OceanDataStore 0.3.0__py3-none-any.whl

OceanDataStore/data/OSTIA/update_OSTIA_copernicus_nrt_daily_to_os.py

@@ -0,0 +1,144 @@
+# =========================================================
+# update_OSTIA_daily_to_os.py
+#
+# Script to write OSTIA daily data to Icechunk repositories
+# in JASMIN cloud object storage.
+#
+# Created By: Ollie Tooth (oliver.tooth@noc.ac.uk)
+# =========================================================
+import logging
+
+import copernicusmarine
+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,
+)
+
+logger = logging.getLogger(__name__)
+
+
+def main():
+    # ========== Initialise OceanDataStore Logging ========== #
+    initialise_logging()
+
+    # ========== Send to Icechunk Repository ========== #
+    bucket = "ostia"
+    store_credentials_json = ".../credentials/jasmin_os_credentials.json"
+    branch = "main"
+    
+    logging.info("In Progress: Sending OSTIA daily data to Icechunk...")
+    # Open OSTIA dataset:
+    ds = copernicusmarine.open_dataset(
+        dataset_id="METOFFICE-GLO-SST-L4-NRT-OBS-SST-V2",
+        variables=["analysed_sst", "analysis_error", "mask", "sea_ice_fraction"],
+        start_datetime="2026-06-27T00:00:00",
+        end_datetime="2026-06-29T23:59:59",
+        minimum_longitude=-45,
+        maximum_longitude=14,
+        minimum_latitude=31,
+        maximum_latitude=85,
+    )
+
+    # Update variable units and attributes:
+    for var in ds.data_vars:
+        if "sst" in var:
+            # Transform units degK -> degC:
+            ds[var] = ds[var] - 273.15
+            ds[var].attrs["units"] = "degC"
+
+    # Rename variables:
+    ds = ds.rename({"analysed_sst": "tos",
+                    "analysis_error": "tos_error",
+                    "sea_ice_fraction": "siconc",
+                    })
+
+    # Update variable long names:
+    ds["tos"].attrs["long_name"] = "Daily Mean Sea Surface Temperature"
+    ds["tos_error"].attrs["long_name"] = "Daily Standard Deviation Error Sea Surface Temperature"
+    ds["siconc"].attrs["long_name"] = "Daily Sea Ice Area Fraction"
+
+    # Add climatological day coordinate:
+    doy = ds['time'].dt.dayofyear
+    is_leap = ds['time'].dt.is_leap_year
+    after_feb28 = (~is_leap) & (doy >= 60)
+    clim_day = xr.where(after_feb28, doy + 1, doy)
+    ds = ds.assign_coords(clim_day=("time", clim_day.data))
+    ds["clim_day"].attrs["long_name"] = "Climatological Day of Year"
+    ds["clim_day"].attrs["description"] = "Climatological calendar day of year (1-366) with leap-year alignment for daily climatology calculations."
+
+    # Add ancillary variables:
+    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-1.4",
+        "title": "OSTIA Near-Real-Time North Atlantic Daily Timeseries",
+        "description": "The Operational Sea Surface Temperature and Ice Analysis (OSTIA) Near-Real-Time - North Atlantic Sea Surface Temperature & Sea Ice Area Fraction Daily Timeseries.",
+        "source": "Satellite observations: GCOM-W, AQUA, GOES<13,16>, MetoSat<08,09,10,11>, Sentinel-<3a,3b>, ERS<1,2>, Envisat, NOAA-<07,08,09,11,12,14,15,16,17,18,19,MTA>, GPM-Core, Suomi-NPP, NOAA-20.",
+        "dataset_type": "observation",
+        "product_type": "timeseries",
+        "product_version": "3.2",
+        "institution": "Met Office, UK",
+        "citation": "Ocean OSTIA Sea Surface Temperature and Sea Ice Analysis. E.U. Copernicus Marine Service Information (CMEMS). Marine Data Store (MDS). DOI: 10.48670/moi-00165 (Accessed on 27 06 2026).",
