GenCast
A diffusion-model-based AI weather forecasting model developed by Google DeepMind. Its probabilistic generative approach natively supports ensemble forecasting, enabling the model to capture uncertainty inherent in weather predictions.
Timeline (last 90 days)
Pangu-Weather employs a 3D Transformer with Earth-specific positional encoding; GraphCast converts the Earth's grid into a graph structure to model long-range atmospheric teleconnections; GenCast supports ensemble forecasting through probabilistic generation.
All Facts (3)
GenCast的精度超越欧洲中期天气预报中心（ECMWF）的传统数值模型
85%UnverifiedGenCast, released by DeepMind in 2024, is a weather forecasting system driven by a diffusion model that can generate global ensemble weather forecasts for the next 15 days within 1 minute.
70%UnverifiedPangu-Weather employs a 3D Transformer with Earth-specific positional encoding; GraphCast converts the Earth's grid into a graph structure to model long-range atmospheric teleconnections; GenCast supports ensemble forecasting through probabilistic generation.
50%