Paper fixes

.github/workflows/check-version.yml

@@ -1,7 +1,7 @@
 # Check for changes in the upstream template. If changes are found, an issue is created
 name: Template check.
 on:
-  workflow_dispatch: 
+  workflow_dispatch:
   schedule:
     - cron: '0 0 1 * *' # Runs at 00:00 UTC on the 1st day of every month
 

.github/workflows/pr-ci.yml

@@ -33,7 +33,7 @@ jobs:
         uses: actions/upload-artifact@v4
         with:
           name: integration-test-logs-${{ matrix.os }}
-          path: tests/integration/resources/geo_boundaries/logs
+          path: tests/integration/resources/module/logs
           if-no-files-found: ignore
           retention-days: 30
       - name: Fail if integration or linting failed

.pre-commit-config.yaml

@@ -12,7 +12,7 @@ repos:
       # Repo quality
       - id: check-added-large-files
         args: [--enforce-all]
-        exclude: ^pixi\.lock$
+        exclude: ^(?:pixi\.lock|figures/architecture\.drawio\.png)$
       - id: forbid-submodules
       - id: check-case-conflict
       - id: check-illegal-windows-names

README.md

@@ -22,15 +22,15 @@ and the `snakemake` [documentation](https://snakemake.readthedocs.io/en/stable/s
 Data processing steps:
 
 <p align="center">
-  <img src="./figures/rulegraph.png" width="60%">
+  <img src="./figures/architecture.drawio.png" width="90%">
 </p>
 
 
 1. The configuration file is read to identify the datasets to use as well as the specific countries and regional aggregation (`subtype` in the configuration) to process.
-    - Country area data: [GADM](https://gadm.org/), [Overture Maps](https://overturemaps.org/) and [NUTS](https://ec.europa.eu/eurostat/web/gisco/geodata/statistical-units/territorial-units-statistics) divisions are supported.
-    - Exclusive Economic Zone (EEZ) data: [Marine regions](https://www.marineregions.org/).
+    - Country landmass data: [eurostat NUTS](https://ec.europa.eu/eurostat/web/gisco/geodata/statistical-units/territorial-units-statistics), [GADM](https://gadm.org/), [geoBoundaries](https://www.geoboundaries.org/), and [Overture Maps](https://overturemaps.org/) are supported.
+    - Exclusive Economic Zone (EEZ) data: [MarineRegions.org](https://www.marineregions.org/).
 2. Individual country files are downloaded and harmonised to fit a standardised schema.
-    - Contested regions are removed at this stage.
+    - If identified, contested regions are removed at this stage.
     - Land is clipped using maritime Exclusive Economic Zones (EEZ).
     - Optionally, a Voronoi algorithm is run to separate EEZ areas to fit subnational regions.
 3. Each country file is combined and then clipped using its neighbours to minimise overlapping polygons.
@@ -40,7 +40,7 @@ Data processing steps:
 > Use the references at the bottom of this page for more details.
 
 > [!CAUTION]
-> To increase the replicability of your workflow, we recommend using NUTS and GADM as sources whenever possible as they are more stable than Overture Maps.
+> To increase the replicability of your workflow, we recommend using NUTS and geoBoundaries as sources whenever possible as they have more stable hosting methods than Overture Maps and GADM.
 
 ## Configuration
 <!-- Please describe how to configure this module below -->
@@ -86,11 +86,15 @@ snakemake --use-conda --cores 2  # run the workflow!
 This module is based on the following research and datasets.
 We encourage users to cite both the original source and our workflow.
 
