{"data":{"event":{"id":"9efa9414-4ad0-4bff-9d6a-fade19fe7860","slug":"weathernext-operational-google-forecasts","title":"Google deploys WeatherNext 2 forecasts in Search, Maps, and Earth Engine","short_summary":"On 17 November 2025 Google DeepMind and Google Research launched WeatherNext 2, an ensemble weather model they reported as faster and more accurate than the prior WeatherNext system, and began using it in Search, Gemini, Pixel Weather, Maps Platform, Earth Engine, and BigQuery.","full_description":"WeatherNext 2 is the productized successor to DeepMind and Google Research ML weather models. The company said the new model generates many scenarios much faster than the previous WeatherNext version and upgraded consumer and enterprise weather surfaces. Forecast skill claims are developer-reported. This event records operational productization rather than the earlier GraphCast and GenCast papers.","ledger_type":"benefit","primary_domain_id":"99fd8a40-a540-41d3-af98-57c1709ee422","event_status":"verified","event_date":"2025-11-17T00:00:00.000Z","discovery_date":"2025-11-17T00:00:00.000Z","first_published_date":"2025-11-17T00:00:00.000Z","last_reviewed_date":"2025-11-17T00:00:00.000Z","geographic_scope":"Global Google weather users","affected_population":"Users of Google Search, Maps, and Pixel Weather in supported regions","base_impact_tier":2,"base_score":"3.00","attribution_multiplier":"0.7000","evidence_multiplier":"0.3000","realization_multiplier":"0.8500","durability_multiplier":"0.5000","current_event_score":"0.241000","confidence_level":"high","score_explanation":"Consumer-scale deployment of MLWP is notable (tier 2), scored separately from the GraphCast/GenCast papers. Attribution to the WeatherNext/GraphCast family. Developer evidence. High realization. Medium durability.","methodology_version_id":"d7881163-fb23-4e71-8625-bac1a8662c0f","original_methodology_version_id":"d7881163-fb23-4e71-8625-bac1a8662c0f","published_at":"2025-11-17T00:00:00.000Z","created_at":"2026-09-13T20:47:20.075Z","updated_at":"2026-09-13T20:47:20.075Z","flags":[],"domain_name":"Climate & Environment","domain_slug":"climate-environment","methodology_version":"0.1"},"contributions":[{"id":"30d73667-2275-47b6-aa69-82d5760c45ea","event_id":"9efa9414-4ad0-4bff-9d6a-fade19fe7860","model_id":"0792cf0a-d86c-4f0c-b9a5-b43cfe6a0117","role_description":"Operational ML weather models serving Google products and Earth Engine.","attribution_multiplier":"0.7000","credit_share":"0.9000","contribution_score":"0.241000","attribution_rationale":"Productized GraphCast/GenCast-class models; ECMWF and ERA5 data remain upstream.","attribution_confidence":"medium","first_used_date":"2025-11-17T00:00:00.000Z","model_version_if_known":null,"review_status":"approved","created_at":"2026-09-13T20:47:20.075Z","model_slug":"weathernext-2","model_name":"WeatherNext 2","identity_class":"named_release","is_internal":false,"family_name":"GraphCast","family_slug":"google-deepmind-graphcast","organization_name":"Google DeepMind","organization_slug":"google-deepmind"}],"sources":[{"id":"21403a0d-be43-43f8-98c1-87cc05fcec1e","event_id":"9efa9414-4ad0-4bff-9d6a-fade19fe7860","url":"https://blog.google/innovation-and-ai/models-and-research/google-deepmind/weathernext-2/","canonical_url":"https://blog.google/innovation-and-ai/models-and-research/google-deepmind/weathernext-2/","source_type":"developer_announcement","publisher":"Google","author":null,"publication_date":"2025-11-17T00:00:00.000Z","retrieved_at":"2026-09-13T20:47:20.075Z","title":"WeatherNext 2: Google DeepMind’s most advanced forecasting model","excerpt":null,"content_hash":null,"source_reliability_class":"low","is_primary_source":true,"is_independent":false,"is_peer_reviewed":false,"archived_url":null,"created_at":"2026-09-13T20:47:20.075Z"},{"id":"0401cf63-7f18-4e92-bc55-b4ff705803c8","event_id":"9efa9414-4ad0-4bff-9d6a-fade19fe7860","url":"https://deepmind.google/science/weathernext/","canonical_url":"https://deepmind.google/science/weathernext/","source_type":"developer_announcement","publisher":"Google DeepMind","author":null,"publication_date":"2025-11-17T00:00:00.000Z","retrieved_at":"2026-09-13T20:47:20.075Z","title":"WeatherNext 2","excerpt":null,"content_hash":null,"source_reliability_class":"low","is_primary_source":true,"is_independent":false,"is_peer_reviewed":false,"archived_url":null,"created_at":"2026-09-13T20:47:20.075Z"}],"claims":[{"id":"50c8db9a-a91d-4afc-8122-aa415f932886","event_id":"9efa9414-4ad0-4bff-9d6a-fade19fe7860","claim_text":"WeatherNext 2 forecast data was made available in Earth Engine and BigQuery and used to upgrade Google weather products.","claim_type":"outcome","claim_status":"supported","confidence_score":null,"created_at":"2026-09-13T20:47:20.075Z","updated_at":"2026-09-13T20:47:20.075Z"}],"revisions":[{"id":"1ed3d045-dd42-489e-8f95-99cff860cee3","event_id":"9efa9414-4ad0-4bff-9d6a-fade19fe7860","model_id":null,"previous_score":"0.000000","new_score":"0.241000","previous_factors":{},"new_factors":{"evidence":0.3,"base_score":3,"durability":0.5,"attribution":0.7,"realization":0.85},"change_reason":"Initial adjudicated seed score under methodology 0.1.","trigger_type":"seed","trigger_source_ids":null,"reviewer_id":null,"review_status":"published","created_at":"2026-09-13T20:47:20.075Z"}],"secondary":[{"name":"Engineering","slug":"engineering"}]},"methodology_version":"0.1"}