OceanDataStore 0.3.0__py3-none-any.whl

OceanDataStore/data/EN.4.2.2/send_EN4.2.2_analysis_g10_monthly_to_os.py

@@ -0,0 +1,165 @@
+# =========================================================
+# send_EN4.2.2_analyses_g10_to_os.py
+#
+# Script to write EN.4.2.2 analyses to Icechunk repository
+# 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, 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 EN.4.2.2 analyses dataset:
+    filepath = "/dssgfs01/scratch/otooth/npd_data/observations/EN.4.2.2/EN.4.2.2.f.analysis.g10.19*.nc"
+    ds = xr.open_mfdataset(filepath, combine="by_coords", data_vars="all", engine="netcdf4")
+
+    # Standardise coordinate dimension names:
+    ds = ds.rename({"lon": "longitude", "lat": "latitude"})
+
+    # Update longitude coordinates to be in the range [-180, 180]:
+    ds = ds.assign_coords(
+        longitude=((ds["longitude"] + 180) % 360) - 180
+    )
+    ds = ds.sortby("longitude")
+
+    # Rename variables to standard names:
+    ds = ds.rename({"temperature": "thetao",
+                    "salinity": "so",
+                    "temperature_uncertainty": "thetao_uncertainty",
+                    "salinity_uncertainty": "so_uncertainty",
+                    "temperature_observation_weights": "thetao_obs_weights",
+                    "salinity_observation_weights": "so_obs_weights"
+                    })
+    
+    # Update variable attributes:
+    ds["thetao"].attrs.update({
+        "long_name": "Potential Temperature",
+    })
+    ds["so"].attrs.update({
+        "long_name": "Practical Salinity",
+    })
+    ds["thetao_uncertainty"].attrs.update({
+        "long_name": "Potential Temperature Error Standard Deviation",
+    })
+    ds["so_uncertainty"].attrs.update({
+        "long_name": "Practical Salinity Error Standard Deviation",
+    })
+    ds["thetao_obs_weights"].attrs.update({
+        "long_name": "Potential Temperature Observation Weights",
+    })
+    ds["so_obs_weights"].attrs.update({
+        "long_name": "Practical Salinity Observation Weights",
+    })
+
+    # Update global attributes:
+    ds.attrs.clear()
+
+    ds = ds.assign_attrs({
+        "Conventions": "CF-1.0",
+        "title": "EN.4.2.2 ocean temperature and salinity monthly timeseries.",
+        "description": "EN.4.2.2 quality controlled ocean temperature and salinity monthly timeseries from objective analyses with uncertainty estimates using Gouretski and Reseghetti (2010) corrections.",
+        "source": "Numerical models: Objective Analysis. In-situ observations: Argo, Arctic Synoptic Basin-wide Oceanography (ASBO) project, Global Temperature and Salinity Profile Programme (GTSPP), and World Ocean Database 2018 (WOD18).",
+        "dataset_type": "observation",
+        "product_type": "timeseries",
+        "product_version": "1.0",
+        "institution": "Met Office, UK",
+        "citation": "Good, S. A., Martin, M. J., and Rayner, N. A., 2013. EN4: quality controlled ocean temperature and salinity profiles and monthly objective analyses with uncertainty estimates, Journal of Geophysical Research: Oceans, 118, 6704-6716, doi:10.1002/2013JC009067.",
+        "references": "Gouretski, V., and Reseghetti, F., 2010: On depth and temperature biases in bathythermograph data: development of a new correction scheme based on analysis of a global ocean database. Deep-Sea Research I, 57, 6. doi:10.1016/j.dsr.2010.03.011.",
+        "acknowledgement": "None",
+        "license": "EN.4.2.2 data were obtained from https://www.metoffice.gov.uk/hadobs/en4/ 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",
+        "vertical_grid_type": "z",
+        "vertical_grid_coordinate": "depth",
+        "vertical_grid_levels": 42,
+        "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['thetao'].isel(time=0, depth=0))
+    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(bnds=1) - ds['depth_bnds'].isel(bnds=0)).isel(time=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",
+    })
+
+    # ========== Send to Icechunk Repository ========== #
+    bucket = "en4.2.2"
+    prefix = "en4.2.2_analysis_g10_monthly"
+    exists = False
+    store_credentials_json = ".../credentials/jasmin_os_credentials.json"
+    branch = "main"
+    commit_message = "Added EN.4.2.2.analysis.g10 monthly (1950-01-1999-12)."
