microsoft / microsoft/aurora

Unrealistic fluttering of geopotential

Open
#111 3 comments 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

Hello. Thank you for this great work!

I tried Aurora prediction with ERA5/pretrained and HRES T0/finetuned following example on docs, and I got some unrealistic result on geopotential predictions. Geopotential on low latitutdes are fluttering unnaturally as shown in the figure.

In both setting I tried use_lora=False but got same result.

Is this just a model' tendency or should I suspect errors in my configuration or input file?

Image

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 reproducing the documented Aurora prediction example with the ERA5/pretrained and HRES T0/finetuned configurations, keeping use_lora=False and comparing the geopotential output at low latitudes. Check the supplied configuration and input file against the example; done means establishing whether the fluttering is reproducible and attributable to the model or to the setup.

Written by the indexing model from the issue text.

Assessment

Tech stack
python
Domain
machine-learning
Issue type
Bug
Difficulty
4/5
Estimated time
3-5 days
Activity status
Stale
Clarity
Needs clarification
Newbie friendliness
25/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.