Google DeepMind and Google Research have introduced WeatherNext 3, an artificial intelligence model designed for global weather forecasting. This new model aims to provide more accurate and higher-resolution predictions, particularly for rain and snowfall, by learning from real-time weather observations.
WeatherNext 3 represents an advancement in meteorology, utilizing deep learning techniques to analyze and predict atmospheric behavior. It is set to be integrated into various Google products, including Google Search, Google Maps, and Gemini, and will also be available on Google's cloud platforms for users and researchers.
According to Google, WeatherNext 3 offers "unprecedented resolution," producing a global picture that is five times sharper than Google's previous models. The model's ability to leverage fresher and richer observational datasets, including raw satellite data, contributes to its enhanced accuracy.
Independent evaluations by Brightband on Operational WeatherBench, a utility for comparing AI forecasts, have shown WeatherNext 3 to be the most accurate among leading contenders. It outperformed other deep-learning models from Google, Microsoft, Nvidia, and the European Center for Medium-Range Weather Forecasting, as well as traditional forecasts from the US National Weather Service and the ECMWF.
A key development in WeatherNext 3 is its capability to go beyond the data typically used by most global AI models. The model learns directly from real-time observations, enabling it to provide timely and more localized predictions. This approach addresses previous challenges in incorporating real-time weather data from sources like satellites and improving spatial resolution.
Traditional weather forecasting has historically relied on supercomputers simulating atmospheric physics through complex equations. WeatherNext 3's AI-driven approach, using historical records and real-time data, offers a different method for making faster and more accurate predictions.
The integration of WeatherNext 3 into core Google products signifies a shift in how weather information will be presented to users. Samier Merchant, a Google senior staff engineer, noted that this marks the first time some of the core variables from such a model will power many Google products.
Beyond consumer applications, the advancements in localized and timely weather information from WeatherNext 3 can have broader implications. Accurate predictions for wind, rain, and extreme weather events are crucial for sectors such as agriculture, global supply chains, clean energy production, and national economies.
✨ This summary was generated by AI from the outlets' reporting listed below. It is not independently verified and may contain errors — check the original sources. How BrevFeed works →
One email each morning: the day's tech stories, clustered across outlets and summarized. No account needed.
One email a day. Unsubscribe in one click, any time.
Spend a few minutes, get the whole day. Every topic's top stories in one hands-free rundown — listen, watch, or read the transcript.
▶ Play today's briefNew every morning, and the back catalogue is archived by date.
Google DeepMind and Google Research have introduced WeatherNext 3, an AI model for global weather forecasting that provides hourly predictions at higher resolutions than previous models. This development matters because it offers more localized and timely weather information, which can impact various sectors like agriculture, supply chains, and energy production.
Google DeepMind and Google Research have released WeatherNext 3, a new AI model for weather forecasting that will be integrated into Google Search, Maps, and Gemini. This model has demonstrated higher accuracy than other leading AI and traditional forecasting systems, offering improved resolution and rain prediction capabilities.
Google released WeatherNext 3, an updated AI weather model that uses real-time satellite observations to provide more accurate and higher-resolution forecasts, particularly for rain and snowfall. This advancement allows for hourly predictions with improved spatial resolution, addressing gaps in areas with fewer ground-based sensors.