OceanDataStore 0.3.0__py3-none-any.whl

OceanDataStore/data/ERA5/update_ERA5_daily_to_os.py

@@ -0,0 +1,141 @@
+# =========================================================
+# send_ERA5_daily_to_os.py
+#
+# Script to write ERA5 daily data to Icechunk repositories
+# in JASMIN cloud object storage.
+#
+# Created By: Ollie Tooth (oliver.tooth@noc.ac.uk)
+# =========================================================
+import logging
+from pathlib import Path
+
+import xarray as xr
+import zarr
+
+from OceanDataStore.cli import initialise_logging, update_icechunk
+from OceanDataStore.data.utils import (
+    compute_cell_area,
+    compute_dx,
+    compute_dy,
+    compute_land_sea_mask,
+)
+
+logger = logging.getLogger(__name__)
+
+
+def main():
+    # ========== Initialise OceanDataStore Logging ========== #
+    initialise_logging()
+
+    # ========== Send to Icechunk Repository ========== #
+    bucket = "era5"
+    store_credentials_json = ".../credentials/jasmin_os_credentials.json"
+    branch = "main"
+    
+    logging.info("In Progress: Sending ERA5 daily data to Icechunk...")
+    # Open ERA5 dataset:
+    filepath = []
+    base = Path("/dssgfs01/scratch/otooth/npd_data/observations/ERA5/daily")
+    for year in range(2026, 2027):
+        filepath.extend(sorted(base.glob(f"sst_y{year}m??_daily.nc")))
+    ds = xr.open_mfdataset(filepath,
+                           combine="by_coords",
+                           data_vars="all",
+                           engine="h5netcdf",
+                           chunks={"time": -1, "latitude": -1, "longitude": -1}
+                           )
+
+    # Update longitude coordinates to be in the range [-180, 180]:
+    ds = ds.assign_coords(
+        longitude=((ds["longitude"] + 180) % 360) - 180
+    )
+    ds = ds.sortby("longitude")
+
+    # Update variable names, units, and attributes:
+    if "number" in ds.data_vars:
+        ds = ds.drop_vars(["number"])
+    for var in ds.data_vars:
+        if "sst" in var:
+            # Transform units degK -> degC:
+            ds[var] = ds[var] - 273.15
+            # Add standard names and units:
+            ds[var].attrs["standard_name"] = "sea_surface_temperature"
+            ds[var].attrs["units"] = "degC"
+            # Rename variables to standard names:
+            ds = ds.rename({var: var.replace("sst", "tos")})
+
+    # Update variable long names:
+    ds["tos"].attrs["long_name"] = "Daily Mean Sea Surface Temperature"
+    ds["tos_var"].attrs["long_name"] = "Daily Variance Sea Surface Temperature"
+    ds["tos_min"].attrs["long_name"] = "Daily Minimum Sea Surface Temperature"
+    ds["tos_max"].attrs["long_name"] = "Daily Maximum Sea Surface Temperature"
+
+    # Add ancillary variables:
+    ds['mask'] = compute_land_sea_mask(ds['tos'].isel(time=0))
+    ds['dx'] = compute_dx(ds)
+    ds['dy'] = compute_dy(ds)
+    ds['cell_area'] = compute_cell_area(ds)
+
+    # Update global attributes:
+    ds.attrs.clear()
+    ds = ds.assign_attrs({
+        "Conventions": "CF-1.7",
+        "title": "ERA5 Sea Surface Daily Timeseries",
+        "description": "ERA5 daily sea surface temperature timeseries.",
+        "source": "Numerical models: IFS Cy41r2 and 4D-Var data assimilation with prescribed sea surface temperature and sea ice concentration. Satellite observations: HadISST2.1.1.0, OSTIA, OSI SAF.",
+        "dataset_type": "reanalysis",
+        "product_type": "timeseries",
+        "product_version": "1.0",
+        "institution": "European Centre for Medium-Range Weather Forecasts (ECMWF)",
+        "citation": "Copernicus Climate Change Service, Climate Data Store, (2023): ERA5 hourly data on single levels from 1940 to present. Copernicus Climate Change Service (C3S) Climate Data Store (CDS). DOI: 10.24381/cds.adbb2d47 (Accessed on 20-05-2026).",