+        "references": "Good, S.; Fiedler, E.; Mao, C.; Martin, M.J.; Maycock, A.; Reid, R.; Roberts-Jones, J.; Searle, T.; Waters, J.; While, J.; Worsfold, M. The Current Configuration of the OSTIA System for Operational Production of Foundation Sea Surface Temperature and Ice Concentration Analyses. Remote Sens. 2020, 12, 720. doi: 10.3390/rs12040720. Donlon, C.J., Martin, M., Stark, J., Roberts-Jones, J., Fiedler, E., and Wimmer, W., 2012, The Operational Sea Surface Temperature and Sea Ice Analysis (OSTIA) system. Remote Sensing of the Environment. doi: 10.1016/j.rse.2010.10.017 2011. John D. Stark, Craig J. Donlon, Matthew J. Martin and Michael E. McCulloch, 2007, OSTIA : An operational, high resolution, real time, global sea surface temperature analysis system., Oceans 07 IEEE Aberdeen, conference proceedings. Marine challenges: coastline to deep sea. Aberdeen, Scotland.IEEE.",
+        "acknowledgement": "Generated using E.U. Copernicus Marine Service Information; https://doi.org/10.48670/moi-00165. These data were provided by GHRSST, Met Office and CMEMS.",
+        "license": "OSTIA data were obtained from https://doi.org/10.48670/moi-00165, and are provided under the Copernicus Marine Environment Monitoring Service Service Level Agreement (SLA) https://marine.copernicus.eu/user-corner/service-commitments-and-licence?pk_vid=42ac3e352be888641780994034c3bb6e",
+        "doi": "10.48670/moi-00165",
+        "platform": "gr",
+        "horizontal_grid_type": "regular rectilinear",
+        "horizontal_grid_resolution": "0.05 degree",
+        "aggregation": "mean",
+        "aggregation_frequency": "daily",
+        "status": "ongoing",
+        "update_frequency": "quarterly",
+        "bbox": "[-44.975, 13.975, 31.025, 84.975]",
+    })
+
+    # Optimise chunk sizes for time-series analysis:
+    # ds = ds.chunk({'time': ds['time'].size, 'latitude': 50, 'longitude': 50})
+    ds = ds.chunk({'time': 1, 'latitude': 1080, 'longitude': 1180})
+
+    # 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.clear()
+        ds[var].encoding['compressors'] = [blosccodec]
+
+    # Define prefix and commit message based on timeseries period:
+    # prefix = "ostia_nrt_na_daily_timeseries"
+    prefix = "ostia_nrt_na_daily_spatial"
+    commit_message = "Added OSTIA Near-Real-Time North Atlantic Daily Timeseries (2026-01-01 - 2026-06-26)."
+
+    # Dask LocalCluster configuration:
+    config_kwargs = {
+            "temporary_directory":"/dssgfs01/working/otooth/Software/OceanDataStore/OceanDataStore/data/OSTIA/",
+            "local_directory":"/dssgfs01/working/otooth/Software/OceanDataStore/OceanDataStore/data/OSTIA/"
+        }
+    cluster_kwargs = {
+            "n_workers" : 20,
+            "threads_per_worker" : 1,
+            "memory_limit":"6GB"
+        }
+
+    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/OSTIA/update_OSTIA_nrt_daily_to_os.py

@@ -0,0 +1,137 @@
+# =========================================================
+# update_OSTIA_daily_to_os.py
+#
+# Script to write OSTIA daily data to 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_cell_area,
+    compute_dx,
+    compute_dy,
+)
+
+logger = logging.getLogger(__name__)
+
+
+def main():
+    # ========== Initialise OceanDataStore Logging ========== #
+    initialise_logging()
+
+    # ========== Send to Icechunk Repository ========== #
+    bucket = "ostia"
+    store_credentials_json = ".../credentials/jasmin_os_credentials.json"
+    branch = "main"
+    
+    logging.info("In Progress: Sending OSTIA daily data to Icechunk...")