+    variable_commits = True
+    config_kwargs = {
+            "temporary_directory":".../OceanDataStore/OceanDataStore/data/EN.4.2.2/",
+            "local_directory":".../OceanDataStore/OceanDataStore/data/EN.4.2.2/"
+        }
+    cluster_kwargs = {
+            "n_workers" : 25,
+            "threads_per_worker" : 1,
+            "memory_limit":"3GB"
+        }
+    
+    # Optimise chunk sizes for spatial analysis:
+    ds = ds.chunk({'time': 1, 'depth': 20, 'latitude': 173, '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/EN.4.2.2/update_EN4.2.2_analysis_g10_monthly_to_os.py

@@ -0,0 +1,161 @@
+# =========================================================
+# update_EN4.2.2_analyses_g10_to_os.py
+#
+# Script to update EN.4.2.2 analyses in Icechunk repository
+# 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,
+    compute_land_sea_mask,
+)
+
+logger = logging.getLogger(__name__)
+
+
+def main():
+    # ========== Initialise OceanDataStore Logging ========== #
+    initialise_logging()
+
+    # ========== Prepare Data ========== #
+    # Open EN.4.2.2 analyses dataset:
+    filepath = "/dssgfs01/scratch/otooth/npd_data/observations/EN.4.2.2/EN.4.2.2.f.analysis.g10.20*.nc"
+    ds = xr.open_mfdataset(filepath, combine="by_coords", data_vars="all", engine="netcdf4")
+
+    # Standardise coordinate dimension names:
+    ds = ds.rename({"lon": "longitude", "lat": "latitude"})
+
+    # Update longitude coordinates to be in the range [-180, 180]:
+    ds = ds.assign_coords(
+        longitude=((ds["longitude"] + 180) % 360) - 180
+    )
+    ds = ds.sortby("longitude")
+
+    # Rename variables to standard names:
+    ds = ds.rename({"temperature": "thetao",
+                    "salinity": "so",
+                    "temperature_uncertainty": "thetao_uncertainty",
+                    "salinity_uncertainty": "so_uncertainty",
+                    "temperature_observation_weights": "thetao_obs_weights",
+                    "salinity_observation_weights": "so_obs_weights"
+                    })
+    
+    # Update variable attributes:
+    ds["thetao"].attrs.update({
+        "long_name": "Potential Temperature",
+    })
+    ds["so"].attrs.update({
+        "long_name": "Practical Salinity",
+    })
+    ds["thetao_uncertainty"].attrs.update({
+        "long_name": "Potential Temperature Error Standard Deviation",
+    })
+    ds["so_uncertainty"].attrs.update({
+        "long_name": "Practical Salinity Error Standard Deviation",
+    })
+    ds["thetao_obs_weights"].attrs.update({
+        "long_name": "Potential Temperature Observation Weights",
+    })
+    ds["so_obs_weights"].attrs.update({
+        "long_name": "Practical Salinity Observation Weights",
+    })
+
+    # Update global attributes:
+    ds.attrs.clear()
+
+    ds = ds.assign_attrs({
+        "Conventions": "CF-1.0",
+        "title": "EN.4.2.2 ocean temperature and salinity monthly timeseries.",
+        "description": "EN.4.2.2 quality controlled ocean temperature and salinity monthly timeseries from objective analyses with uncertainty estimates using Gouretski and Reseghetti (2010) corrections.",
+        "source": "Numerical models: Objective Analysis. In-situ observations: Argo, Arctic Synoptic Basin-wide Oceanography (ASBO) project, Global Temperature and Salinity Profile Programme (GTSPP), and World Ocean Database 2018 (WOD18).",
+        "dataset_type": "observation",
+        "product_type": "timeseries",
+        "product_version": "1.0",
+        "institution": "Met Office, UK",
+        "citation": "Good, S. A., Martin, M. J., and Rayner, N. A., 2013. EN4: quality controlled ocean temperature and salinity profiles and monthly objective analyses with uncertainty estimates, Journal of Geophysical Research: Oceans, 118, 6704-6716, doi:10.1002/2013JC009067.",
+        "references": "Gouretski, V., and Reseghetti, F., 2010: On depth and temperature biases in bathythermograph data: development of a new correction scheme based on analysis of a global ocean database. Deep-Sea Research I, 57, 6. doi:10.1016/j.dsr.2010.03.011.",
+        "acknowledgement": "None",
+        "license": "EN.4.2.2 data were obtained from https://www.metoffice.gov.uk/hadobs/en4/ 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",
+        "vertical_grid_type": "z",
+        "vertical_grid_coordinate": "depth",
+        "vertical_grid_levels": 42,
+        "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['thetao'].isel(time=0, depth=0))
+    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(bnds=1) - ds['depth_bnds'].isel(bnds=0)).isel(time=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",
+    })
+
+    # ========== Send to Icechunk Repository ========== #
+    bucket = "en4.2.2"
+    prefix = "en4.2.2_analysis_g10_monthly"
+    store_credentials_json = ".../credentials/jasmin_os_credentials.json"
+    branch = "main"
+    commit_message = "Added EN.4.2.2.analysis.g10 monthly (2000-01-2026-03)."