+        "references": "Hersbach, H., Bell, B., Berrisford, P., Biavati, G., Horányi, A., Muñoz Sabater, J., Nicolas, J., Peubey, C., Radu, R., Rozum, I., Schepers, D., Simmons, A., Soci, C., Dee, D., Thépaut, J-N. (2023): ERA5 hourly data on single levels from 1940 to present. Copernicus Climate Change Service (C3S) Climate Data Store (CDS), DOI: 10.24381/cds.adbb2d47.",
+        "acknowledgement": "Generated using or contains modified Copernicus Climate Change Service information . Neither the European Commission nor ECMWF is responsible for any use that may be made of the Copernicus information or data it contains.",
+        "license": "ERA5 data were obtained from https://cds.climate.copernicus.eu/datasets/reanalysis-era5-single-levels and are provided under a Creative Commons CC-BY-4.0 License https://creativecommons.org/licenses/by/4.0/",
+        "doi": "10.24381/cds.adbb2d47",
+        "platform": "gr",
+        "horizontal_grid_type": "regular rectilinear",
+        "horizontal_grid_resolution": "31 km",
+        "aggregation": "mean, variance, min, max",
+        "aggregation_frequency": "daily",
+        "status": "completed",
+        "update_frequency": "None",
+        "bbox": "[-180.0, 180.0, -90.0, 90.0]",
+    })
+
+    # Optimise chunk sizes for time-series analysis:
+    ds = ds.chunk({'time': ds['time'].size, 'latitude': 50, 'longitude': 50})
+
+    # Update variable encodings:
+    blosccodec = zarr.codecs.BloscCodec(cname="zstd", clevel=3, shuffle=zarr.codecs.BloscShuffle.shuffle)
+    for var in list(ds.data_vars) + list(ds.coords):
+        ds[var].encoding['compressors'] = [blosccodec]
+
+    # Define prefix and commit message based on climatology period:
+    prefix = "era5_daily_timeseries"
+    commit_message = "Added ERA5 Sea Surface Daily Timeseries (2026-01-2026-06)."
+
+    # Dask LocalCluster configuration:
+    config_kwargs = {
+            "temporary_directory":"/dssgfs01/working/otooth/Software/OceanDataStore/OceanDataStore/data/ERA5/",
+            "local_directory":"/dssgfs01/working/otooth/Software/OceanDataStore/OceanDataStore/data/ERA5/"
+        }
+    cluster_kwargs = {
+            "n_workers" : 20,
+            "threads_per_worker" : 1,
+            "memory_limit":"5GB"
+        }
+
+    update_icechunk(
+        file=ds,
+        bucket=bucket,
+        object_prefix=prefix,
+        store_credentials_json=store_credentials_json,
+        append_dim='time',
+        branch=branch,
+        commit_message=commit_message,
+        dask_config_kwargs=config_kwargs,
+        dask_cluster_kwargs=cluster_kwargs,
+        )
+
+if __name__ == "__main__":
+    main()

OceanDataStore/data/ERA5/update_ERA5_monthly_to_os.py

@@ -0,0 +1,169 @@
+# =========================================================
+# update_ERA5_monthly_to_os.py
+#
+# Script to update ERA5 monthly data in Icechunk repositories
+# in JASMIN cloud object storage.
+#
+# Created By: Ollie Tooth (oliver.tooth@noc.ac.uk)
+# =========================================================
+import logging
+
+import xarray as xr
+import zarr
+
+from OceanDataStore.cli import initialise_logging, update_icechunk
+from OceanDataStore.data.utils import (
+    compute_land_sea_mask,
+    compute_cell_area,
+    compute_dx,
+    compute_dy,
+)
+
+logger = logging.getLogger(__name__)
+
+
+def main():
+    # ========== Initialise OceanDataStore Logging ========== #
+    initialise_logging()
+
+    # ========== Update Icechunk Repository ========== #
+    bucket = "era5"
+    store_credentials_json = ".../credentials/jasmin_os_credentials.json"
+    branch = "main"
+    
+    logging.info("In Progress: Updating ERA5 monthly data in Icechunk...")
