feat(training): downscaling #811
Open
Conversation
This file contains hidden or 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
for more information, see https://pre-commit.ci
…m/ecmwf/anemoi-core into feature/multi-dataset-integration
for more information, see https://pre-commit.ci
…m/ecmwf/anemoi-core into feature/multi-dataset-integration
for more information, see https://pre-commit.ci
for more information, see https://pre-commit.ci
for more information, see https://pre-commit.ci
…m/ecmwf/anemoi-core into feature/multi-dataset-integration
for more information, see https://pre-commit.ci
…m/ecmwf/anemoi-core into feature/multi-dataset-integration
for more information, see https://pre-commit.ci
for more information, see https://pre-commit.ci
…m/ecmwf/anemoi-core into feature/multi-dataset-integration
for more information, see https://pre-commit.ci
…m/ecmwf/anemoi-core into feature/multi-dataset-integration
for more information, see https://pre-commit.ci
MeraX
reviewed
Jan 21, 2026
Contributor
MeraX
left a comment
MeraX
left a comment
There was a problem hiding this comment.
Hi Mario, thanks for bringing this in! I was just thinking about the name of this feature/task. I was wondering if "downscaling" is the most generic term to describe what it actually provides.
If I'm not mistaken, I belief, the new task could basically be used for anything that predicts Y(t) from X(t) and former X if using multi step input. X and Y could be different datasets and grids, but they could also be the same. I.e. this new task also supports various possibilities of statistical post processing and generation of derived products. I wouldn't call all of these "downscaling". But to be honest, I have no good name in mind. Maybe something in the direction of "diagnosing task"?
Co-authored-by: Marek Jacob <[email protected]>
MeraX
reviewed
Jan 21, 2026
mchantry
reviewed
Jan 21, 2026
JPXKQX
commented
Jan 22, 2026
…-core into multids/downscaling
for more information, see https://pre-commit.ci
MeraX
reviewed
Jan 26, 2026
Co-authored-by: Marek Jacob <[email protected]>
for more information, see https://pre-commit.ci
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.
Description
This PR adds support for downscaling in anemoi. After multiple datasets, the downscaling task can be added to the supported use cases.
Thanks to @MeraX @TobiasGoeckeDWD, who co-developed this branch during their visit to Reading in October 2025.
As a contributor to the Anemoi framework, please ensure that your changes include unit tests, updates to any affected dependencies and documentation, and have been tested in a parallel setting (i.e., with multiple GPUs). As a reviewer, you are also responsible for verifying these aspects and requesting changes if they are not adequately addressed. For guidelines about those please refer to https://anemoi.readthedocs.io/en/latest/
By opening this pull request, I affirm that all authors agree to the Contributor License Agreement.