How diffs_stddev_by_level.nc is computed? about graphcast HOT 2 CLOSED

Hi @omshinde, thanks for your message.

This is what we mention in he paper here:

The statistics are approximated by sampling a short 2-step sequence from the dataset (the two steps $X^t$ and $X^{t+1}$, separated by 6h), and computing the difference between the two steps. Then you do this for many two step trajectories (ideally the whole dataset, but in our case we did it only for 8192 sequences), and compute the standard deviation of those differences across all of the trajectories, and all of the latitude and longitude points of those trajectories.

from graphcast.

Thank you so much @alvarosg ..Also. apologies for overlooking this from the paper. I am closing this issue as I don't have any further questions as of now.

from graphcast.