Add InSAR-based Antarctic grounding line to subset training tiles within grounded ice boundary #147
Conversation
This file contains 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
Adding the InSAR-based Antarctic grounding line dataset from Mouginot et al., 2017. The vector polygon is stored in a shapefile format, and we download it from the PGC Quantarctica archive. Also ignoring the .shp, .shx and .dbf data files now. Moving forward, I really need to standardize on the citekey naming scheme (that uses either the dataset or literature citation's first author, dubious years, etc)...
Add rtree from PyPI to make geopandas.sjoin work, and for that we need libspatialindex from conda-forge.
weiji14
added
enhancement ✨
|
Check out this pull request on ReviewNB: https://app.reviewnb.com/weiji14/deepbedmap/pull/147 Visit www.reviewnb.com to know how we simplify your Jupyter Notebook workflows. |
Constrain our square training tiles to only exist within the grounded ice area (give or take). To do that, we first buffer the MEASURES InSAR-based grounding line (actually a polygon of grounded ice areas) by 10km, and then select all the tiles which are contained within this buffered polygon. Makes use of geopandas' sjoin (spatial join). Also, the re-saved geojson files appear to show some decimal differences for tiles_4326.geojson but not tiles_3031.geojson, perhaps because there has been some changes in the pyproj library or something else?
weiji14
added a commit
that referenced
this pull request
May 29, 2019
Closes #147 Add InSAR-based Antarctic grounding line to subset training tiles within grounded ice boundary.
2 tasks
weiji14
added a commit
that referenced
this pull request
May 29, 2019
Finally we have Arthern Accumulation, and at a spatial resolution of 1000m just like BEDMAP2! Putting it down as conditional input W3, after REMA W1 and MEASURES Ice Velocity W2. We are down from 2499 to 2347 tiles due to the new grounding line restriction from #147, though this subset should be scientifically better. Time to spin up our GPUs for some neural network training!
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.
Adding MEaSUREs Antarctic Grounding Line from Differential Satellite Radar Interferometry from Mouginot et al., 2017, a vector polygon stored in shapefile format downloaded from PGC's Quantarctica archive. Constraining DeepBedMap training to areas more or less within the grounding line (i.e. not in ice shelf cavities).
References:
TODO: