Tag
Google DeepMind announces WeatherNext 3, an AI model that updates hourly to predict weather conditions for wind and solar farms, enhancing energy generation forecasts.
Google's AI weather model WeatherNext 3 has been updated to use more raw satellite data and incorporate physical information, improving forecast accuracy by up to 30% for surface temperature, and is now the source for forecasts in Google services.
GenONet is a novel deep learning architecture that uses Deep Operator Networks within a Generative Adversarial Network framework for high-resolution precipitation nowcasting, producing sharp and physically consistent forecasts.
This paper introduces Tianmu-TC, a physics-constrained generative AI framework for global tropical cyclone forecasting that outperforms traditional systems in reliability and computational efficiency.
WindBorne Systems, which uses AI-powered weather forecasting with long-flying balloons, raised a $37M Series B round co-led by Khosla Ventures and Galvanize to expand commercial applications and grow its customer base beyond government agencies.
Google Cloud named primary HPC provider for NOAA's Weather and Climate Operational Supercomputing System, enabling operational numerical weather prediction in the public cloud for faster simulations and life-saving warnings.
AirCast-SR is a diffusion-based foundation model that downscales global AI weather forecasts from 0.25° to 1 km resolution at hourly cadence, producing 67-hour forecasts with near-zero bias and structural realism, while running inference in minutes on a single commodity GPU.
Google DeepMind and Google Research launched Weather Lab, an interactive platform featuring experimental AI-based tropical cyclone prediction models that can forecast cyclone formation, track, intensity, and shape up to 15 days ahead. The models are being validated in partnership with the U.S. National Hurricane Center to improve forecast accuracy and support real-time warnings.
At the I/O 2026 keynote, Google announced the latest AI achievements including Gemini 3.5, Omni, Code Mender, Gemini for Science, WeatherNext, and emphasized that AGI is imminent, and demonstrated AI applications in cybersecurity, scientific simulation, and health.