+    # Open OSTIA dataset:
+    data_path = "/dssgfs01/working/otooth/data/observations/OSTIA"
+    ds = xr.open_dataset(f"{data_path}/ostia_global_sst_daily_NA_nrt_2025_2026.zarr",
+                         engine="zarr",
+                         ).sel(time=slice("2026-01", "2026-06"))
+
+    # Update variable units and attributes:
+    for var in ds.data_vars:
+        if "sst" in var:
+            # Transform units degK -> degC:
+            ds[var] = ds[var] - 273.15
+            ds[var].attrs["units"] = "degC"
+
+    # Rename variables:
+    ds = ds.rename({"analysed_sst": "tos",
+                    "analysis_error": "tos_error",
+                    "sea_ice_fraction": "siconc",
+                    })
+
+    # Update variable long names:
+    ds["tos"].attrs["long_name"] = "Daily Mean Sea Surface Temperature"
+    ds["tos_error"].attrs["long_name"] = "Daily Standard Deviation Error Sea Surface Temperature"
+    ds["siconc"].attrs["long_name"] = "Daily Sea Ice Area Fraction"
+
+    # Add climatological day coordinate:
+    doy = ds['time'].dt.dayofyear
+    is_leap = ds['time'].dt.is_leap_year
+    after_feb28 = (~is_leap) & (doy >= 60)
+    clim_day = xr.where(after_feb28, doy + 1, doy)
+    ds = ds.assign_coords(clim_day=("time", clim_day.data))
+    ds["clim_day"].attrs["long_name"] = "Climatological Day of Year"
+    ds["clim_day"].attrs["description"] = "Climatological calendar day of year (1-366) with leap-year alignment for daily climatology calculations."
+
+    # Add ancillary variables:
+    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-1.4",
+        "title": "OSTIA Near-Real-Time North Atlantic Daily Timeseries",
+        "description": "The Operational Sea Surface Temperature and Ice Analysis (OSTIA) Near-Real-Time - North Atlantic Sea Surface Temperature & Sea Ice Area Fraction Daily Timeseries.",
+        "source": "Satellite observations: GCOM-W, AQUA, GOES<13,16>, MetoSat<08,09,10,11>, Sentinel-<3a,3b>, ERS<1,2>, Envisat, NOAA-<07,08,09,11,12,14,15,16,17,18,19,MTA>, GPM-Core, Suomi-NPP, NOAA-20.",
+        "dataset_type": "observation",
+        "product_type": "timeseries",
+        "product_version": "3.2",
+        "institution": "Met Office, UK",
+        "citation": "Ocean OSTIA Sea Surface Temperature and Sea Ice Analysis. E.U. Copernicus Marine Service Information (CMEMS). Marine Data Store (MDS). DOI: 10.48670/moi-00165 (Accessed on 27 06 2026).",
+        "references": "Good, S.; Fiedler, E.; Mao, C.; Martin, M.J.; Maycock, A.; Reid, R.; Roberts-Jones, J.; Searle, T.; Waters, J.; While, J.; Worsfold, M. The Current Configuration of the OSTIA System for Operational Production of Foundation Sea Surface Temperature and Ice Concentration Analyses. Remote Sens. 2020, 12, 720. doi: 10.3390/rs12040720. Donlon, C.J., Martin, M., Stark, J., Roberts-Jones, J., Fiedler, E., and Wimmer, W., 2012, The Operational Sea Surface Temperature and Sea Ice Analysis (OSTIA) system. Remote Sensing of the Environment. doi: 10.1016/j.rse.2010.10.017 2011. John D. Stark, Craig J. Donlon, Matthew J. Martin and Michael E. McCulloch, 2007, OSTIA : An operational, high resolution, real time, global sea surface temperature analysis system., Oceans 07 IEEE Aberdeen, conference proceedings. Marine challenges: coastline to deep sea. Aberdeen, Scotland.IEEE.",
+        "acknowledgement": "Generated using E.U. Copernicus Marine Service Information; https://doi.org/10.48670/moi-00165. These data were provided by GHRSST, Met Office and CMEMS.",
+        "license": "OSTIA data were obtained from https://doi.org/10.48670/moi-00165, and are provided under the Copernicus Marine Environment Monitoring Service Service Level Agreement (SLA) https://marine.copernicus.eu/user-corner/service-commitments-and-licence?pk_vid=42ac3e352be888641780994034c3bb6e",
+        "doi": "10.48670/moi-00165",
+        "platform": "gr",
+        "horizontal_grid_type": "regular rectilinear",
+        "horizontal_grid_resolution": "0.05 degree",
+        "aggregation": "mean",
+        "aggregation_frequency": "daily",
+        "status": "ongoing",
+        "update_frequency": "quarterly",
+        "bbox": "[-44.975, 13.975, 31.025, 84.975]",
+    })
+
+    # Optimise chunk sizes for time-series analysis:
+    # ds = ds.chunk({'time': ds['time'].size, 'latitude': 50, 'longitude': 50})
+    ds = ds.chunk({'time': 1, 'latitude': 1080, 'longitude': 1180})
+
+    # 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.clear()
+        ds[var].encoding['compressors'] = [blosccodec]
+
+    # Define prefix and commit message based on timeseries period:
+    # prefix = "ostia_nrt_na_daily_timeseries"
+    prefix = "ostia_nrt_na_daily_spatial"
+    commit_message = "Added OSTIA Near-Real-Time North Atlantic Daily Timeseries (2026-01-01 - 2026-06-26)."