+    # Open ERA5 dataset:
+    filepath = "/dssgfs01/scratch/otooth/npd_data/observations/ERA5/monthly/sst_y20??m??_monthly.nc"
+    ds_sst = xr.open_mfdataset(filepath,
+                               combine="by_coords",
+                               data_vars="all",
+                               engine="h5netcdf",
+                               chunks={"time": -1, "latitude": -1, "longitude": -1}
+                               )
+    
+    filepath = "/dssgfs01/scratch/otooth/npd_data/observations/ERA5/monthly/siconc_y20??m??_monthly.nc"
+    ds_si = xr.open_mfdataset(filepath,
+                              combine="by_coords",
+                              data_vars="all",
+                              engine="h5netcdf",
+                              chunks={"time": -1, "latitude": -1, "longitude": -1}
+                              )
+
+    # SST: Update longitude coordinates to be in the range [-180, 180]:
+    ds_sst = ds_sst.assign_coords(
+        longitude=((ds_sst["longitude"] + 180) % 360) - 180
+    )
+    ds_sst = ds_sst.sortby("longitude")
+
+    # SIC: Update longitude coordinates to be in the range [-180, 180]:
+    ds_si = ds_si.assign_coords(
+        longitude=((ds_si["longitude"] + 180) % 360) - 180
+    )
+    ds_si = ds_si.sortby("longitude")
+
+    # SST: Update variable names, units, and attributes:
+    if "number" in ds_sst.data_vars:
+        ds_sst = ds_sst.drop_vars(["number"])
+    for var in ds_sst.data_vars:
+        if "sst" in var:
+            # Transform units degK -> degC:
+            ds_sst[var] = ds_sst[var] - 273.15
+            # Add standard names and units:
+            ds_sst[var].attrs["standard_name"] = "sea_surface_temperature"
+            ds_sst[var].attrs["units"] = "degC"
+            # Rename variables to standard names:
+            ds_sst = ds_sst.rename({var: var.replace("sst", "tos")})
+
+    # SIC: Update variable names, units, and attributes:
+    if "number" in ds_si.data_vars:
+        ds_si = ds_si.drop_vars(["number"])
+    for var in ds_si.data_vars:
+        if "siconc" in var:
+            # Add standard names and units:
+            ds_si[var].attrs["standard_name"] = "sea_ice_area_fraction"
+            ds_si[var].attrs["units"] = "1"
+
+    # SST: Update variable long names:
+    ds_sst["tos"].attrs["long_name"] = "Daily Mean Sea Surface Temperature"
+    ds_sst["tos_var"].attrs["long_name"] = "Daily Variance Sea Surface Temperature"
+    ds_sst["tos_min"].attrs["long_name"] = "Daily Minimum Sea Surface Temperature"
+    ds_sst["tos_max"].attrs["long_name"] = "Daily Maximum Sea Surface Temperature"
+
+    # SIC: Update variable long names:
+    ds_si["siconc"].attrs["long_name"] = "Daily Mean Sea Ice Area Fraction"
+    ds_si["siconc_var"].attrs["long_name"] = "Daily Variance Sea Ice Area Fraction"
+    ds_si["siconc_min"].attrs["long_name"] = "Daily Minimum Sea Ice Area Fraction"
+    ds_si["siconc_max"].attrs["long_name"] = "Daily Maximum Sea Ice Area Fraction"
+
+    # Merge SST and SIC datasets:
+    ds = xr.merge([ds_sst, ds_si], compat="override", join="override")
+
+    # Add ancillary variables:
+    ds['mask'] = compute_land_sea_mask(ds['tos'].isel(time=0))
+    ds['dx'] = compute_dx(ds)
+    ds['dy'] = compute_dy(ds)
+    ds['cell_area'] = compute_cell_area(ds)
+
+    # Update global attributes:
+    ds.attrs.clear()
+    ds = ds.assign_attrs({
+        "Conventions": "CF-1.7",
+        "title": "ERA5 Sea Surface Monthly Timeseries",
+        "description": "ERA5 monthly sea surface temperature and sea ice area fraction timeseries.",
+        "source": "Numerical models: IFS Cy41r2 and 4D-Var data assimilation with prescribed sea surface temperature and sea ice concentration. Satellite observations: HadISST2.1.1.0, OSTIA, OSI SAF.",
+        "dataset_type": "reanalysis",
+        "product_type": "timeseries",
+        "product_version": "1.0",
+        "institution": "European Centre for Medium-Range Weather Forecasts (ECMWF)",
+        "citation": "Copernicus Climate Change Service, Climate Data Store, (2023): ERA5 hourly data on single levels from 1940 to present. Copernicus Climate Change Service (C3S) Climate Data Store (CDS). DOI: 10.24381/cds.adbb2d47 (Accessed on 20-05-2026).",
+        "references": "Hersbach, H., Bell, B., Berrisford, P., Biavati, G., Horányi, A., Muñoz Sabater, J., Nicolas, J., Peubey, C., Radu, R., Rozum, I., Schepers, D., Simmons, A., Soci, C., Dee, D., Thépaut, J-N. (2023): ERA5 hourly data on single levels from 1940 to present. Copernicus Climate Change Service (C3S) Climate Data Store (CDS), DOI: 10.24381/cds.adbb2d47.",
+        "acknowledgement": "Generated using or contains modified Copernicus Climate Change Service information . Neither the European Commission nor ECMWF is responsible for any use that may be made of the Copernicus information or data it contains.",
+        "license": "ERA5 data were obtained from https://cds.climate.copernicus.eu/datasets/reanalysis-era5-single-levels and are provided under a Creative Commons CC-BY-4.0 License https://creativecommons.org/licenses/by/4.0/",
+        "doi": "10.24381/cds.adbb2d47",
+        "platform": "gr",
+        "horizontal_grid_type": "regular rectilinear",
+        "horizontal_grid_resolution": "31 km",
+        "aggregation": "mean, variance, min, max",
+        "aggregation_frequency": "monthly",
+        "status": "completed",
+        "update_frequency": "None",
+        "bbox": "[-180.0, 180.0, -90.0, 90.0]",
+    })
+
+    # Optimise chunk sizes for spatial analysis:
+    ds = ds.chunk({'time': 1, 'latitude': 721, 'longitude': 1440})
+
+    # Update variable encodings:
+    blosccodec = zarr.codecs.BloscCodec(cname="zstd", clevel=3, shuffle=zarr.codecs.BloscShuffle.shuffle)
+    for var in list(ds.data_vars) + list(ds.coords):
+        ds[var].encoding['compressors'] = [blosccodec]
+
+    # Define prefix and commit message based on climatology period:
+    prefix = "era5_monthly_timeseries"
+    commit_message = "Add ERA5 Sea Surface Monthly Timeseries (2000-01-2026-05)."
+
+    # Dask LocalCluster configuration:
+    config_kwargs = {
+            "temporary_directory":"/dssgfs01/working/otooth/Software/OceanDataStore/OceanDataStore/data/ERA5/",
+            "local_directory":"/dssgfs01/working/otooth/Software/OceanDataStore/OceanDataStore/data/ERA5/"
+        }
+    cluster_kwargs = {
+            "n_workers" : 25,
+            "threads_per_worker" : 1,
+            "memory_limit":"4GB"
+        }
+
+    update_icechunk(
+        file=ds,
+        bucket=bucket,
+        object_prefix=prefix,
+        store_credentials_json=store_credentials_json,
+        append_dim='time',
+        branch=branch,
+        commit_message=commit_message,
+        dask_config_kwargs=config_kwargs,
+        dask_cluster_kwargs=cluster_kwargs,
+        )
+
+if __name__ == "__main__":
+    main()

OceanDataStore/data/HadISST/download_HadISST1_data.sh

@@ -0,0 +1,43 @@
+#!/bin/bash
+
+# ----------------------------------------------------------------
+# download_HadISST1_data.sh
+#
+# This script downloads the HadISST1 dataset from the Met Office
+# Hadley Centre HadISST website. The files to be downloaded are
+# HadISST1_sst.nc.gz & HadISST_ice.nc.gz.
