microsoft / microsoft/aurora

Indexing bug in Air pollution model

Open
#98 1 comment 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

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

Description

Hi,
First of all, thank you for your amazing work on Aurora and for releasing the Air pollution model !

I noticed that you simulate an indexing bug between atmospheric and static 'z' in the implementation of this Air pollution model.
Was this bug also present during your finetuning of the model, or does it only concern the inference that produced the results presented in your paper?
If the bug was indeed present during finetuning, would it be relevant to set simulate_indexing_bug to False during further finetuning to try and fix it?

Thank you ! 😀

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 at the Air pollution model implementation and search for the simulate_indexing_bug flag. Compare how the atmospheric and static z indexing is used during finetuning and inference, then establish whether the reported bug affects both workflows and what configuration represents the intended behavior.

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.