docs(models): Docathon #202
Merged
Conversation
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
|
I think we agreed on the following names:
|
paulaharder
reviewed
Mar 19, 2025
paulaharder
reviewed
Mar 19, 2025
paulaharder
reviewed
Mar 19, 2025
paulaharder
reviewed
Mar 19, 2025
paulaharder
reviewed
Mar 19, 2025
|
I tested all the steps and overall it looks great to me : ) I left some minor comments. Let me know if I should just apply some of the changes myself |
for more information, see https://pre-commit.ci
Thank you! I've tried to include your comments. |
HCookie
reviewed
Mar 21, 2025
HCookie
reviewed
Mar 21, 2025
HCookie
reviewed
Mar 21, 2025
|
@b8raoult Can you update the logo here? |
Co-authored-by: Harrison Cook <[email protected]>
# Adds temporal interpolation functionality to anemoi A forecaster with longer time steps might yield better predictions going days out than a 1 hour forecaster, as it has to make fewer auto-regressive steps. To produce the hourly predictions still, we can use the information available from a longer time-stepping forecaster, e.g. hours 12 and 18 as input to predict hours 13-17. These predictions can be made individually, assisted by some information about the target time as input. Preliminary results indicate that this approach works well when combining a 6 hour forecaster and hourly interpolator during inference. Additionally, when hourly analysis is not available, there does not seem to be a major loss in training the interpolator as an emulator on nwp model runs, as long as it is combined with a forecasting model trained on analysis during inference. --------------------------------------------------------------------------------------------------- Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com> Co-authored-by: Harrison Cook <[email protected]>
JPXKQX
approved these changes
Mar 25, 2025
This was referenced Mar 25, 2025
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Update anemoi-models documentation.
What I've done:
ToDo:
anemoi.models.preprocessing.imputerRemark:
Please feel free to change whatever you want. I'm not attached to any of my changes :)
📚 Documentation preview 📚: https://anemoi-training--202.org.readthedocs.build/en/202/
📚 Documentation preview 📚: https://anemoi-graphs--202.org.readthedocs.build/en/202/
📚 Documentation preview 📚: https://anemoi-models--202.org.readthedocs.build/en/202/