+#
+# Files will be downloaded into the current directory.
+#
+# Created By: Ollie Tooth (oliver.tooth@noc.ac.uk)
+# Created On: 2026-05-27
+# ----------------------------------------------------------------
+set -euo pipefail
+
+# --- Inputs --- #
+# Output directory for downloaded files:
+output_dir="/dssgfs01/scratch/otooth/npd_data/observations/HadISST"
+
+# Define base URL to HadISST1 dataset:
+url=https://www.metoffice.gov.uk/hadobs/hadisst/data
+
+# --- Main Script --- #
+echo "==================================================="
+echo "          Downloading HadISST1 Dataset"
+echo "                     v0.1.0"
+echo "               Oliver J. Tooth, NOC"
+echo "==================================================="
+echo "In Progress: Downloading HadISST1 dataset..."
+
+# Download the HadISST1 dataset:
+echo "-> Downloading HadISST1_sst.nc.gz & HadISST_ice.nc.gz..."
+wget -P $output_dir $url/HadISST_sst.nc.gz
+wget -P $output_dir $url/HadISST_ice.nc.gz
+
+# Unzip the files:
+echo "-> Unzipping HadISST1 dataset..."
+gunzip $output_dir/HadISST_sst.nc.gz
+gunzip $output_dir/HadISST_ice.nc.gz
+
+# Update users via stdout:
+echo "...Completed: HadISST1 dataset downloaded and unzipped."

OceanDataStore/data/HadISST/run_send_HadISST1_monthly_to_os.slurm

@@ -0,0 +1,32 @@
+#!/bin/bash
+#SBATCH --job-name=hadisst1_monthly
+#SBATCH --partition=test
+#SBATCH --time=00:20:00
+#SBATCH --ntasks-per-core=1
+#SBATCH --ntasks-per-node=64
+#SBATCH --ntasks-per-socket=32
+#SBATCH --nodes=1
+
+# ==============================================================
+# run_send_HadISST1_monthly_to_os.slurm
+#
+# Description: SLURM script to send the HadISST1 monthly 
+# time-series dataset to Icechunk repository.
+#
+# Created By: Ollie Tooth (oliver.tooth@noc.ac.uk)
+# Created On: 2026-06-24
+#
+# ==============================================================
+set -euo pipefail
+
+# -- Python Environment -- #
+# Activate miniconda environment:
+source /dssgfs01/working/otooth/miniforge3/bin/activate
+conda activate env_ods
+
+# -- Send HadISST1 monthly time-series datasets to JASMIN OS -- #
+echo "In Progress: Sending HadISST1 monthly time-series to Icechunk..."
+
+python3 send_HadISST1_monthly_to_os.py
+
+echo "Completed: Sent HadISST1 monthly time-series to Icechunk."

OceanDataStore/data/HadISST/send_HadISST1_monthly_to_os.py

@@ -0,0 +1,133 @@
+# =========================================================
+# send_HadISST1_monthly_to_os.py
+#
+# Script to write HadISST1 monthly data to Icechunk
+# repository in JASMIN cloud object storage.
