Skip to content

95 watervapor lsm util func - #96

Merged
rogerkuou merged 8 commits into
73_water_vapor_notebookfrom
95_watervapor_lsm_util_func
Sep 14, 2026
Merged

rogerkuou merged 8 commits into
73_water_vapor_notebookfrom
95_watervapor_lsm_util_func

Conversation

@rogerkuou

Copy link
Copy Markdown
Collaborator

fix #95
this improved PR #74
Add a utility function to make watervapor LSM from SST LSM

@rogerkuou
rogerkuou marked this pull request as ready for review September 10, 2026 12:56
@rogerkuou

Copy link
Copy Markdown
Collaborator Author

Hi @SarahAlidoost , in this PR I implemented the function to make land-sea mask for watervapor data from SST. I made this PR to a feature branch to improve #74 . Maybe you want to review this one first?

@rogerkuou rogerkuou mentioned this pull request Sep 10, 2026
Comment thread climanet/utils.py Outdated
Comment thread climanet/utils.py Outdated

@SarahAlidoost SarahAlidoost left a comment

Copy link
Copy Markdown
Member

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

@rogerkuou Please see my suggestions! let me know if something is not clear.

rogerkuou and others added 3 commits September 11, 2026 12:08
Co-authored-by: SarahAlidoost <55081872+SarahAlidoost@users.noreply.github.com>
@rogerkuou

Copy link
Copy Markdown
Collaborator Author

Thanks @SarahAlidoost , I applied your comments and updated the function names and variable names. Can you give it another look?

@SarahAlidoost SarahAlidoost left a comment

Copy link
Copy Markdown
Member

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

@rogerkuou thanks for addressing the comments. It can be merged.

@rogerkuou
rogerkuou merged commit 54e17d6 into 73_water_vapor_notebook Sep 14, 2026
3 checks passed
@rogerkuou
rogerkuou deleted the 95_watervapor_lsm_util_func branch September 14, 2026 08:36
rogerkuou added a commit that referenced this pull request Sep 15, 2026
* rename daily notebooks

* add draft example notebook for watervapor

* check empty dataset in prediction

* update hourly watervapor notebook

* initiate loss as zero tensor

* update notebook

* changed loss to float

* rename patch with crop in dataset and predict module

* fix geo_embeding in the model

* remove spatial transfomer from the model

* add some model improvemnets

* uncomment groupnorm in decoder

* improve docstring

* remove patch from dataset, adjust api in source modules

* fix linters

* fix tests

* fix docstring and comments

* fix nbs

* add model.train in train loop (a bug)

* update scripts

* fix run_best_tuned_model script

* rerun example_tuning nb

* re-structure training

* rename_notebook

* add example notebook for daily watervapor data

* update unit name

* init hourly watervapo notebook

* initial water vapor hourly training

* add commented out code section for generating 0.5 deg lsm

* 95 watervapor lsm util func (#96)

* implement lsm convertion func from sst to wv

* add unit test; fix linting issue

* update notebooks with lsm conversion func

* linting

* rerun daily notebook

* Apply batched suggestions from code review

Co-authored-by: SarahAlidoost <55081872+SarahAlidoost@users.noreply.github.com>

* rename function

* update variable name

---------

Co-authored-by: SarahAlidoost <55081872+SarahAlidoost@users.noreply.github.com>

* Apply suggestion from @SarahAlidoost

Co-authored-by: SarahAlidoost <55081872+SarahAlidoost@users.noreply.github.com>

* solve conficts

* change spatial_patch_size to spatial_crop_size

* remove duplicated cell

* remove unuser import

* use jan for hourly notebook

* update parameters in hourly notebook

* rerun hourly notenook

---------

Co-authored-by: SarahAlidoost <f.alidoost@esciencecenter.nl>
Co-authored-by: SarahAlidoost <55081872+SarahAlidoost@users.noreply.github.com>
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

2 participants