090-source-0002", "AIBD-0090-source-0003", "AIBD-0090-source-0004", "AIBD-0090-source-0005", "AIBD-0090-source-0006", "AIBD-0090-source-0007" ], "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 live runs on public charts); CIRA/Colorado State University (evaluation)" } }, "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 CIRA preprint isolates the AI models' contribution via NHC verification and consensus experiments. The nine-day Hurricane Lee landfall forecast rests on vendor statements and press quotes of ECMWF staff. ECMWF documents read (Newsletters 177 and 178, science blog, Severe Event Catalog) do not record it." } } }, "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 CIRA preprint isolates the AI models' contribution via NHC verification and consensus experiments. The nine-day Hurricane Lee landfall forecast rests on vendor statements and press quotes of ECMWF staff. ECMWF documents read (Newsletters 177 and 178, science blog, Severe Event Catalog) do not record it." } } }, "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 report, one independent news report, two independent preprints, 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": "Skill evaluation, no verified discrete event." }, { "group": "organizational", "reason": "Skill evaluation, no verified discrete event." }, { "group": "societal", "reason": "Skill evaluation, no verified discrete event." } ] } }, "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": "Skill evaluation, no verified discrete event." }, { "group": "organizational", "reason": "Skill evaluation, no verified discrete event." }, { "group": "societal", "reason": "Skill evaluation, no verified discrete event." } ] } }, "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": "value_present", "value": { "kind": "structured", "data": { "answer": "Google's AI-based earthquake alert system underestimated hazard magnitude; same developer family and hazard-prediction task as DeepMind's GraphCast cyclone forecasts, harming the exposed public.", "links": [ { "database": "AI Incident Database", "identifier": "1546", "title": "Google Android Earthquake Alerts System Reportedly Underestimated Kahramanmaraş Earthquake and Failed to Send Urgent Warnings to Millions", "url": "https://incidentdatabase.ai/cite/1546", "group": "societal", "basis": "Google's AI-based earthquake alert system underestimated hazard magnitude; same developer family and hazard-prediction task as DeepMind's GraphCast cyclone forecasts, harming the exposed public.", "relation": "comparable_harm" } ] } }, "provenance": { "kind": "legacy_record", "basis": "Existing paired_incident classification; no new source review.", "record_fields": [ "paired_incident" ], "source_refs": [] }, "review_state": "record_mapped", "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": "adding all four improved the NHC track consensus by 11% at 120 h", "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": "value_present", "value": { "kind": "record_fields", "fields": { "paired_incident": { "database": "AI Incident Database", "identifier": "1546", "title": "Google Android Earthquake Alerts System Reportedly Underestimated Kahramanmaraş Earthquake and Failed to Send Urgent Warnings to Millions", "url": "https://incidentdatabase.ai/cite/1546", "group": "societal", "basis": "Google's AI-based earthquake alert system underestimated hazard magnitude; same developer family and hazard-prediction task as DeepMind's GraphCast cyclone forecasts, harming the exposed public." } } }, "provenance": { "kind": "legacy_record", "basis": "Preserved from the existing AIBD record; external sources were not rechecked.", "record_fields": [ "paired_incident" ], "source_refs": [] }, "review_state": "record_mapped", "coverage": "partial" }, "follow_up[]": { "state": "value_present", "value": { "kind": "record_fields", "fields": { "later": { "status": "scaled", "date": "2026-03-30", "note": "By the 2025 season NHC had brought AI-based models, including a newer Google DeepMind ensemble, into real-time operations, per its verification report.", "quote": "The 2025 season marked the first time that NHC incorporated AI-based models into real-time operations.", "url": "https://www.nhc.noaa.gov/verification/pdfs/Verification_2025.pdf" } } }, "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-0090" } }, "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" } }, "provenance": { "kind": "legacy_record", "basis": "Preserved from the existing AIBD record; external sources were not rechecked.", "record_fields": [ "benefit_type" ], "source_refs": [] }, "review_state": "record_mapped", "coverage": "partial" }, "outcomes[].claim": { "state": "value_present", "value": { "kind": "record_fields", "fields": { "account": "Google DeepMind's GraphCast was run live on ECMWF's public charts from 2023. DeepMind's blog of 14 November 2023 says the live model predicted Hurricane Lee's landfall in Nova Scotia in September 2023 about nine days in advance. The blog says only “In September”, so the year is implied by its 14 November 2023 post date. The ECMWF publications read do not document the case. MIT Technology Review quoted ECMWF's Peter Dueben saying the models are so good they cannot be avoided. An independent CIRA/Colorado State evaluation applied NHC verification to May-November 2023 cyclones. It found GraphCast-operational and three other AI models' track errors comparable to the best operational models. Adding all four improved the NHC track consensus by 11% at 120 h.", "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": "Skill evaluation, no verified discrete event." }, { "group": "organizational", "reason": "Skill evaluation, no verified discrete event." }, { "group": "societal", "reason": "Skill evaluation, no verified discrete event." } ] } }, "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": "Medium-range global weather forecasting by machine learning, including severe-event prediction such as tropical cyclone tracks." } }, "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": { "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": [ "developer_country", "deployer_country" ], "source_refs": [] }, "review_state": "record_mapped", "coverage": "partial" }, "purpose": { "state": "value_present", "value": { "kind": "record_fields", "fields": { "purpose": "Medium-range global weather forecasting by machine learning, including severe-event prediction such as tropical cyclone tracks." } }, "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": "2024-09-08", "revisions": [ { "date": "2026-10-20", "change": "Record drafted from the cited sources.", "editor": "AIBD" }, { "date": "2026-10-20", "change": "Paired with AI Incident Database incident 1546 (medium confidence); severity not given by the source.", "source": "https://incidentdatabase.ai/cite/1546", "editor": "AIBD" }, { "date": "2026-10-20", "change": "Dated the ECMWF Newsletter editorial 16 October 2023 from the page metadata because the page gives only “October 2023”, replaced the account's “1 September is used” parenthetical, which contradicted the date observed, with the blog's own “In September” wording, and quoted the CIRA preprint's disclaimer on the journal it was submitted to, locating the quote on p. 23 of the PDF, in place of the misnamed journal.", "source": "https://www.ecmwf.int/en/newsletter/177/editorial/aifs-launched; https://deepmind.google/blog/graphcast-ai-model-for-faster-and-more-accurate-global-weather-forecasting/; https://arxiv.org/abs/2409.06735", "editor": "AIBD" }, { "date": "2026-10-21", "change": "Added what the benefit is measured against, what happened since from the cited sources.", "source": "https://arxiv.org/abs/2409.06735; https://www.nhc.noaa.gov/verification/pdfs/Verification_2025.pdf", "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: account, the replication conditions, the system's part rewritten in shorter sentences with abbreviations expanded; 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": [ "AI models initialized from operational NWP analyses and run alongside physics-based models", "Verification using the NHC procedure, including early-model conversion and consensus experiments" ], "must_hold": [ "Track skill does not extend to intensity: the CIRA preprint reports a substantial low intensity bias", "Independent case evaluation (Storm Ciaran) found peak winds underestimated by all AI models tested" ], "echoes": [ { "date": "2023-11-02", "setting": "Storm Ciaran, northern Europe: AI models captured synoptic structure but underestimated peak winds (independent evaluation)", "model_version": "GraphCast, Pangu-Weather, FourCastNet, FourCastNet-v2", "outcome": "unknown", "source": "https://arxiv.org/abs/2312.02658" }, { "date": "2026-03-30", "setting": "NHC 2025 verification: a newer Google DeepMind ensemble (GDMI) outperformed official Atlantic track forecasts at 12–72 h", "outcome": "recurred", "source": "https://www.nhc.noaa.gov/verification/pdfs/Verification_2025.pdf" } ] } } }, "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": [ "AI models initialized from operational NWP analyses and run alongside physics-based models", "Verification using the NHC procedure, including early-model conversion and consensus experiments" ], "must_hold": [ "Track skill does not extend to intensity: the CIRA preprint reports a substantial low intensity bias", "Independent case evaluation (Storm Ciaran) found peak winds underestimated by all AI models tested" ], "echoes": [ { "date": "2023-11-02", "setting": "Storm Ciaran, northern Europe: AI models captured synoptic structure but underestimated peak winds (independent evaluation)", "model_version": "GraphCast, Pangu-Weather, FourCastNet, FourCastNet-v2", "outcome": "unknown", "source": "https://arxiv.org/abs/2312.02658" }, { "date": "2026-03-30", "setting": "NHC 2025 verification: a newer Google DeepMind ensemble (GDMI) outperformed official Atlantic track forecasts at 12–72 h", "outcome": "recurred", "source": "https://www.nhc.noaa.gov/verification/pdfs/Verification_2025.pdf" } ] } } }, "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": "2026-10-20", "change": "Paired with AI Incident Database incident 1546 (medium confidence); severity not given by the source.", "source": "https://incidentdatabase.ai/cite/1546", "editor": "AIBD" }, { "date": "2026-10-20", "change": "Dated the ECMWF Newsletter editorial 16 October 2023 from the page metadata because the page gives only “October 2023”, replaced the account's “1 September is used” parenthetical, which contradicted the date observed, with the blog's own “In September” wording, and quoted the CIRA preprint's disclaimer on the journal it was submitted to, locating the quote on p. 23 of the PDF, in place of the misnamed journal.", "source": "https://www.ecmwf.int/en/newsletter/177/editorial/aifs-launched; https://deepmind.google/blog/graphcast-ai-model-for-faster-and-more-accurate-global-weather-forecasting/; https://arxiv.org/abs/2409.06735", "editor": "AIBD" }, { "date": "2026-10-21", "change": "Added what the benefit is measured against, what happened since from the cited sources.", "source": "https://arxiv.org/abs/2409.06735; https://www.nhc.noaa.gov/verification/pdfs/Verification_2025.pdf", "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: account, the replication conditions, the system's part rewritten in shorter sentences with abbreviations expanded; 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": "Meteorological research and operational forecast centers" } }, "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": "preprint", "citation": "DeMaria, M., Franklin, J. L., Chirokova, G., Radford, J., DeMaria, R., Musgrave, K. D., Ebert-Uphoff, I. (2024). Evaluation of Tropical Cyclone Track and Intensity Forecasts from Artificial Intelligence Weather Prediction (AIWP) Models. arXiv:2409.06735, submitted 8 Sep 2024; the preprint's disclaimer reads 'This work has been submitted to the Artificial Intelligence in the Earth Sciences American Meteorological Society journal'. The quote is on p. 23 of the full PDF, not on the abstract page.", "title": "Evaluation of Tropical Cyclone Track and Intensity Forecasts from AIWP Models", "url": "https://arxiv.org/abs/2409.06735", "date": "2024-09-08", "written_by": "independent", "quote": "When all four were added the track consensus improved by 11% at 120 h, with improvements that were statistically significant at 72-120 h." }, { "kind": "press release", "citation": "Google DeepMind (2023). GraphCast: AI model for faster and more accurate global weather forecasting. DeepMind blog, 14 November 2023.", "title": "GraphCast: AI model for faster and more accurate global weather forecasting", "url": "https://deepmind.google/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": "preprint", "citation": "Lam, R., Sanchez-Gonzalez, A., Willson, M., et al. (2023). GraphCast: Learning skillful medium-range global weather forecasting. arXiv:2212.12794 (published in Science, 2023).", "title": "GraphCast: Learning skillful medium-range global weather forecasting", "url": "https://arxiv.org/abs/2212.12794", "date": "2023-08-04", "written_by": "makers", "quote": "GraphCast significantly outperforms the most accurate operational deterministic systems on 90% of 1380 verification targets" }, { "kind": "news report", "citation": "MIT Technology Review (2023). Google DeepMind's weather AI can forecast extreme weather faster and more accurately. 14 November 2023.", "title": "Google DeepMind's weather AI can forecast extreme weather faster and more accurately", "url": "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": "It showed that these models are so good that we cannot avoid them anymore." }, { "kind": "press release", "citation": "Rabier, F. (2023). The AIFS is launched (editorial). ECMWF Newsletter No. 177, Autumn 2023; the page states 'Published in October 2023' and its metadata dates it 16 October 2023.", "title": "The AIFS is launched", "url": "https://www.ecmwf.int/en/newsletter/177/editorial/aifs-launched", "date": "2023-10-16", "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": "Charlton-Perez, A. J., Dacre, H. F., Driscoll, S., et al. (2024). Do AI models produce better weather forecasts than physics-based models? A quantitative evaluation case study of Storm Ciaran. arXiv:2312.02658 (University of Reading).", "title": "Do AI models produce better weather forecasts than physics-based models? A quantitative evaluation case study of Storm Ciaran", "url": "https://arxiv.org/abs/2312.02658", "date": "2024-02-19", "written_by": "independent", "quote": "accurately capture the synoptic-scale structure of the cyclone" }, { "kind": "report", "citation": "Cangialosi, J. P., Martinez, J., Reinhart, B., Papin, P. (2026). National Hurricane Center Forecast Verification Report: 2025 Hurricane Season. NOAA/NHC, 30 March 2026.", "title": "NHC Forecast Verification Report, 2025 Hurricane Season", "url": "https://www.nhc.noaa.gov/verification/pdfs/Verification_2025.pdf", "date": "2026-03-30", "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-0090-source-0001", "AIBD-0090-source-0002", "AIBD-0090-source-0003", "AIBD-0090-source-0004", "AIBD-0090-source-0005", "AIBD-0090-source-0006", "AIBD-0090-source-0007" ], "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": "preprint", "citation": "DeMaria, M., Franklin, J. L., Chirokova, G., Radford, J., DeMaria, R., Musgrave, K. D., Ebert-Uphoff, I. (2024). Evaluation of Tropical Cyclone Track and Intensity Forecasts from Artificial Intelligence Weather Prediction (AIWP) Models. arXiv:2409.06735, submitted 8 Sep 2024; the preprint's disclaimer reads 'This work has been submitted to the Artificial Intelligence in the Earth Sciences American Meteorological Society journal'. The quote is on p. 23 of the full PDF, not on the abstract page.", "title": "Evaluation of Tropical Cyclone Track and Intensity Forecasts from AIWP Models", "url": "https://arxiv.org/abs/2409.06735", "date": "2024-09-08", "written_by": "independent", "quote": "When all four were added the track consensus improved by 11% at 120 h, with improvements that were statistically significant at 72-120 h." }, { "kind": "press release", "citation": "Google DeepMind (2023). GraphCast: AI model for faster and more accurate global weather forecasting. DeepMind blog, 14 November 2023.", "title": "GraphCast: AI model for faster and more accurate global weather forecasting", "url": "https://deepmind.google/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": "preprint", "citation": "Lam, R., Sanchez-Gonzalez, A., Willson, M., et al. (2023). GraphCast: Learning skillful medium-range global weather forecasting. arXiv:2212.12794 (published in Science, 2023).", "title": "GraphCast: Learning skillful medium-range global weather forecasting", "url": "https://arxiv.org/abs/2212.12794", "date": "2023-08-04", "written_by": "makers", "quote": "GraphCast significantly outperforms the most accurate operational deterministic systems on 90% of 1380 verification targets" }, { "kind": "news report", "citation": "MIT Technology Review (2023). Google DeepMind's weather AI can forecast extreme weather faster and more accurately. 14 November 2023.", "title": "Google DeepMind's weather AI can forecast extreme weather faster and more accurately", "url": "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": "It showed that these models are so good that we cannot avoid them anymore." }, { "kind": "press release", "citation": "Rabier, F. (2023). The AIFS is launched (editorial). ECMWF Newsletter No. 177, Autumn 2023; the page states 'Published in October 2023' and its metadata dates it 16 October 2023.", "title": "The AIFS is launched", "url": "https://www.ecmwf.int/en/newsletter/177/editorial/aifs-launched", "date": "2023-10-16", "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": "Charlton-Perez, A. J., Dacre, H. F., Driscoll, S., et al. (2024). Do AI models produce better weather forecasts than physics-based models? A quantitative evaluation case study of Storm Ciaran. arXiv:2312.02658 (University of Reading).", "title": "Do AI models produce better weather forecasts than physics-based models? A quantitative evaluation case study of Storm