euroargodev / euroargodev/BlueCloud

Temporal representation of classes

Open
#4 1 comment 0 reactions 0 assignees View on GitHub
Dominant language
Jupyter Notebook
Stars
0
Forks
1
PR merge metrics
No merged PRs in 30d

Description

I added some new graphical representations to show a seasional distribution of classes.
I used as exemple the mediterranean argo dataset from 2012 to 2013. Here is the spatial distribution of classes, posteriors and profiles:

![ArgoMed_map_labels_EX](https://user-images.githubusercontent.com/59824937/87799669-ce748080-c84d-11ea-8d65-c1a82fb5a933.png)
![ArgoMed_posteriors_EX](https://user-images.githubusercontent.com/59824937/87799691-d3393480-c84d-11ea-8ef7-158526d1d28c.png)
med_pcm_2012-2013_profiles

Classes k=5 and k=1 correspond to Atlantic and Black see so they are not taken in to account. We find 2 classes in the western basin (k =2 and k=7) , one class in the central basin (k = 3) and one class in the eastern basin (k = 6). Classes k = 4 and k =0 are both in central and eastern basins.

Bar plots showing number of profiles per class grouped by month and by season are:

![ArgoMed_months_hist_EX](https://user-images.githubusercontent.com/59824937/87800542-d1bc3c00-c84e-11ea-8757-f66040a599c0.png)
![ArgoMed_seasons_hist_rel_EX](https://user-images.githubusercontent.com/59824937/87800548-d41e9600-c84e-11ea-9a57-31c2a1d3a880.png)

We can distinguish a seasonal behavior. For exemple: k = 0 shows a maximun in december and k= 4 shows a maximun in June. But regarding the profiles of these 2 classes I am not sure that they correspond to winter (k=0) and summer (k=4) profiles. What do you thing about it?

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.