Release 0.7.0

.github/workflows/distribute.yml

@@ -29,26 +29,7 @@ jobs:
           python -m build
 
       - name: upload to PyPI.org
-        uses: pypa/[email protected].10
+        uses: pypa/[email protected].12
         with:
           user: __token__
           password: ${{ secrets.TOOLS_PYPI_PAK }}
-
-  verify-distribution:
-    runs-on: ubuntu-latest
-    needs:
-      - call-version-info-workflow
-      - distribute
-    defaults:
-      run:
-        shell: bash -l {0}
-    steps:
-      - uses: actions/checkout@v4
-
-      - uses: mamba-org/setup-micromamba@v1
-        with:
-          environment-file: environment.yml
-
-      - name: Ensure asf_tools v${{ needs.call-version-info-workflow.outputs.version }}} is pip installable
-        run: |
-          python -m pip install asf_tools==${{ needs.call-version-info-workflow.outputs.version_tag }}

.github/workflows/static-analysis.yml

@@ -8,7 +8,7 @@ jobs:
     steps:
       - uses: actions/checkout@v4
 
-      - uses: actions/setup-python@v4
+      - uses: actions/setup-python@v5
         with:
           python-version: "3.10"
 

CHANGELOG.md

@@ -6,6 +6,11 @@ The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.0.0/),
 and this project adheres to [PEP 440](https://www.python.org/dev/peps/pep-0440/) 
 and uses [Semantic Versioning](https://semver.org/spec/v2.0.0.html).
 
+## [0.7.0]
+
+## Added
+* Scripts and entrypoints for generating our global watermasking dataset added to `watermasking`.
+
 
 ## [0.6.0]
 

environment.yml

@@ -23,7 +23,10 @@ dependencies:
   - boto3
   - fiona
   - gdal>=3.7
+  - geopandas
   - numpy
+  - osmium-tool
+  - pyogrio
   - pysheds>=0.3
   - rasterio
   - scikit-fuzzy

pyproject.toml

@@ -25,14 +25,15 @@ dependencies = [
     "astropy",
     "fiona",
     "gdal>=3.3",
+    "geopandas",
     "numpy",
+    "pyogrio",
     "pysheds>=0.3",
     "rasterio",
     "scikit-fuzzy",
     "scikit-image",
     "scipy",
-    "shapely",
-    "tqdm",
+    "shapely"
 ]
 dynamic = ["version"]
 
@@ -41,6 +42,9 @@ make_composite = "asf_tools.composite:main"
 water_map = "asf_tools.hydrosar.water_map:main"
 calculate_hand = "asf_tools.hydrosar.hand.calculate:main"
 flood_map = "asf_tools.hydrosar.flood_map:main"
+generate_osm_dataset = "asf_tools.watermasking.generate_osm_tiles:main"
+generate_worldcover_dataset = "asf_tools.watermasking.generate_worldcover_tiles:main"
+fill_missing_tiles = "asf_tools.watermasking.fill_missing_tiles:main"
 
 [project.entry-points.hyp3]
 water_map = "asf_tools.hydrosar.water_map:hyp3"

src/asf_tools/watermasking/README.MD

@@ -0,0 +1,18 @@
+These scripts are for creating a global (or regional) water mask dataset based off of OpenStreetMaps, and optionally augmented by ESA WorldCover.
+
+For the OSM water mask dataset, follow these steps to replicate our dataset:
+
+1. Download the "Latest Weekly Planet PBF File" file from here: "https://planet.openstreetmap.org/".
+2. Download the WGS84 water polygons shapefile from: "https://osmdata.openstreetmap.de/data/water-polygons.html".
+3. The files should be unzipped and you should have something like `planet.osm.pbf` or `planet.pbf` and `water_polygons.shp` (and the support files for `water_polygons.shp`). 
+4. Run ```generate_osm_dataset --planet-file-path [path-to-planet.pbf] --ocean-polygons-path [path-to-water-polygons.shp] --lat-begin -85 --lat-end 85 --lon-begin -180 --lon-end 180 --tile-width 5 --tile-height 5```
+5. Run ```fill_missing_tiles --fill-value 0 --lat-begin -90 --lat-end -85 --lon-begin -180 --lon-end 180 --tile-width 5 --tile-height 5```
+6. Run ```fill_missing_tiles --fill-value 1 --lat-begin 85 --lat-end 90 --lon-begin -180 --lon-end 180 --tile-width 5 --tile-height 5```
+
+For the WorldCover water mask dataset, follow these steps:
+
+1. Download the portions of the dataset for the areas you would like to cover from here: "https://worldcover2020.esa.int/downloader"
+2. Extract the contents into a folder. Note, if you download multiple portions of the dataset, extract them all into the same folder.
+3. Run ```generate_worldcover_dataset --worldcover-tiles-dir [path-to-worldcover-data] --lat-begin 55 --lat-end 80 --lon-begin -180 --lon-end 180 --tile-width 5 --tile-height 5```
+
+Note that we only use WorldCover data over Alaska, Canada, and Russia for our dataset.