+
+    # Dask LocalCluster configuration:
+    config_kwargs = {
+            "temporary_directory":"/dssgfs01/working/otooth/Software/OceanDataStore/OceanDataStore/data/OSTIA/",
+            "local_directory":"/dssgfs01/working/otooth/Software/OceanDataStore/OceanDataStore/data/OSTIA/"
+        }
+    cluster_kwargs = {
+            "n_workers" : 20,
+            "threads_per_worker" : 1,
+            "memory_limit":"6GB"
+        }
+
+    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/WOA23/download_WOA23_climatology.sh

@@ -0,0 +1,41 @@
+#!/bin/bash
+
+# ----------------------------------------------------------------
+# download_WOA23_climatology.sh
+#
+# Description: Download the World Ocean Atlas 2023 30-year climatologies
+# using URLs provided by the National Centers for Environmental Information.
+# WOA23 provides Climate Normals for temperature and salinity at 0.25 degree
+# resolution as 30-year averages for validating models.
+#
+# Created By: Ollie Tooth (oliver.tooth@noc.ac.uk)
+# Created On: 2026-05-27
+# ----------------------------------------------------------------
+set -euo pipefail
+
+echo "==================================================="
+echo "          Downloading WOA23 Climatologies"
+echo "                     v0.1.0"
+echo "               Oliver J. Tooth, NOC"
+echo "==================================================="
+echo "In Progress: Downloading WOA23 Upper 1500m Climatologies..."
+for i in {00..16}; do echo $i; wget https://www.ncei.noaa.gov/data/oceans/woa/WOA23/DATA/temperature/netcdf/decav71A0/0.25/woa23_decav71A0_t${i}_04.nc ; done
+
+for i in {00..16}; do echo $i; wget https://www.ncei.noaa.gov/data/oceans/woa/WOA23/DATA/temperature/netcdf/decav81B0/0.25/woa23_decav81B0_t${i}_04.nc ; done
+
+for i in {00..16}; do echo $i; wget https://www.ncei.noaa.gov/data/oceans/woa/WOA23/DATA/temperature/netcdf/decav91C0/0.25/woa23_decav91C0_t${i}_04.nc ; done
+echo "Completed: Downloaded Upper 1500m WOA23 temperature climatologies"
+
+echo "In Progress: Downloading WOA23 Upper 1500m Salinity Climatologies..."
+for i in {00..16}; do echo $i; wget https://www.ncei.noaa.gov/data/oceans/woa/WOA23/DATA/salinity/netcdf/decav71A0/0.25/woa23_decav71A0_s${i}_04.nc ; done
+
+for i in {00..16}; do echo $i; wget https://www.ncei.noaa.gov/data/oceans/woa/WOA23/DATA/salinity/netcdf/decav81B0/0.25/woa23_decav81B0_s${i}_04.nc ; done
+
+for i in {00..16}; do echo $i; wget https://www.ncei.noaa.gov/data/oceans/woa/WOA23/DATA/salinity/netcdf/decav91C0/0.25/woa23_decav91C0_s${i}_04.nc ; done
+echo "Completed: Downloaded Upper 1500m WOA23 salinity climatologies"
+
+# Winter average of full time period, covering full ocean depth:
+echo "In Progress: Downloading WOA23 Full Depth Climatologies..."