Ciaran", "url": "https://arxiv.org/abs/2312.02658", "date": "2024-02-19", "written_by": "independent", "quote": "accurately capture the synoptic-scale structure of the cyclone" }, { "kind": "report", "citation": "Cangialosi, J. P., Martinez, J., Reinhart, B., Papin, P. (2026). National Hurricane Center Forecast Verification Report: 2025 Hurricane Season. NOAA/NHC, 30 March 2026.", "title": "NHC Forecast Verification Report, 2025 Hurricane Season", "url": "https://www.nhc.noaa.gov/verification/pdfs/Verification_2025.pdf", "date": "2026-03-30", "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": "CIRA/Colorado State evaluation: GraphCast and three AI models match top operational cyclone track models in 2023; adding all four cut consensus error 11% at 120 h.", "account": "Google DeepMind's GraphCast was run live on ECMWF's public charts from 2023. DeepMind's blog of 14 November 2023 says the live model predicted Hurricane Lee's landfall in Nova Scotia in September 2023 about nine days in advance. The blog says only “In September”, so the year is implied by its 14 November 2023 post date. The ECMWF publications read do not document the case. MIT Technology Review quoted ECMWF's Peter Dueben saying the models are so good they cannot be avoided. An independent CIRA/Colorado State evaluation applied NHC verification to May-November 2023 cyclones. It found GraphCast-operational and three other AI models' track errors comparable to the best operational models. Adding all four improved the NHC track consensus by 11% at 120 h." } }, "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." }, "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": "The event concerned GraphCast’s live experimental forecasts on ECMWF charts in 2023. The CIRA evaluation used GraphCast-operational." }, "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 experimental run on ECMWF charts (2023); GraphCast-operational in the CIRA evaluation" } }, "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 (graph neural network global weather model)" } }, "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": "Independent 2023-season verification finds GraphCast and three peer AI models match the best operational cyclone track models", "headline": "GraphCast matches best operational cyclone track models in 2023" } }, "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": [ "bb38f03334646e6b0f7f149482e370293906d58328dbd4d492e74f7d7631f631" ], "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 GraphCast was run live on ECMWF's public charts from 2023. DeepMind's blog of 14 November 2023 says the live model predicted Hurricane Lee's landfall in Nova Scotia in September 2023 about nine days in advance. The blog says only “In September”, so the year is implied by its 14 November 2023 post date. The ECMWF publications read do not document the case. MIT Technology Review quoted ECMWF's Peter Dueben saying the models are so good they cannot be avoided. An independent CIRA/Colorado State evaluation applied NHC verification to May-November 2023 cyclones. It found GraphCast-operational and three other AI models' track errors comparable to the best operational models. Adding all four improved the NHC track consensus by 11% at 120 h.", "replication": { "produced_by": [ "AI models initialized from operational NWP analyses and run alongside physics-based models", "Verification using the NHC procedure, including early-model conversion and consensus experiments" ], "must_hold": [ "Track skill does not extend to intensity: the CIRA preprint reports a substantial low intensity bias", "Independent case evaluation (Storm Ciaran) found peak winds underestimated by all AI models tested" ], "echoes": [ { "date": "2023-11-02", "setting": "Storm Ciaran, northern Europe: AI models captured synoptic structure but underestimated peak winds (independent evaluation)", "model_version": "GraphCast, Pangu-Weather, FourCastNet, FourCastNet-v2", "outcome": "unknown", "source": "https://arxiv.org/abs/2312.02658" }, { "date": "2026-03-30", "setting": "NHC 2025 verification: a newer Google DeepMind ensemble (GDMI) outperformed official Atlantic track forecasts at 12–72 h", "outcome": "recurred", "source": "https://www.nhc.noaa.gov/verification/pdfs/Verification_2025.pdf" } ] } } }, "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": 34, "reviewed": 0, "record_mapped": 34, "not_assessed": 57, "complete": false, "by_state": { "value_present": 34, "not_reported": 0, "unresolved": 0, "not_assessed": 57, "not_applicable": 0, "withheld": 0, "source_unavailable": 0 } } } }