Aurora

Aurora is a cutting-edge AI foundation model developed by a team of Microsoft researchers that can extract valuable insights from vast amounts of atmospheric data. This 1.3 billion parameter model excels at a wide range of prediction tasks, even in data-sparse regions or extreme weather scenarios. It is trained in two phases: a pre-training phase that learns general-purpose representations of weather and climate from a vast and diverse set of data, and a fine-tuning phase that adapts it to specific tasks like 10-day global weather forecasting or 5-day air pollution prediction, producing high-resolution global forecasts much faster than traditional numerical weather models while matching or exceeding their accuracy. Aurora 1.5, developed by Microsoft Weather as an extension of the original model by Microsoft Research AI for Science, adds 22 new forecast variables (including cloud cover, precipitation and radiation), hourly resolution, and probabilistic ensemble forecasting for uncertainty quantification; its ensemble forecasts outperform the ECMWF ensemble on 88.9% of evaluated targets (days 1-10) and cut tropical-cyclone track error by 16% versus the original Aurora. Aurora 1.5 is available on GitHub and Microsoft Foundry.