Google's WeatherNext 3 AI Weather Model Uses Live Satellite Data for Hourly High-Resolution Forecasts
12 Sources
[1]
Google's AI weather model now uses more raw satellite data
Google is one of the major players in AI (meaning machine learning) weather forecast model space. The models it and others generate have their strengths and weaknesses, but the main advantage is that they can have forecast performance similar to traditional models while requiring far less computing
[2]
Google's latest AI weather model gives you no excuse to forget your umbrella
Scientists at Google Deepmind and Google Research released a new artificial intelligence model for weather forecasting today that sees our changing atmosphere more clearly and predicts its behavior more often. WeatherNext 3 is the latest wave of a sea change in meteorology brought out by deep
[3]
Google says its AI weather model is getting better
Google is rolling out an updated AI weather model that's supposed to be more accurate, especially when it comes to predicting rain and snowfall. In the announcement today, the company says it's now able to make forecasts with "unprecedented resolution" using its new WeatherNext 3 AI model. It can
[4]
Google's new AI weather model uses live satellite data for higher-resolution forecasts - Engadget
Google DeepMind has released the WeatherNext 3, an updated version of its last AI-powered weather model that it claims offers even more detailed forecasts across key variables like temperature, moisture and wind speed. DeepMind notes the new model should be particularly useful to companies working
[5]
Google DeepMind Just Rolled Out Its Most Accurate AI Global Weather Model
In the year 2026, predicting hyper-local weather is still tricky, even though it impacts everything from supply chains and sporting events to tourism and energy production. Now, Google says its latest AI model is getting a lot better at it. Google DeepMind and Google Research rolled out
[6]
Google weather forecasts are getting more local and more accurate
Google says that precipitation forecasts made a day or more in advance can be up to 50% more accurate. Weather forecasting can be bang on the money, or infuriatingly inaccurate. Most of us have probably looked out the window at falling rain while our weather app confidently suggests we won't get
[7]
Google's WeatherNext 3 AI model in Search, Gemini has '50% more accurate precipitation forecasts'
Google today announced WeatherNext 3 as its "most advanced and accurate global weather AI model," with immediate benefits for Search and Gemini. Other AI weather models (including WeatherNext 2) are "trained on data from numerical weather prediction (NWP) models." Although useful, NWP models are
[8]
Weatherwatch: AI model beats standard methods at predicting cyclones
Artificial intelligence system delivers a three-day forecast as accurate as previous two-day predictions Google's WeatherNext AI model is better than existing systems at forecasting cyclones, according to a paper published in Nature. The AI-based technology gives an extra day of warning,
[9]
Introducing WeatherNext 3, our most advanced and accurate global weather AI model
Figure 2: Comparison of 2-meter temperature forecasts over the UK. WeatherNext 2 (left) at 25-kilometer (0.25°) resolution vs. WeatherNext 3 (right) at a native 5-kilometer (0.05°) resolution. WeatherNext 3 resolves the intricate local topography, preventing the pixelated, over-smoothed thermal
[10]
Google's Weather Forecasting Model Just Got a Massive Upgrade
Google detailed its latest AI-powered weather forecasting model this morning, announcing that it's already rolling out to a handful of Google services that will utilize it the most. Called WeatherNext 3, users will find its forecasting inside of Google Search, Gemini, Maps, the broader Google Maps
[11]
Google DeepMind unveils WeatherNext 3 with sharper AI forecasts
Google DeepMind has released WeatherNext 3, an updated AI weather model that uses live satellite data to deliver higher-resolution forecasts for temperature, moisture and wind speed. The new model produces hourly forecasts on a 5-kilometer square grid, compared with the 25-kilometer square grid
[12]
Google launches WeatherNext 3 AI model By Investing.com
Investing.com - Alphabet Inc. (NASDAQ:GOOGL) announced today the launch of WeatherNext 3, its most advanced global weather forecasting AI model, which integrates real-time satellite data and provides hourly forecast updates at higher resolution than its predecessor. The new model generates
Share
Copy Link
Google DeepMind and Google Research unveiled WeatherNext 3, their most advanced AI weather model that incorporates live satellite data to generate hourly forecasts at up to 5-kilometer resolution. The model delivers up to 50% more accurate precipitation predictions and now powers weather experiences across Google Search, Gemini, and Google Maps.
Google Launches WeatherNext 3 with Live Satellite Data Integration
Google DeepMind and Google Research released WeatherNext 3, marking a significant advancement in AI-based weather forecasting model technology
1
2
. The new AI weather model represents a departure from traditional approaches by incorporating live satellite data directly into its predictions, enabling hourly forecasts instead of the standard six-hour intervals used by most weather models3
. This integration allows WeatherNext 3 to capture real-time atmospheric observations, significantly reducing the lag time between current weather conditions and forecast generation that has plagued earlier AI weather models1
.The model has already claimed the top position on Operational WeatherBench, an independent leaderboard run by AI weather forecasting startup Brightband that compares leading AI and traditional weather models
2
5
. WeatherNext 3 outperforms competing models from Microsoft, Nvidia, and the European Centre for Medium-Range Weather Forecasts, while also beating traditional forecasts from the US National Weather Service and ECMWF2
.High-Resolution Forecasts Transform Weather Prediction Accuracy
WeatherNext 3 delivers high-resolution forecasts at up to 5-kilometer resolution for key surface variables including surface temperature, moisture, and dewpoint—five times sharper than the 25-kilometer resolution of WeatherNext 2
3
4
. Wind speed predictions are generated at 25-kilometer resolution, with specialized forecasts for 100-meter wind speeds at roughly turbine height to support renewable energy generation planning4
5
.The model features 2.4 times more parameters than its predecessor, enabling it to process more complex atmospheric patterns
2
. According to Google Research engineer Samier Merchant, the team achieved roughly 5% improvement in upper atmosphere condition accuracy over WeatherNext 2, equating to approximately six more hours of accurate forecast lead time1
. The model's ability to predict conditions for specific weather station data locations improved accuracy by up to 30% by incorporating elevation and land-ocean classification1
.Precipitation Predictions Show Dramatic Improvement
Precipitation predictions represent one of WeatherNext 3's most substantial advances, with up to 50% more accurate forecasts when looking a day or more ahead
3
5
. Google DeepMind reports 60% improvement over WeatherNext 2 in rain evaluations2
. The model achieves this through a separate machine-learning component trained specifically on satellite-based precipitation estimates, providing multiple precipitation forecasts to represent the range of possible outcomes1
.Using satellite data to make predictions fills critical gaps in locations where ground-based rain gauges are sparse—primarily outside the US and Europe—where Google says WeatherNext 3 can provide the biggest improvements
3
. This capability matters significantly for regions across Latin America, Africa, and Asia-Pacific, where high-resolution forecasting has historically been limited by the enormous cost of supercomputers needed to run traditional numerical weather prediction models5
.Breaking Free from Reanalysis Dependency
Most AI weather models have relied entirely on reanalyses—global atmospheric snapshots produced by blending various weather data sources into consistent pictures generated every six hours
1
. WeatherNext 3 challenges this limitation by incorporating raw observational data alongside traditional weather analysis, though it still depends on national weather datasets for complete forecasts2
.Google claims WeatherNext 3 is the first AI model to directly incorporate raw observations for high-resolution global forecasts, though AI weather startup WindBorne notes its WeatherMesh 6 model has been incorporating raw observations from weather balloons since late 2025
2
. According to DeepMind research scientist Ferran Alet, "Machine learning targets the problem we are really solving, which is approximate noisy physics from incomplete information and finite compute, and so it learns patterns from a lot of data"2
.Related Stories
Renewable Energy Applications Drive Strategic Focus
WeatherNext 3 includes specialized forecasts designed specifically for renewable energy generation, predicting wind speeds at 100 meters above ground—roughly the height of a wind turbine—alongside high-resolution cloud cover and solar radiation levels to help solar farms estimate electricity generation
4
5
. This capability addresses Google's own growing energy demands for data centers powering generative AI tools. "As the energy needs of Google, but [also] entire humanity, is increasing its energy needs, to make sure that we make renewable a very appealing opportunity is very important for us," Alet told The Verge3
.The speed and low cost of AI weather models promise economic impact for regions where expensive high-quality sensors and supercomputers have put accurate forecasts out of reach
2
. Bill Gates recently cited AI-powered weather forecasting as a transformative technology2
, while European and US weather agencies are already incorporating AI models into their forecast products.Integration Across Google Ecosystem and Research Community
WeatherNext 3 now powers weather experiences across Google Search, Gemini, Google Maps, the Google Maps Platform Weather API, and Google Earth Engine
4
5
. According to Merchant, "This is going to be the first time that some of the core variables feed and power a lot of the Google products"2
. Users can experiment with the model through the Google Weather Lab, while the original WeatherNext model became open-source in August 20264
.Google has collaborated with the US National Hurricane Center and agencies across Asia to improve weather forecasting using its AI models
3
. Despite improvements, AI weather models are expected to work alongside traditional physics-based simulations rather than replace them entirely. WeatherNext 3 remains trained on data from physics-based models, and meteorology agencies typically examine multiple predictions before issuing warnings3
. Google still directs users to local meteorological agencies or national weather services for official forecasts, severe weather warnings, and public safety advisories5
.The white paper reveals some persistent challenges, including hexagonal patterns visible in precipitation maps reflecting the model's grid structure, and inconsistencies in global average temperature across ensemble forecasts
1
. Watch for continued refinement in direct data assimilation capabilities as Google and competitors push toward fully independent AI weather models that rely less on traditional numerical weather prediction outputs.References
Summarized by
Navi
[1]
[3]
[4]
Related Stories
Google's AI-Powered Weather Model Revolutionizes Forecasting Accuracy
23 Jul 2024
Google DeepMind's GenCast AI Model Revolutionizes Weather Forecasting Accuracy
05 Dec 2024•Technology
DeepMind's AI weather model gives forecasters an extra day to prepare for deadly tropical cyclones
06 Aug 2026•Science and Research
Recent Highlights
1
AI Hallucination Nearly Sparked US Military Confrontation With Chinese Ship in Middle East
Technology
2
OpenAI AI Agent Hacks Australian Government Healthcare Website in First-of-Its-Kind Breach
Technology
3
AI leaders warn UN Security Council of existential risks to humanity, call for global safeguards
Policy and Regulation
Recent Highlights
Today's Top Stories
Don’t drown in AI news. We cut through the noise - filtering, ranking and summarizing the most important AI news, breakthroughs and research daily. Follow topics that matter to you and stay ahead.
