MetOffice / MetOffice/CSET

Ingestion of data from ML models.

Open
#1,546 2 comments 0 reactions 1 assignee Claimed by @cehalliwell View on GitHub
enhancement super
Dominant language
Python
Stars
33
Forks
19
Avg merge
1d 22h
Merged PRs (30d)
30

Description

### What problem does your feature request solve?

We need to be able to read in data produced by Machine Learning (ML) models and perform any necessary processing of the data to be able to produce standard CSET plots of the data.

### Describe the solution you'd like

The model should be considered as another "Model XX" in CSET, where the data source is the output from the ML model. Some processing of the ML data may be required to get it into the correct format (e.g. field names might be different to the CSET list and a new operator may be required). Once the ML data has been processed, the CSET functionality can be used on the data in the same way as physical models.

### Describe alternatives you've considered
This cannot be done with the existing functionality.

Links
#1975 [Handling BRIS regional ML data]
#1973 [Issue loading Pangu ML data - Dimension Ordering/Callback]

Contributor guide

No contributing guide indexed for this repository

Assessment

This issue has not been assessed yet.

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.