microsoft / microsoft/aurora

Using 1° resolution instead of 0.25°

Open
#184 1 comment 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

Dominant language
Python
Stars
1k
Forks
174
PR merge metrics
No merged PRs in 30d

Description

Hi Aurora team,

My lab has access to 1° ERA5 data, but Aurora requires 0.25° in its primary model. Would it be possible to pass this 1° data straight to Aurora, or must we use torch.nn.functional.interpolate(...)?
We are fine-tuning for MJO prediction, so 1° resolution is sufficient for us to calculate RMM indices.

Many thanks for your work!
Kieran

Contributor guide

Open the contributing guide

First steps

  1. Read the whole issue, then the project's contributing guide.
  2. Comment on the issue to say you are picking it up — it saves two people doing the same work.
  3. Fork the repository and make your change on a branch.
  4. Open a pull request that references the issue number.

Research direction

Start by tracing Aurora's primary model input resolution and the torch.nn.functional.interpolate(...) path mentioned in the issue. Determine whether 1° ERA5 data can be passed directly while preserving the stated MJO/RMM use case; done should be a documented, tested decision about direct support or required preprocessing.

Written by the indexing model from the issue text.

Assessment

Tech stack
python, pytorch
Domain
machine-learning
Issue type
Feature
Difficulty
4/5
Estimated time
3-5 days
Activity status
Quiet
Clarity
Needs clarification
Newbie friendliness
35/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.