+#
+# Created By: Ollie Tooth (oliver.tooth@noc.ac.uk)
+# =========================================================
+import logging
+
+import numpy as np
+import xarray as xr
+import zarr
+
+from OceanDataStore.cli import initialise_logging, send_to_icechunk
+from OceanDataStore.data.utils import (
+    compute_cell_area,
+    compute_dx,
+    compute_dy,
+    compute_land_sea_mask,
+)
+
+logger = logging.getLogger(__name__)
+
+
+def main():
+    # ========== Initialise OceanDataStore Logging ========== #
+    initialise_logging()
+
+    # ========== Prepare Data ========== #
+    # Open HadISST1 monthly dataset:
+    filedir = "/dssgfs01/scratch/otooth/npd_data/observations/HadISST"
+    ds = xr.open_dataset(f"{filedir}/HadISST_sst.nc", engine="netcdf4")
+    ds_si = xr.open_dataset(f"{filedir}/HadISST_ice.nc", engine="netcdf4")
+
+    # Add sea ice concentration to single dataset:
+    ds['sic'] = ds_si['sic']
+
+    # Rename variables to standard names:
+    ds = ds.rename({"sst": "tos", "sic": "siconc"})
+    # Fill missing sea surface temperature values with NaNs:
+    ds['tos'] = xr.where(cond=ds['tos'] == -1000, x=np.nan, y=ds['tos'])
+
+    # Update variable attributes:
+    ds["tos"].attrs.update({
+        "long_name": "Sea Surface Temperature",
+    })
+    ds["siconc"].attrs.update({
+        "long_name": "Sea Ice Area Fraction",
+    })
+
+    # Update global attributes:
+    ds.attrs.clear()
+
+    ds = ds.assign_attrs({
+        "Conventions": "CF-1.0",
+        "title": "Hadley Centre Sea Ice and Sea Surface Temperature (HadISST) monthly timeseries.",
+        "description": "HadISST v1.1 monthly averages of sea surface temperature and sea ice concentration.",
+        "source": "Numerical models: Reduced Space Optimal Interpolation. In-situ observations: Met Office Marine Data Bank (MDB), Comprehensive Ocean-Atmosphere Data Set (COADS). Satellite observations: Advanced Very High Resolution Radiometer (AVHRR).",
+        "dataset_type": "observation",
+        "product_type": "timeseries",
+        "product_version": "1.1",
+        "institution": "Met Office, UK",
+        "citation": "Rayner, N. A., Parker, D. E., Horton, E. B., Folland, C. K., Alexander, L. V., Rowell, D. P., Kent, E. C., Kaplan, A.  Global analyses of sea surface temperature, sea ice, and night marine air temperature since the late nineteenth century J. Geophys. Res.Vol. 108, No. D14, 4407 10.1029/2002JD002670.",
+        "references": "Rayner, N. A., Parker, D. E., Horton, E. B., Folland, C. K., Alexander, L. V., Rowell, D. P., Kent, E. C., Kaplan, A.  Global analyses of sea surface temperature, sea ice, and night marine air temperature since the late nineteenth century J. Geophys. Res.Vol. 108, No. D14, 4407 10.1029/2002JD002670.",
+        "acknowledgement": "None",
+        "license": "HadISST1.1 data were obtained from https://www.metoffice.gov.uk/hadobs/hadisst/ and are © Crown Copyright, Met Office, [2026], provided under a Non-Commercial Government Licence http://www.nationalarchives.gov.uk/doc/non-commercial-government-licence/version/2/.",
+        "doi": "None",
+        "platform": "gr",
+        "horizontal_grid_type": "regular rectilinear",
+        "horizontal_grid_resolution": "1 degree",
+        "aggregation": "mean",
+        "aggregation_frequency": "monthly",
+        "status": "ongoing",
+        "update_frequency": "quarterly",
+        "bbox": "[-180.0, 180.0, -90.0, 90.0]",
+    })
+
+    # Add ancillary variables:
+    ds['mask'] = compute_land_sea_mask(ds['tos'].isel(time=0))
+    ds['dx'] = compute_dx(ds)
+    ds['dy'] = compute_dy(ds)
+    ds['cell_area'] = compute_cell_area(ds)
+
+    # Add Northern and Southern Hemisphere sea ice area timeseries:
+    ds['siarea_NH'] = (ds['siconc'].where(ds['latitude'] > 0) * ds['cell_area']).sum(dim=['latitude', 'longitude'])
+    ds['siarea_NH'].attrs = {'long_name': 'Total Northern Hemisphere Sea Ice Area', 'standard_name': 'sea_ice_area', 'units': 'm2'}
+
+    ds['siarea_SH'] = (ds['siconc'].where(ds['latitude'] < 0) * ds['cell_area']).sum(dim=['latitude', 'longitude'])
+    ds['siarea_SH'].attrs = {'long_name': 'Total Southern Hemisphere Sea Ice Area', 'standard_name': 'sea_ice_area', 'units': 'm2'}
+
+    # ========== Send to Icechunk Repository ========== #
+    bucket = "hadisst"
+    prefix = "hadisst_v1.1_monthly"
+    exists = False
+    store_credentials_json = ".../credentials/jasmin_os_credentials.json"
+    branch = "main"
+    commit_message = "Added HadISST1 sea surface temperature and sea ice concentration monthly (1870-01-2026-04)."
