google-deepmind / google-deepmind/weathernext
Different loss values for seemingly same forecast
Open
- Dominant language
- Python
- Stars
- 7.7k
- Forks
- 986
- PR merge metrics
- No merged PRs in 30d
Description
I performed "1 Eval Step" forecast with Graphcast small using dataset_source-era5_date-2022-01-01_res-1.0_levels-13_steps-01.nc, steps-12.nc, and steps-40.nc.
The loss is different for each case even though we are only performing a 6 hr forecast in each case. Why might this be? As I understand it, the prediction should be the same in all these cases and the target should also be the same (ERA5 Reanalysis 6hr into the future).
Loss Values:
0.9296875 for 6hr forecast 1-step data 01 Jan 2022
0.69140625 for 6hr forecast 12-step data 01 Jan 2022
0.66015625 for 6hr forecast 40-step data 01 Jan 2022
Contributor guide
Assessment
This issue has not been assessed yet.