+wget https://www.ncei.noaa.gov/data/oceans/woa/WOA23/DATA/temperature/netcdf/decav/0.25/woa23_decav_t13_04.nc
+wget https://www.ncei.noaa.gov/data/oceans/woa/WOA23/DATA/salinity/netcdf/decav/0.25/woa23_decav_s13_04.nc
+echo "Completed: Downloaded WOA23 Full Depth Climatologies"

OceanDataStore/data/WOA23/run_send_WOA23_annual_climatology_to_os.slurm

@@ -0,0 +1,32 @@
+#!/bin/bash
+#SBATCH --job-name=woa23_annual_climatology
+#SBATCH --partition=compute
+#SBATCH --time=01:00:00
+#SBATCH --ntasks-per-core=1
+#SBATCH --ntasks-per-node=64
+#SBATCH --ntasks-per-socket=32
+#SBATCH --nodes=1
+
+# ==============================================================
+# run_send_WOA23_annual_climatology_to_os.slurm
+#
+# Description: SLURM script to send the WOA23 Annual Climatology
+# datasets to Icechunk repository.
+#
+# Created By: Ollie Tooth (oliver.tooth@noc.ac.uk)
+# Created On: 2026-06-05
+#
+# ==============================================================
+set -euo pipefail
+
+# -- Python Environment -- #
+# Activate miniconda environment:
+source .../miniforge3/bin/activate
+conda activate env_ods
+
+# -- Send WOA23 annual climatology to JASMIN OS -- #
+echo "In Progress: Sending WOA23 Annual Climatologies to Icechunk..."
+
+python3 send_WOA23_annual_climatology_to_os.py
+
+echo "Completed: Sent WOA23 Annual Climatologies to Icechunk."

OceanDataStore/data/WOA23/run_send_WOA23_monthly_climatology_to_os.slurm

@@ -0,0 +1,32 @@
+#!/bin/bash
+#SBATCH --job-name=woa23_monthly_climatology
+#SBATCH --partition=compute
+#SBATCH --time=01:00:00
+#SBATCH --ntasks-per-core=1
+#SBATCH --ntasks-per-node=64
+#SBATCH --ntasks-per-socket=32
+#SBATCH --nodes=1
+
+# ==============================================================
+# run_send_WOA23_monthly_climatology_to_os.slurm
+#
+# Description: SLURM script to send the WOA23 Monthly Climatology
+# datasets to Icechunk repository.
+#
+# Created By: Ollie Tooth (oliver.tooth@noc.ac.uk)
+# Created On: 2026-06-06
+#
+# ==============================================================
+set -euo pipefail
+
+# -- Python Environment -- #
+# Activate miniconda environment:
+source .../miniforge3/bin/activate
+conda activate env_ods
+
+# -- Send WOA23 monthly climatology to JASMIN OS -- #
+echo "In Progress: Sending WOA23 Monthly Climatologies to Icechunk..."
+
+python3 send_WOA23_monthly_climatology_to_os.py
+
+echo "Completed: Sent WOA23 Monthly Climatologies to Icechunk."

OceanDataStore/data/WOA23/send_WOA23_annual_climatology_to_os.py

@@ -0,0 +1,263 @@
+# =========================================================
+# send_WOA23_annual_climatology_to_os.py
+#
+# Script to write WOA23 annual climatologies to Icechunk
+# repository in JASMIN cloud object storage.
+#
+# Created By: Ollie Tooth (oliver.tooth@noc.ac.uk)
+# =========================================================
+import logging
+
+import numpy as np
+import pandas as pd
+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,
+)
+
+logger = logging.getLogger(__name__)
+
+
+def main():
+    # ========== Initialise OceanDataStore Logging ========== #
+    initialise_logging()
+    logging.info("In Progress: Sending WOA23 Annual Climatologies to JASMIN Object Store.")
+
+    # ========== Prepare Data ========== #
+    filedir = "/dssgfs01/scratch/otooth/npd_data/observations/WOA2023"
+    # Define file paths for WOA23 annual climatologies:
+    salinity_paths = [f"{filedir}/woa23_decav71A0_s00_04.nc",
+                      f"{filedir}/woa23_decav81B0_s00_04.nc",
+                      f"{filedir}/woa23_decav91C0_s00_04.nc",
+                      ]
+    temperature_paths = [f"{filedir}/woa23_decav71A0_t00_04.nc",
+                         f"{filedir}/woa23_decav81B0_t00_04.nc",
+                         f"{filedir}/woa23_decav91C0_t00_04.nc"
+                         ]
+
+    # Define year bounds for each WOA23 annual climatology:
+    year_bound_start = [1971, 1981, 1991]
+    year_bound_end = [2000, 2010, 2020]
+
+    for temp_path, sal_path, start_year, end_year in zip(temperature_paths, salinity_paths, year_bound_start, year_bound_end):
+        logging.info(f"-> In Progress: Preparing WOA23 {start_year}-{end_year} annual climatology...")
+        # Open WOA23 annual climatologies dataset:
+        ds_s = xr.open_dataset(sal_path, decode_times=False)
+        ds_t = xr.open_dataset(temp_path, decode_times=False)
+
+        ds = xr.merge([ds_s, ds_t], compat='no_conflicts').squeeze(drop=True)
+        ds['climatology_bounds'].values = np.array([np.datetime64(f'{start_year}-01-01', 'ns'), np.datetime64(f'{end_year}-12-31', 'ns')])
+
+        ds = ds.rename({"lon": "longitude",
+                        "lat": "latitude",
+                        "climatology_bounds": "time_bnds"
+                        })
+
+        # Use OceanDataStore standard variable names:
+        for var in ds.data_vars:
+            if var.startswith("t_"):
+                ds = ds.rename({var: var.replace("t_", "thetao_")})
+            elif var.startswith("s_"):
+                ds = ds.rename({var: var.replace("s_", "so_")})
+
+        # Add ancillary variables:
+        ds['dx'] = compute_dx(ds)
+        ds['dy'] = compute_dy(ds)
+        ds['cell_area'] = compute_cell_area(ds)
+
+        # Custom ancillary variables:
+        ds['cell_thickness'] = ds['depth_bnds'].isel(nbounds=1) - ds['depth_bnds'].isel(nbounds=0)
+        ds['cell_volume'] = ds['cell_thickness'] * ds['cell_area']
+
+        # Update attributes for custom ancillary variables:
+        ds['cell_thickness'].attrs.update({
+            'long_name': "Grid-Cell Thickness",
+            'standard_name': "cell_thickness",
+            'units': "m",
+        })
+        ds['cell_volume'].attrs.update({
+            'long_name': "Grid-Cell Volume",
+            'standard_name': "cell_volume",
+            'units': "m3",
+        })
+        logging.info(f"Completed: Prepared WOA23 {start_year}-{end_year} annual climatology dataset with ancillary variables.")
+
+        # ========== Prepare Ancillary Data ========== #
+        # Open WOA23 land sea mask:
+        df_mask = pd.read_table("/dssgfs01/working/otooth/Software/OceanDataStore/OceanDataStore/data/WOA23/data/landsea_04.msk",
+                                delimiter=',',
+                                header=0
+                                )
+        # Define level of sea floor (i.e. bottom standard level) at each grid cell:
+        ds['bottom_level'] = xr.full_like(ds['cell_area'], fill_value=np.nan).squeeze(drop=True)
+        ds['bottom_level'].data = df_mask['Bottom_Standard_Level'].values.reshape(720, 1440)
+        ds['bottom_level'].name = "bottom_level"
+        ds['bottom_level'].attrs = {"standard_name": "model_level_number_at_sea_floor",
+                            "long_name": "Model Level Number at Sea Floor",
+                            "units": "1"}
+        # Define land sea mask (1 for ocean grid cells, 0 for land grid cells):
+        ds['mask'] = ds['bottom_level'] > 1
+        ds['mask'].name = "land_binary_mask"
+        ds["mask"] = ds["mask"].assign_attrs({'long_name': "Land-Sea Binary Mask",
+                                              "standard_name": "sea_binary_mask",
+                                              "comment": "1 = sea, 0 = land"
+                                              })
+        logging.info("Completed: Prepared land sea mask & bottom level variables.")
