{"rewrite":{"id":"r_e20436055985e0f00cca5978","clusterId":"c_10d442bb071fce5ac20128af","slug":"google-s-weathernext-3-uses-satellite-data-to-update-forecasts-hourly","model":"deepseek-v4-flash","headline":"Google's WeatherNext 3 Uses Satellite Data to Update Forecasts Hourly","summary":"Google DeepMind and Google Research announced WeatherNext 3, an AI weather model that ingests real-time geostationary satellite observations directly instead of learning from numerical model data. This removes the roughly six-hour delay in supercomputer-based data, letting it generate new forecasts hourly. Spatial resolution improves up to about five times over WeatherNext 2, down to 5km intervals for surface temperature and humidity. It is already rolling into Google Search, Gemini, and Google Maps.","whyItMatters":"By feeding on live satellite observations rather than delayed numerical model output, WeatherNext 3 shortens the gap between observation and forecast to one hour and sharpens resolution to 5km.","webCardHtml":"\u003cp\u003ePrecipitation has been a weak point for global models because rain forms in narrow bands that shift quickly. WeatherNext 3 trains on NASA satellite precipitation data and renders the shape and extent of rain clouds in finer detail than WeatherNext 2, which the article illustrates with side-by-side comparisons against satellite observation.\u003c/p\u003e\u003cp\u003eThe model is already live in Google Search, the Gemini app, and Google Maps, and forecast data is available to researchers through BigQuery, Google Earth Engine, and Google Cloud Storage. An experimental map viewer called Weather Lab exists, though it returned a not-available message when accessed from Japan at the time of writing.\u003c/p\u003e","blueskyPost":"Google's WeatherNext 3 skips the supercomputer wait. It ingests geostationary satellite observations directly, updates forecasts hourly, and sharpens resolution to 5km, about five times finer than WeatherNext 2. Already rolling into Search, Gemini, and Maps.","twitterPost":"Google's WeatherNext 3 feeds on live satellite data instead of delayed supercomputer output, cutting forecast updates to one hour and resolution to 5km. It is already in Search, Gemini, and Maps.","threadsPost":null,"newsletterBlurb":"Google DeepMind and Google Research unveiled WeatherNext 3, an AI weather model that reads geostationary satellite observations directly, bypassing the roughly six-hour lag of numerical model data. Forecasts update hourly and surface resolution drops to 5km, about five times finer than WeatherNext 2. The model is already reaching Google Search, Gemini, and Google Maps.","attributionJson":"[{\"source\":\"GIGAZINE\",\"url\":\"https://gigazine.net/news/20260904-google-weathernext-3/\",\"title\":\"GoogleがAI気象モデル「WeatherNext 3」発表、衛星データを直接使ってスパコンの待ち時間を回避し1時間ごとに予報更新\"}]","lintFlagsJson":null,"lintHits":0,"costUsd":0,"inputTokens":5381,"outputTokens":2733,"status":"published","repairAttempts":0,"nextRepairAt":null,"factsAttemptedAt":null,"createdAt":"2026-09-04T10:03:06.000Z","publishedAt":"2026-09-04T10:04:07.000Z","updatedAt":"2026-09-04T10:04:07.000Z"},"cluster":{"id":"c_10d442bb071fce5ac20128af","canonicalTitle":"GoogleがAI気象モデル「WeatherNext 3」発表、衛星データを直接使ってスパコンの待ち時間を回避し1時間ごとに予報更新","representativeArticleId":"a_7fc32d091abd8c99323f76c5","sourceCount":1,"writtenSourceCount":1,"writeAttempts":0,"isSolo":true,"entitiesJson":"{\"anime_titles\":[],\"manga_titles\":[],\"work_titles\":[],\"studios\":[],\"people\":[],\"type\":\"news\",\"domain\":\"other\",\"is_roundup\":false}","contentType":"news","status":"published","firstSeenAt":"2026-09-04T09:00:00.000Z","lastSeenAt":"2026-09-04T09:00:00.000Z","updatedAt":"2026-09-04T10:04:04.000Z"},"attribution":[{"source":"GIGAZINE","url":"https://gigazine.net/news/20260904-google-weathernext-3/","title":"GoogleがAI気象モデル「WeatherNext 3」発表、衛星データを直接使ってスパコンの待ち時間を回避し1時間ごとに予報更新"}],"entities":{"anime_titles":[],"manga_titles":[],"work_titles":[],"studios":[],"people":[],"type":"news","domain":"other","is_roundup":false},"keyFacts":null}