Indexing bug in Air pollution model

[leonardledy]

Hi,
First of all, thank you for your amazing work on Aurora and for releasing the Air pollution model !

I noticed that you simulate an indexing bug between atmospheric and static 'z' in the implementation of this Air pollution model.
Was this bug also present during your finetuning of the model, or does it only concern the inference that produced the results presented in your paper?
If the bug was indeed present during finetuning, would it be relevant to set simulate_indexing_bug to False during further finetuning to try and fix it?

Thank you ! 😀

[wesselb]

Hey @leonardledy! Thanks for the kind words. :)

Yes, this bug unfortunately was present when the model was fine-tuned.

If the bug was indeed present during finetuning, would it be relevant to set simulate_indexing_bug to False during further finetuning to try and fix it?

Definitely! You might be able to squeeze a little more performance out of the model.