Point to Grid Translator for MetNet3 (OMO weather stations) - #85
Open
trudramukerji14 wants to merge 2 commits into
Open
Point to Grid Translator for MetNet3 (OMO weather stations)#85trudramukerji14 wants to merge 2 commits into
trudramukerji14 wants to merge 2 commits into
Conversation
trudramukerji14
marked this pull request as ready for review
August 13, 2026 13:34
Contributor
Author
|
Hi @jacobbieker I just made this PR on the point-to-grid translator for the OMO stations. Let me know if I missed anything or if I should add/change anything here. No rush! |
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Pull Request
Description
The point-to-grid translator maps sparse weather station observations onto the same 624×624 grid resolution as the other image-based inputs (radar, satellite), so they can all be concatenated together into a single tensor.
Note on data sources: . This implementation uses MADIS 1-minute ASOS data as a public approximation, with 14 variables selected from the OMO variable list at madis.ncep.noaa.gov as our best approximation of the input channels described in Table 1 of the paper. The 14 variables used are based on the OMO variable list at:
https://madis.ncep.noaa.gov/sfc_OMO_variable_list.shtml
"""
Note on projection: The paper does not specify the map projection used. This implementation uses Lambert Conformal Conic (LCC) projection via pyproj, which is the standard projection for CONUS weather data and is used by all other MetNet-3 input sources (MRMS, HRRR, NEXRAD).
**Other changes:
How Has This Been Tested?
Added tests to tests/test_data.py covering:
test_output_shape — verifies the output tensor has the correct shape [14, grid_height, grid_width]
test_fill_value — verifies empty grid cells have the correct fill value when no stations are provided
test_nan_handling — verifies NaN values in station observations are ignored and don't propagate to the grid
test_outside_bounds — verifies stations outside the grid domain are correctly ignored
test_averaging — verifies multiple stations falling in the same pixel are correctly averaged
Checklist: