Skip to content
This repository has been archived by the owner on Sep 7, 2023. It is now read-only.

Stop giving the ML model satellite images of the _future_! #89

Open
JackKelly opened this issue Oct 7, 2021 · 2 comments
Open

Stop giving the ML model satellite images of the _future_! #89

JackKelly opened this issue Oct 7, 2021 · 2 comments
Labels
data Data processing, loading, or analysis machine learning model

Comments

@JackKelly
Copy link
Member

To test things, we showed the ML model satellite images of the future (i.e we showed the ML model satellite images after t0). We should probably stop doing that now that the code is working pretty well :)
@JackKelly JackKelly added data Data processing, loading, or analysis machine learning model labels Oct 7, 2021
@peterdudfield
Copy link
Contributor

I had run an experiment for this

https://github.com/openclimatefix/predict_pv_yield/blob/issue/85-perciever-nwp/experiments/2021-10/2021-10-01/experiment.txt

Error went from 3% to 3.6%, bare in mind baseline is 5%, as a a rough idea

@JackKelly
Copy link
Member Author

Awesome - thanks loads for running this experiment! Sounds like good news to me!

@flowirtz flowirtz moved this to Todo in Nowcasting Oct 15, 2021
Sign up for free to subscribe to this conversation on GitHub. Already have an account? Sign in.
Assignees
No one assigned
Labels
data Data processing, loading, or analysis machine learning model
Projects
No open projects
Nowcasting
Status: Todo
Milestone
No milestone
Development

No branches or pull requests
2 participants
@JackKelly @peterdudfield