+    variable_commits = True
+    config_kwargs = {
+            "temporary_directory":"/dssgfs01/working/otooth/Software/OceanDataStore/OceanDataStore/data/HadISST/",
+            "local_directory":"/dssgfs01/working/otooth/Software/OceanDataStore/OceanDataStore/data/HadISST/"
+        }
+    cluster_kwargs = {
+            "n_workers" : 15,
+            "threads_per_worker" : 1,
+            "memory_limit":"3GB"
+        }
+    
+    # Optimise chunk sizes for spatial analysis:
+    ds = ds.chunk({'time': 30, 'latitude': 180, 'longitude': 360})
+
+    # Update variable encodings:
+    blosccodec = zarr.codecs.BloscCodec(cname="zstd", clevel=3, shuffle=zarr.codecs.BloscShuffle.shuffle)
+    for var in list(ds.data_vars) + list(ds.coords):
+        ds[var].encoding['compressors'] = [blosccodec]
+
+    send_to_icechunk(
+        file=ds,
+        bucket=bucket,
+        object_prefix=prefix,
+        store_credentials_json=store_credentials_json,
+        exists=exists,
+        append_dim='time',
+        branch=branch,
+        commit_message=commit_message,
+        variable_commits=variable_commits,
+        dask_config_kwargs=config_kwargs,
+        dask_cluster_kwargs=cluster_kwargs,
+        )
+
+if __name__ == "__main__":
+    main()

OceanDataStore/data/NSIDC/download_NSIDC_monthly_1979_2025_data.sh

@@ -0,0 +1,54 @@
+#!/bin/bash
+
+# ----------------------------------------------------------------
+# download_NSIDC_monthly_1979_2025_data.sh
+#
+# Description: Download the National Snow & Ice Data Centre (NSIDC)
+# Sea Ice Index version 4 sea ice extent & concentration GeoTiff
+# files from 1979 to 2025.
+#
+# Created By: Ollie Tooth (oliver.tooth@noc.ac.uk)
+# Created On: 2026-05-27
+# ----------------------------------------------------------------
+set -euo pipefail
+
+# --- Inputs --- #
+# Define hemisphere to download data for (options: "north" or "south"):
+hemisphere="north"
+
+# Define output directory for downloaded files:
+output_dir="/dssgfs01/scratch/otooth/npd_data/observations/NSIDC/"$hemisphere"/"
+
+# Single year download:
+single_year=True
+# Define year to download if single_year is True:
+year=2025
+
+# -- Defaults -- #
+# Default URL prefix:
+url_prefix="https://noaadata.apps.nsidc.org/NOAA/G02135/"$hemisphere"/monthly/geotiff"
+
+# -- Main Script -- #
+echo "==================================================="
+echo "          Downloading NSIDC Sea Ice Index"
+echo "                     v4.0"
+echo "               Oliver J. Tooth, NOC"
+echo "==================================================="
+echo "In Progress: Downloading NSIDC Sea Ice Index dataset..."
+
+mkdir -p $output_dir
+cd $output_dir
+
+# Download monthly sea ice extent & concentration files from 1979 to 2025:
+for month in 01_Jan 02_Feb 03_Mar 04_Apr 05_May 06_Jun 07_Jul 08_Aug 09_Sep 10_Oct 11_Nov 12_Dec
+do 
+    if [ "$single_year" = True ]; then
+        echo "Downloading NSIDC $year Sea Ice Conc. GeoTiffs for: $month"
+        wget -r -nd --no-check-certificate --reject "index.html*" -np -e robots=off $url_prefix/$month/ -A "*_${year}*_v4.0.tif"
+    else
+        echo "Downloading NSIDC 1979-2025 Sea Ice Conc. GeoTiffs for: $month"
+        wget -r -nd --no-check-certificate --reject "index.html*" -np -e robots=off $url_prefix/$month/
+    fi
+done
+
+echo "-> Completed: Downloaded NSIDC" $hemisphere "Sea Ice Extent & Concentration GeoTiffs"