-
Notifications
You must be signed in to change notification settings - Fork 3
Commit
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
Add 2d variance metrics to reservoir training (#2361)
This adds scalar metrics for the mean vertically-summed grid-scale variance of outputs in the x, y plane. Since the prognostic run reservoir predictions have issues with too much grid-scale noise in column-integrated quantities, I would like to see how the hyperparameters affect this in offline evaluation. I don't have area or pressure thicknesses saved in the data, so this is a very rough way of estimated the variance in column-integrated quantities. During synchronization of the reservoir the `_rc_out` precipitable water field has a higher variance than the `_hyb_in` field, which suggests that this should be visible in offline evaluation. ![image](https://github.com/ai2cm/fv3net/assets/16710132/a896a961-4324-4a51-a693-fec05b0e880a)
- Loading branch information
Showing
2 changed files
with
58 additions
and
5 deletions.
There are no files selected for viewing
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters