Google launches WeatherNext 3 – AI forecasts weather directly from satellite data
Google and DeepMind have launched WeatherNext 3, an AI model that abandons physics-based simulations to learn weather patterns directly from satellite data. The model is already live in Search, Maps, and Gemini.

What happened?
Google Research and DeepMind have announced WeatherNext 3, a new AI model for weather forecasting. The model discards traditional physics-based simulations in favour of training directly on real-time satellite data. It delivers hourly forecasts on a five-kilometre resolution grid, which is five times sharper than the previous version, providing higher precision for local weather phenomena.
Key facts
| Lanseringsdatum | 6 september 2024 |
|---|---|
| Upplösning | 5 km rutnät (5x skarpare) |
| Förbättring nederbörd | Upp till 50 % mer exakt |
| Integrationer | Google Search, Maps, Gemini |
Why it matters
By training directly on satellite data, WeatherNext 3 can generate faster and more accurate forecasts. The model delivers up to 50 percent more precise precipitation predictions and tailored data for the renewable energy sector. These features have already been rolled out directly into Google Search, Google Maps, and the AI assistant Gemini.
Who is affected?
The launch impacts end-users seeking weather information within the Google ecosystem, as well as stakeholders in renewable energy who rely on precise local forecasts. The model covers global regions and is integrated into tools for both consumers and decision-makers.
Impact on the EU
The model is available globally via Google's consumer services. No specific information regarding restrictions or particular adaptations for the EU market was provided in conjunction with the launch.
What else you should know
Traditional meteorological models are built on complex physical equations of the atmosphere, which require immense computational resources. By training AI models directly on observations, WeatherNext 3 represents a shift in weather forecasting where data-driven models challenge classical supercomputer simulations.
Quick answers about this story
Vad har hänt?
När hände det?
Varför spelar det roll?
Hur påverkas energisektorn?
The link opens in a new window and leads to the publisher's own site.
Källan har spårats automatiskt från utgivaren via Aheadlines signalkedja.
AI-verktyg i artikeln
Topics
Get similar news straight to your inbox
The reader's room
Send in a question or an addition. The newsroom reads everything before it's published and replies when relevant. No AI-generated text – just people.
Sign in to submit a comment or question.
Read the article through your role
- Decide whether this affects strategy over 6–12 months or is just noise.
- Discuss with leadership: do we own the right question or does ownership need to move?
- Ask: what risk are we taking by NOT acting on this this quarter?
Generated angle — not editorial analysis of "Google launches WeatherNext 3 – AI forecasts weather directl"