src/asf_tools/watermasking/fill_missing_tiles.py

@@ -0,0 +1,75 @@
+import argparse
+import os
+import subprocess
+
+import numpy as np
+from osgeo import gdal, osr
+
+from asf_tools.watermasking.utils import lat_lon_to_tile_string
+
+
+gdal.UseExceptions()
+
+
+def main():
+
+    parser = argparse.ArgumentParser(
+        prog='fill_missing_tiles.py',
+        description='Script for creating filled tifs in areas with missing tiles.'
+    )
+
+    parser.add_argument('--fill-value', help='The value to fill the data array with.', default=0)
+    parser.add_argument('--lat-begin', help='The minimum latitude of the dataset in EPSG:4326.', default=-85)
+    parser.add_argument('--lat-end', help='The maximum latitude of the dataset in EPSG:4326.', default=85)
+    parser.add_argument('--lon-begin', help='The minimum longitude of the dataset in EPSG:4326.', default=-180)
+    parser.add_argument('--lon-end', help='The maximum longitude of the dataset in EPSG:4326.', default=180)
+    parser.add_argument('--tile-width', help='The desired width of the tile in degrees.', default=5)
+    parser.add_argument('--tile-height', help='The desired height of the tile in degrees.', default=5)
+
+    args = parser.parse_args()
+
+    fill_value = int(args.fill_value)
+    lat_begin = int(args.lat_begin)
+    lat_end = int(args.lat_end)
+    lon_begin = int(args.lon_begin)
+    lon_end = int(args.lon_end)
+    tile_width = int(args.tile_width)
+    tile_height = int(args.tile_height)
+
+    lat_range = range(lat_begin, lat_end, tile_height)
+    lon_range = range(lon_begin, lon_end, tile_width)
+
+    for lat in lat_range:
+        for lon in lon_range:
+
+            tile = lat_lon_to_tile_string(lat, lon, is_worldcover=False, postfix='')
+            tile_tif = 'tiles/' + tile + '.tif'
+            tile_cog = 'tiles/cogs/' + tile + '.tif'
+
+            print(f'Processing: {tile}')
+
+            xmin, ymin = lon, lat
+            pixel_size_x = 0.00009009009
+            pixel_size_y = 0.00009009009
+
+            # All images in the dataset should be this size.
+            data = np.empty((55500, 55500))
+            data.fill(fill_value)
+
+            driver = gdal.GetDriverByName('GTiff')
+            dst_ds = driver.Create(tile_tif, xsize=data.shape[0], ysize=data.shape[1], bands=1, eType=gdal.GDT_Byte)
+            dst_ds.SetGeoTransform([xmin, pixel_size_x, 0, ymin, 0, pixel_size_y])
+            srs = osr.SpatialReference()
+            srs.ImportFromEPSG(4326)
+            dst_ds.SetProjection(srs.ExportToWkt())
+            dst_band = dst_ds.GetRasterBand(1)
+            dst_band.WriteArray(data)
+            del dst_ds
+
+            command = f'gdal_translate -of COG -co NUM_THREADS=all_cpus {tile_tif} {tile_cog}'.split(' ')
+            subprocess.run(command)
+            os.remove(tile_tif)
+
+
+if __name__ == '__main__':
+    main()