+        
+        # Open WOA23 basin mask:
+        df_basin = pd.read_table("/dssgfs01/working/otooth/Software/OceanDataStore/OceanDataStore/data/WOA23/data/basinmask_04.msk",
+                                delimiter=',',
+                                header=0
+                                )
+        # Define basin mask (integer values for each ocean basin, NaN for land grid cells):
+        ds['basin_mask'] = xr.full_like(ds['cell_area'], fill_value=np.nan).squeeze(drop=True)
+        for basin, longitude, latitude in df_basin[["Basin_0m", "Longitude", "Latitude"]].itertuples(index=False):
+            ds['basin_mask'].loc[dict(latitude=latitude, longitude=longitude)] = basin
+
+        ds['basin_mask'].attrs = {
+            "standard_name": "ocean_basin_mask",
+            "long_name": "Ocean Basin Mask",
+            "basin_name": {
+            1: "Atlantic Ocean",
+            2: "Pacific Ocean",
+            3: "Indian Ocean",
+            4: "Mediterranean Sea",
+            5: "Baltic Sea",
+            6: "Black Sea",
+            7: "Red Sea",
+            8: "Persian Gulf",
+            9: "Hudson Bay",
+            10: "Southern Ocean",
+            11: "Arctic Ocean",
+            12: "Sea of Japan",
+            13: "Kara Sea",
+            14: "Sulu Sea",
+            15: "Baffin Bay",
+            16: "East Mediterranean",
+            17: "West Mediterranean",
+            18: "Sea of Okhotsk",
+            19: "Banda Sea",
+            20: "Caribbean Sea",
+            21: "Andaman Basin",
+            22: "North Caribbean",
+            23: "Gulf of Mexico",
+            24: "Beaufort Sea",
+            25: "South China Sea",
+            26: "Barents Sea",
+            27: "Celebes Sea",
+            28: "Aleutian Basin",
+            29: "Fiji Basin",
+            30: "North American Basin",
+            31: "West European Basin",
+            32: "Southeast Indian Basin",
+            33: "Coral Sea",
+            34: "East Indian Basin",
+            35: "Central Indian Basin",
+            36: "Southwest Atlantic Basin",
+            37: "Southeast Atlantic Basin",
+            38: "Southeast Pacific Basin",
+            39: "Guatemala Basin",
+            40: "East Caroline Basin",
+            41: "Marianas Basin",
+            42: "Philippine Sea",
+            43: "Arabian Sea",
+            44: "Chile Basin",
+            45: "Somali Basin",
+            46: "Mascarene Basin",
+            47: "Crozet Basin",
+            48: "Guinea Basin",
+            49: "Brazil Basin",
+            50: "Argentine Basin",
+            51: "Tasman Sea",
+            52: "Atlantic Indian Basin",
+            53: "Caspian Sea",
+            54: "Sulu Sea II",
+            55: "Venezuela Basin",
+            56: "Bay of Bengal",
+            57: "Java Sea",
+            58: "East Indian Atlantic Basin",
+            59: "Chiloe",
+            60: "Bransfield Strait",
+            }
+        }
+        logging.info("Completed: Prepared ocean basin mask variable.")