+- eurostat NUTS (various years). Nomenclature of territorial units for statistics (NUTS).
+    - License: reuse is authorised provided the source is acknowledged. <https://ec.europa.eu/eurostat/statistics-explained/index.php?title=Copyright/licence_policy>
 - GADM 4.1. (2018). Global Administrative Areas (GADM).
     - License: GADM data is freely available for academic and non-commercial use. <https://gadm.org/license.html>.
-- NUTS (various years). Nomenclature of territorial units for statistics (NUTS).
-    - License: reuse is authorised provided the source is acknowledged. <https://ec.europa.eu/eurostat/statistics-explained/index.php?title=Copyright/licence_policy>
-- Overture Maps Divisions database (most recent version). Overture Maps Foundation.
-    - License: ODbL. See <https://docs.overturemaps.org/attribution/> and <https://opendatacommons.org/licenses/odbl/summary/> for details.
+- geoBoundaries (most recent version). William & Mary geoLab.
+    - License: varies per dataset type (from CC-BY 4.0 compliant to non-commercial use only).
+    Consult their documentation for details.
+    <https://www.geoboundaries.org/>.
 - Marine Regions World EEZ v12 (2023). Flanders Marine Institute (MarineRegions.org).
     - License: CC-By. See <https://www.marineregions.org/disclaimer.php>.
+- Overture Maps Divisions database (most recent version). Overture Maps Foundation.
+    - License: ODbL. See <https://docs.overturemaps.org/attribution/> and <https://opendatacommons.org/licenses/odbl/summary/> for details.

config/china_example.yaml

@@ -1,6 +1,5 @@
 # Example of regional disaggregation of a large country
 # China has contested borders, which will be removed by the module
-overture_release: "latest"
 crs:
   projected: "epsg:3857"
   geographic: "epsg:4326"

config/config.yaml

@@ -1,5 +1,4 @@
 # A minimal example of how to configure this module
-overture_release: "latest"
 voronoi_eez:
   enabled: True
   sample_spacing: 10000 # sample every 10 km
@@ -16,11 +15,13 @@ countries:
     subtype: "country"
     source: "overture"
   NLD:
-    subtype: "0"
-    source: "gadm"
+    subtype: 0
+    source: "geoboundaries"
+    release_type: "gbOpen"
   BEL:
-    subtype: "country"
-    source: "overture"
+    subtype: 1
+    source: "geoboundaries"
+    release_type: "gbOpen"
   CHE:
     subtype: "country"
     source: "overture"

