• Home
  • Technology
  • Gaming
  • Entertainment
  • World & Business
  • Science
  • Sports
  • AI
HomeTechnologyGamingEntertainmentWorld & BusinessScienceSportsAI
    • HomeTechnologyGamingEntertainmentWorld & BusinessScienceSportsAI
    • Home
    • Technology
    • Gaming
    • Entertainment
    • World & Business
    • Science
    • Sports
    • AI
    AI

    Google DeepMind Releases WeatherNext 3

    Raia Hadsell voices pride in the Google DeepMind team's new weather model.

    RH
    DA
    ST
    3 Sources, 25d ago, first seen 25d ago

    TLDR

    Raia Hadsell posted that she is proud of the launch by her research team at Google DeepMind. She said the model proves frontier AI can represent the complexity of Earth's atmosphere and that the work helps the planet and benefits humanity. A separate retweet from researcher Shubhendu Trivedi quoted Tom Andersson stating that the team released WeatherNext 3 and called it the best global weather model available.

    Combined views

    13.5K

    3 Sources, first seen 25d ago

    Combined views

    13.5K

    3 Sources, first seen 25d ago

    117 likes
    117 likes
    10 comments
    66 saves
    253 reposts

    Sentiment

    Positive——Negative

    Summary

    Not enough discussion yet.

    No sentiment analysis available yet.

    10 comments
    66 saves
    253 reposts

    Sentiment

    Positive——Negative

    Summary

    Not enough discussion yet.

    No sentiment analysis available yet.

    Today's Rank

    —

    Not ranked yet

    Today's Rank

    —

    Not ranked yet

    3 Sources

    @_onionesqueRT @tom_r_andersson: Our team just released WeatherNext 3, the best global weather model currently available (benchmark: https://t.co/xvzOm…
    @RaiaHadsellI'm incredibly proud of this launch! Our research team is absolutely killing it - proving without a doubt that frontier AI can accurately model the complexity of the earth's atmosphere and showing what GDM is doing to help our planet and benefit humanity.
    @dair_aiBanger paper from Google DeepMind. Every AI weather model so far has been trained and initialized on analysis data, which is itself the output of another model. That means the forecast inherits whatever biases the analysis carries, and it cannot use a new satellite observation directly. WeatherNext 3 changes what the model is trained on. It ingests low-latency geostationary satellite data and refreshes its forecast every hour instead of every six. Resolution now matches the best physics-based global models at 0.1 degree with hourly steps, including solar radiation and cloud cover. It also learns targets that live in observation space rather than analysis space. Satellite-derived precipitation, tropical cyclone tracks, and station observations are all predicted directly. Because it models sparse station data conditioned on local geography, it gives 2m temperature and dewpoint at any location and time, with substantially lower error than competing global models. The result is a new state of the art for probabilistic medium-range forecast skill. Why does it matter? The convenient training label in many domains is itself a model output, and inheriting its bias is the price. Moving supervision to raw observations is the general lesson here, and weather is where it can be measured cleanly. Paper: https://arxiv.org/abs/2609.03582 Chat with Paper: https://academy.dair.ai/papers/weathernext-3-increasing-resolution-and-performance-of-global-weather-models-wit-2609.03582

    3 Sources

    @_onionesqueRT @tom_r_andersson: Our team just released WeatherNext 3, the best global weather model currently available (benchmark: https://t.co/xvzOm…
    @RaiaHadsellI'm incredibly proud of this launch! Our research team is absolutely killing it - proving without a doubt that frontier AI can accurately model the complexity of the earth's atmosphere and showing what GDM is doing to help our planet and benefit humanity.
    @dair_aiBanger paper from Google DeepMind. Every AI weather model so far has been trained and initialized on analysis data, which is itself the output of another model. That means the forecast inherits whatever biases the analysis carries, and it cannot use a new satellite observation directly. WeatherNext 3 changes what the model is trained on. It ingests low-latency geostationary satellite data and refreshes its forecast every hour instead of every six. Resolution now matches the best physics-based global models at 0.1 degree with hourly steps, including solar radiation and cloud cover. It also learns targets that live in observation space rather than analysis space. Satellite-derived precipitation, tropical cyclone tracks, and station observations are all predicted directly. Because it models sparse station data conditioned on local geography, it gives 2m temperature and dewpoint at any location and time, with substantially lower error than competing global models. The result is a new state of the art for probabilistic medium-range forecast skill. Why does it matter? The convenient training label in many domains is itself a model output, and inheriting its bias is the price. Moving supervision to raw observations is the general lesson here, and weather is where it can be measured cleanly. Paper: https://arxiv.org/abs/2609.03582 Chat with Paper: https://academy.dair.ai/papers/weathernext-3-increasing-resolution-and-performance-of-global-weather-models-wit-2609.03582