Google has launched the WeatherNext 2 forecasting model, which uses artificial intelligence to improve weather predictions. This model is accessible to developers and researchers and shows enhancements in 99.9% of variables compared to its predecessor, WeatherNext. WeatherNext 2 generates forecasts eight times faster than before, with a resolution time of up to one hour, producing four six-hour forecasts daily and extending lead times for predictions up to 15 days. It utilizes a Tensor Processing Unit (TPU) to make predictions in under a minute, contrasting with traditional supercomputers that take hours. The model is based on a Functional Generative Network (FGN), replacing the previous Graph Neural Network (GNN) and Conditional Diffusion model. WeatherNext 2 is available through platforms like Earth Engine, BigQuery, and Vertex AI, and enhances services such as Google Search, Gemini, the Pixel Weather app, and the Weather API within Google Maps.