config/europe_example.yaml

@@ -1,115 +1,157 @@
 # A minimal example of how to configure this module
-overture_release: "latest"
 voronoi_eez:
   enabled: True
   sample_spacing: 10000
 crs:
   projected: "epsg:3035"
   geographic: "epsg:4326"
 countries:
+  "ALB":
+    subtype: "1"
+    source: "geoboundaries"
+    release_type: "gbOpen"
   "AUT":
     subtype: "1"
-    source: "gadm"
+    source: "geoboundaries"
+    release_type: "gbOpen"
   "BEL":
     subtype: "1"
-    source: "gadm"
+    source: "geoboundaries"
+    release_type: "gbOpen"
   "BGR":
     subtype: "1"
-    source: "gadm"
-  "HRV":
+    source: "geoboundaries"
+    release_type: "gbOpen"
+  "BIH":
     subtype: "1"
-    source: "gadm"
+    source: "geoboundaries"
+    release_type: "gbOpen"
+  "CHE":
+    subtype: "1"
+    source: "geoboundaries"
+    release_type: "gbOpen"
   "CYP":
     subtype: "1"
-    source: "gadm"
+    source: "geoboundaries"
+    release_type: "gbOpen"
   "CZE":
     subtype: "1"
-    source: "gadm"
+    source: "geoboundaries"
+    release_type: "gbOpen"
+  "DEU":
+    subtype: "1"
+    source: "geoboundaries"
+    release_type: "gbOpen"
   "DNK":
-    subtype: "2"
+    subtype: "1"
     source: "nuts"
-    resolution: 03M
+    resolution: 01M
     year: 2024
+  "ESP":
+    subtype: "1"
+    source: "geoboundaries"
+    release_type: "gbOpen"
+    extra_eez: 8364
   "EST":
     subtype: "1"
-    source: "gadm"
+    source: "geoboundaries"
+    release_type: "gbOpen"
   "FIN":
     subtype: "1"
-    source: "gadm"
+    source: "geoboundaries"
+    release_type: "gbOpen"
   "FRA":
     subtype: "1"
-    source: "gadm"
-  "DEU":
-    subtype: "1"
-    source: "gadm"
+    source: "geoboundaries"
+    release_type: "gbOpen"
+  "GBR":
+    subtype: "region"
+    source: "overture"
+  "GGY":
+    subtype: "0"
+    source: "geoboundaries"
+    release_type: "gbOpen"
   "GRC":
     subtype: "1"
-    source: "gadm"
+    source: "geoboundaries"
+    release_type: "gbOpen"
+  "HRV":
+    subtype: "1"
+    source: "geoboundaries"
+    release_type: "gbOpen"
   "HUN":
     subtype: "1"
-    source: "gadm"
+    source: "geoboundaries"
+    release_type: "gbOpen"
+  "IMN":
+    subtype: "0"
+    source: "geoboundaries"
+    release_type: "gbOpen"
   "IRL":
     subtype: "region"
     source: "overture"
   "ITA":
     subtype: "1"
-    source: "gadm"
-  "LVA":
-    subtype: "1"
-    source: "gadm"
+    source: "geoboundaries"
+    release_type: "gbOpen"
   "LTU":
     subtype: "1"
-    source: "gadm"
+    source: "geoboundaries"
+    release_type: "gbOpen"
   "LUX":
     subtype: "1"
-    source: "gadm"
+    source: "geoboundaries"
+    release_type: "gbOpen"
+  "LVA":
+    subtype: "1"
+    source: "geoboundaries"
+    release_type: "gbOpen"
+  "MKD":
+    subtype: "1"
+    source: "geoboundaries"
+    release_type: "gbOpen"
+  "MNE":
+    subtype: "1"
+    source: "geoboundaries"
+    release_type: "gbOpen"
   "NLD":
     subtype: "region"
     source: "overture"
+  "NOR":
+    subtype: "1"
+    source: "geoboundaries"
+    release_type: "gbOpen"
   "POL":
     subtype: "1"
-    source: "gadm"
+    source: "geoboundaries"
+    release_type: "gbOpen"
   "PRT":
-    subtype: "2"
+    subtype: "1"
     source: "nuts"
-    resolution: 03M
+    resolution: 01M
     year: 2024
+    extra_eez: [8361, 8363]
   "ROU":
     subtype: "1"
-    source: "gadm"
+    source: "geoboundaries"
+    release_type: "gbOpen"
+  "SRB":
+    subtype: "1"
+    source: "geoboundaries"
+    release_type: "gbOpen"
   "SVK":
     subtype: "1"
-    source: "gadm"
+    source: "geoboundaries"
+    release_type: "gbOpen"
   "SVN":
     subtype: "1"
-    source: "gadm"
-  "ESP":
-    subtype: "1"
-    source: "gadm"
+    source: "geoboundaries"
+    release_type: "gbOpen"
   "SWE":
     subtype: "1"
-    source: "gadm"
-  "GBR":
-    subtype: "region"
-    source: "overture"
-  "ALB":
-    subtype: "1"
-    source: "gadm"
-  "BIH":
-    subtype: "1"
-    source: "gadm"
-  "MKD":
-    subtype: "1"
-    source: "gadm"
-  "MNE":
-    subtype: "1"
-    source: "gadm"
-  "NOR":
-    subtype: "1"
-    source: "gadm"
-  "SRB":
-    subtype: "1"
-    source: "gadm"
-  "CHE":
+    source: "geoboundaries"
+    release_type: "gbOpen"
+  "XKX":
     subtype: "1"
-    source: "gadm"
+    source: "geoboundaries"
+    release_type: "gbOpen"

config/usa_example.yaml

@@ -1,6 +1,5 @@
 # Example of regional disaggregation of a large country
 # USA has multiple marine zones, which can be appended as extras
-overture_release: "latest"
 voronoi_eez:
   enabled: True
   sample_spacing: 10000 # sample every 10 km