Open jacobbieker opened 3 months ago
https://www.microsoft.com/en-us/research/blog/introducing-aurora-the-first-large-scale-foundation-model-of-the-atmosphere/
They used 3D Swin transformer to encode data, trained on era5, gfs, cmip6, and more. They then used 3D perceiver transformer for the processing and decoding, as well as LoRA in the fine tuning stages for longer rollout.
One of the few ones not trained just on ERA5.
Code has now been open sourced: https://github.com/microsoft/aurora
Arxiv/Blog/Paper Link
https://www.microsoft.com/en-us/research/blog/introducing-aurora-the-first-large-scale-foundation-model-of-the-atmosphere/
Detailed Description
They used 3D Swin transformer to encode data, trained on era5, gfs, cmip6, and more. They then used 3D perceiver transformer for the processing and decoding, as well as LoRA in the fine tuning stages for longer rollout.
One of the few ones not trained just on ERA5.
Context