microsoft
Aurora Atmospheric/Weather Forecasting Models
Adding the Aurora Atmospheric/Weather Forecasting models from https://github.com/microsoft/aurora!
See their docs and paper for more info!
cc: @wesselb @crisbodnar @megstanley
Last I knew, Aurora only supports medium-range weather forecasting (2 hrs–2 wks), not climate modeling (decadal scale). Would be good to confirm with the authors. We need to be very careful with naming here, as there is a huge distinction between data-driven stateful models and physics-driven statistical distribution models.
Last I knew, Aurora only supports medium-range weather forecasting (2 hrs–2 wks), not climate modeling (decadal scale). Would be good to confirm with the authors. We need to be very careful with naming here, as there is a huge distinction between data-driven stateful models and physics-driven statistical distribution models.
You're correct, the paper specifically says "forecasting of weather and atmospheric processes". I'll make sure to not use the term "climate modeling".
@adamjstewart, @isaaccorley, you're correct that Aurora only does medium-term forecasting (up to 10 days in 6 hour steps). Note, however, that it doesn't just do weather forecasting: we have models for ocean waves and air pollution too.
Looks good to me. For
load_checkpoint, can we override to use commit hash / have our own version of it in this file?
Planning to upstream this fix directly to the aurora repo https://github.com/microsoft/aurora/issues/114
Can you rebase this? Should be much simpler now that [models] was added in a different PR.
Failing minimum tests due to https://github.com/huggingface/safetensors/issues/641, for now maybe we can pin to older safetensors.
Can we support older aurora? The aurora 1.6.0 version pins to a specific version of timm<1.0 which conflicts with our min version of timm being >1.0
@isaaccorley I'll let you take over again. Now that the tests are actually running, there are a bunch of new errors.