Add new datasets - April 2026

src/ccdtools/config/datasets.yaml

@@ -120,8 +120,30 @@ datasets:
       - basal melt rates
       - smb
       - ice thickness
+      - paolo 2024
+      - NSIDC 0792
     extension: nc
 
+  rema:
+    display_name: REMA
+    path: /g/data/av17/admin/staging/cryosphere-data-pool/elevation_geometry/rema
+    description: The Reference Elevation Model of Antarctica (REMA) is a high resolution, time-stamped Digital Surface Model (DSM) of Antarctica.
+    tags:
+      - antarctica
+      - surface elevation
+      - rema
+    extension: tif
+    doi:
+      v2: 10.7910/DVN/EBW8UC
+    resolutions:
+      v2: 
+        static:
+          100m: 100m
+          500m: 500m
+          1000m: 1km
+    static_patterns:
+      v2: "rema_mosaic_"
+
   # GEOSPTATIAL DATASETS
   measures_antarctic_boundaries:
     display_name: Antarctic Boundaries for IPY 2007-2009 from Satellite Radar
@@ -133,6 +155,9 @@ datasets:
       - grounding line
       - ice front
       - ice mask
+      - NSIDC 0709
+      - boundaries
+      - drainage basins
     extension: shp
     doi:
       v1: 10.5067/SEVV4MR8P1ZN
@@ -198,6 +223,30 @@ datasets:
           50km: "50"
     static_patterns:
       v1: "aq1_01_"
+
+  annual_ice_shelves_mass_balance:
+    doi: 10.5281/zenodo.8052519
+    display_name: Annual mass budget of Antarctic ice shelves from 1997 to 2021
+    path: /g/data/av17/admin/staging/cryosphere-data-pool/basal_forcing/ice_shelves_annual_mass_balance_1997_2021
+    description: Sub-ice shelf basal melt rates, masks, and basal mass balance timeseries from Davison et al. 2023.
+    tags:
+      - antarctica
+      - basal melt rates
+      - davison 2023
+    ignore_dirs:
+      - code
+    subdatasets:
+      v1:
+        melt_rate:
+          subpath: data/basal_melt
+          extension: tif
+        masks:
+          subpath: data/masks/merged
+          extension: shp
+        timeseries:
+          subpath: data/basal_melt/timeseries/csv_outputs
+          extension: csv
+          loader: davison_timeseries
 
   # ICE VELOCITY DATASETS
   measures_annual_antarctic_ice_velocity_maps:

src/ccdtools/loaders.py

@@ -11,6 +11,7 @@
 from datetime import datetime
 import re
 import warnings
+import pathlib
 
 def default(self, row, resolution = None, static = True, **kwargs):
     """
@@ -532,4 +533,43 @@ def _preprocessor(ds):
         "for timesteps where a given variable does not have data. Users should use caution when considering\n"
         "time-varying analysis and might consider 'trimming' data to isolate all non-NaN arrays for a given variable.")
 
+    return output
+
+def davison_timeseries(self, row, **kwargs):
+
+    # Extract parameters from row
+    path, ext, skip_lines, no_data, ignore_dirs, ignore_files, loader, resolutions, static_patterns = self._extract_row_params(row)
+
+    # Normalise lists as needed
+    ignore_dirs = self._normalise_list(ignore_dirs)
+    ignore_files = self._normalise_list(ignore_files)
+
+    # Find files
+    files = self._recursive_find_files(path, ext, ignore_dirs = ignore_dirs, ignore_files = ignore_files)
+
+    # Set low_memory option
+    low_memory = kwargs.pop("low_memory", False)
+
+    # Empty lisy to store all files
+    data_list = []
+
+    # Loop over files, read them in, append them to list, and strip ice shelf name
+    for f in files:
+        # Extract name before "-timeseries.csv"
+        name = pathlib.Path(f).stem.replace("-timeseries", "")
+
+        data = pd.read_csv(f, skiprows = skip_lines, low_memory = low_memory, index_col = 0, **kwargs)
+
+        # Add new column with extracted name as the first colum
+        data.insert(0, "shelf_name", name)
+
+        data_list.append(data)
+
+    # Concatenate all CSVs
+    output = pd.concat(data_list, ignore_index=True)
+
+    # Replace no_data values
+    if no_data is not None:
+        output = output.replace(no_data, np.nan)
+
     return output