Google DeepMind and Google Research have introduced WeatherNext 3, which the company describes as its most advanced and accurate global weather model so far.
Independent live evaluations by Brightband also rank it as the most accurate global weather model currently available.
Unlike previous AI weather systems that relied mainly on delayed numerical weather prediction data, WeatherNext 3 can learn directly from real-time observations, including satellite and weather station data.
The model produces a new global forecast every hour and can provide predictions at resolutions as detailed as 5 kilometers.
Higher-Resolution and More Frequent Forecasts
WeatherNext 3 generates hourly forecasts across several spatial resolutions while maintaining consistency between large-scale weather patterns and local conditions.
Key surface variables such as temperature and moisture can be forecast at 5km resolution, while other surface variables use 10km resolution.
Atmospheric variables such as wind speed are forecast at 25km resolution.
Google says this provides a global weather picture roughly five times sharper than WeatherNext 2, which produced forecasts on a 25km grid every six hours.
The system uses a Functional Generative Network mesh transformer that combines hourly geostationary satellite mosaics with traditional historical analysis.
It can produce dense weather fields, cyclone tracks, and forecasts for specific weather station locations.
Uses Live Satellite and Weather Station Data
One of the biggest changes in WeatherNext 3 is the data used to generate forecasts.
Most AI weather models, including WeatherNext 2, train on information produced by numerical weather prediction models. These physics-based systems rely on supercomputers and can carry a data delay of around six hours.
Google says this delay can create problems when forecasting quickly changing conditions such as rain and surface temperatures.
WeatherNext 3 instead uses a continuously updated mosaic of global geostationary satellite observations.
This allows it to generate a new forecast every hour using the latest available satellite data.
Google says the shorter update cycle can provide earlier and more detailed information when storms, fronts or precipitation systems develop quickly.
The model also trains directly on sparse weather station observations, allowing it to better capture local differences caused by geography, including coastlines, valleys and mountain ranges.
Google says this could be particularly useful in parts of Latin America, Africa and Asia-Pacific, where high-resolution regional forecasting has traditionally been limited by the high computing costs of conventional models.
Major Improvement in Rain and Snow Forecasting
Google has also focused on improving precipitation forecasting, an area where both traditional and AI-based global weather models have struggled.
WeatherNext 3 trains on NASA’s Integrated Multi-satellite Retrievals for GPM, or IMERG, alongside Google’s own global precipitation reanalysis based on satellite radar data.
According to Google’s evaluations, the model delivered a Continuous Ranked Probability Score improvement of up to 60% against IMERG in medium-range global forecasts.
It also improved by up to 30% against MRMS and 10% against rain gauge measurements at early forecast lead times.
WeatherNext 3 can also reproduce sharper boundaries around precipitation systems instead of producing the more blurred estimates seen in previous models.
Built for Renewable Energy Forecasting
WeatherNext 3 introduces weather predictions designed specifically for renewable energy production.
The model can forecast wind speeds at a height of 100 meters, roughly matching the height of many wind turbines.
It also provides high-resolution cloud cover and solar radiation forecasts to help solar farms estimate how much sunlight will reach the ground.
Google says this information can help grid operators and renewable energy developers estimate future power generation and better match supply with consumer demand.
Where WeatherNext 3 Is Available
Google is making WeatherNext 3 data available to researchers, developers and businesses without requiring them to set up the model themselves.
Users can access the global forecasts through BigQuery and Earth Engine, or download the data in bulk through Google Cloud Storage.
WeatherNext 3 is also beginning to power weather experiences across Google Search, the Gemini app, Google Maps, Google Maps Platform Weather API, and Google Earth Engine starting today.
Google says the model particularly improves longer-term forecasts.
For forecasts made a day or more in advance, users could see precipitation predictions that are up to 50% more accurate, with the largest improvements expected in regions where weather forecasting has historically been less reliable.
Google notes that weather remains inherently unpredictable and advises users to rely on local meteorological agencies or national weather services for official forecasts, severe weather warnings, and public safety information.
The post Google WeatherNext 3 Makes Forecasts Five Times Sharper appeared first on ProPakistani.