+
+        # ========== CF Attributes ========== #
+        ds.attrs.clear()
+        ds = ds.assign_attrs({
+            "Conventions": "CF-1.6",
+            "title": f"World Ocean Atlas 2023 temperature and salinity annual climatology ({start_year}-{end_year}).",
+            "description": f"World Ocean Atlas 2023 (WOA23) temperature and salinity annual climatology for the global ocean from objectively analysed, quality controlled in-situ profile data ({start_year}-{end_year}).",
+            "source": "Numerical models: Objective Analysis. In-situ observations: World Ocean Database (WOD).",
+            "dataset_type": "observation",
+            "product_type": "climatology",
+            "product_version": "1.0",
+            "institution": "NOAA National Centers for Environmental Information (NCEI)",
+            "citation": "Reagan, James R.; Boyer, Tim P.; García, Hernán E.; Locarnini, Ricardo A.; Baranova, Olga K.; Bouchard, Courtney; Cross, Scott L.; Mishonov, Alexey V.; Paver, Christopher R.; Seidov, Dan; Wang, Zhankun; Dukhovskoy, Dmitry (2023). World Ocean Atlas 2023 (NCEI Accession 0270533). https://www.ncei.noaa.gov/archive/accession/0270533. In Reagan, James R.; Boyer, Tim P.; García, Hernán E.; Locarnini, Ricardo A.; Baranova, Olga K.; Bouchard, Courtney; Cross, Scott L.; Mishonov, Alexey V.; Paver, Christopher R.; Seidov, Dan; Wang, Zhankun; Dukhovskoy, Dmitry (2023). World Ocean Atlas 2023. NOAA National Centers for Environmental Information. Dataset. https://doi.org/10.25921/va26-hv25. Accessed 06-05-2026.",
+            "references": "Locarnini, R.A., A.V. Mishonov, O.K. Baranova, J.R. Reagan, T.P. Boyer, D. Seidov, Z. Wang, H.E. Garcia, C. Bouchard, S.L. Cross, C.R. Paver, and D. Dukhovskoy (2024). World Ocean Atlas 2023, Volume 1: Temperature. A. Mishonov Technical Editor, NOAA Atlas NESDIS 89. https://doi.org/10.25923/54bh-1613. Reagan, J.R., D. Seidov, Z. Wang, D. Dukhovskoy, T.P. Boyer, R.A. Locarnini, O.K. Baranova, A.V. Mishonov, H.E. Garcia, C. Bouchard, S.L. Cross, and C.R. Paver (2023). World Ocean Atlas 2023, Volume 2: Salinity. A. Mishonov Technical Editor, NOAA Atlas NESDIS 90, https://doi.org/10.25923/70qt-9574.",
+            "acknowledgement": "None",
+            "license": "World Ocean Atlas 2023 data were obtained from https://www.ncei.noaa.gov/access/world-ocean-atlas-2023/ and are provided under a Creative Commons CC0 1.0 Universal License https://creativecommons.org/publicdomain/zero/1.0/",
+            "doi": "https://doi.org/10.25921/va26-hv25",
+            "platform": "gr",
+            "horizontal_grid_type": "regular rectilinear",
+            "horizontal_grid_resolution": "0.25 degree",
+            "vertical_grid_type": "z",
+            "vertical_grid_coordinate": "depth",
+            "vertical_grid_levels": 57,
+            "aggregation": "mean",
+            "aggregation_frequency": "annual",
+            "status": "completed",
+            "update_frequency": "None",
+            "bbox": "[-180.0, 180.0, -90.0, 90.0]",
+        })
+        logging.info(f"Completed: Added CF-compliant global attributes to WOA23 {start_year}-{end_year} annual climatology dataset.")
+
+        # ========== Send to Icechunk Repository ========== #
+        logging.info(f"In Progress: Sending WOA23 {start_year}-{end_year} annual climatology to Icechunk Repository...")
+        bucket = "woa23"
+        prefix = f"woa23_{start_year}_{end_year}_annual_climatology"
+        exists = False
+        store_credentials_json = ".../credentials/jasmin_os_credentials.json"
+        branch = "main"
+        commit_message = f"Added WOA23 {start_year}-{end_year} annual climatology."
+        variable_commits = True
+        config_kwargs = {
+                "temporary_directory":".../OceanDataStore/OceanDataStore/data/WOA23/",
+                "local_directory":".../OceanDataStore/OceanDataStore/data/WOA23/"
+            }
+        cluster_kwargs = {
+                "n_workers" : 25,
+                "threads_per_worker" : 1,
+                "memory_limit":"3GB"
+            }
+        
+        # Optimise chunk sizes for spatial analysis:
+        ds = ds.chunk({'longitude': 1440, 'latitude': 720, 'depth': 5})
+    
+        # 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,
+            branch=branch,
+            commit_message=commit_message,
+            variable_commits=variable_commits,
+            dask_config_kwargs=config_kwargs,
+            dask_cluster_kwargs=cluster_kwargs,
+            )
+
+        logging.info(f"Completed: Sent WOA23 {start_year}-{end_year} annual climatology to Icechunk Repository.")
+
+if __name__ == "__main__":
+    main()