+    config_kwargs = {
+            "temporary_directory":".../OceanDataStore/OceanDataStore/data/EN.4.2.2/",
+            "local_directory":".../OceanDataStore/OceanDataStore/data/EN.4.2.2/"
+        }
+    cluster_kwargs = {
+            "n_workers" : 25,
+            "threads_per_worker" : 1,
+            "memory_limit":"3GB"
+        }
+    
+    # Optimise chunk sizes for spatial analysis:
+    ds = ds.chunk({'time': 1, 'depth': 20, 'latitude': 173, '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]
+
+    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/create_ERA5_daily_climatology.py

@@ -0,0 +1,110 @@
+# =========================================================
+# create_ERA5_daily_climatology.py
+#
+# Script to calculate daily mean, minimum, maximum, and
+# variance for ERA5 sea surface temperature data.
+#
+# Created By: Adam Blaker (atb299@noc.ac.uk)
+# =========================================================
+import numpy as np
+import xarray as xr
+import glob
+import argparse
+import re
+from dask.distributed import Client
+
+def extract_year(filename):
+    """Extract year from filename like sst_y2011m07.nc"""
+    match = re.search(r"y(\d{4})m\d{2}", filename)
+    return int(match.group(1)) if match else None
+
+def preprocess(ds):
+    if "valid_time" in ds.dims:
+        ds = ds.rename({"valid_time": "time"})
+    return ds
+
+def main(start_year, end_year, data_path="./", output="sst_climatology.nc"):
+
+    client = Client(n_workers=16, threads_per_worker=1)
+    print(client, flush=True)
+
+    # Find all SST files
+    files = sorted(glob.glob(f"{data_path}/sst_y????m??_daily.nc"))
+
+    # print("Files: ", files)
+
+    # Filter files by year
+    selected_files = [
+        f for f in files
+        if extract_year(f) is not None and start_year <= extract_year(f) <= end_year
+    ]
+
+    if not selected_files:
+        raise ValueError("No files found in the specified year range.")
+
+    print(f"Using {len(selected_files)} files from {start_year} to {end_year}")
+
+    # Open multiple files
+    ds = xr.open_mfdataset(selected_files, preprocess=preprocess, combine="by_coords", parallel=True, chunks={"time": 31, "latitude": 721, "longitude": 360})
+    # print("New chunks:", ds["sst"].chunks, flush=True)
+
+    ds = ds.chunk({
+        "time": -1,
+        "latitude": 100,
+        "longitude": 100
+    })
+
+    # Compute daily climatology (day of year)
+    g_sst = ds["sst"].groupby("time.dayofyear")   # Group once for readability
+
+    mean = g_sst.mean("time")
+    mean = mean.persist()
+
+    var = g_sst.var("time")
+    var = var.persist()
+
+    p10 = g_sst.quantile(0.10, dim="time")
+    p10 = p10.persist()
+
+    p90 = g_sst.quantile(0.90, dim="time")
+    p90 = p90.persist()
+
+    minimum = g_sst.min("time")
+    minimum = minimum.persist()
+
+    maximum = g_sst.max("time")
+    maximum = maximum.persist()
+
+    # Build output dataset
+    clim = xr.Dataset()
+    
+    clim["sst_mean"]        = mean
+    clim["sst_variance"]    = var
+    clim["sst_p10"]         = p10.astype(np.float32)
+    clim["sst_p90"]         = p90.astype(np.float32)
+    clim["sst_minimum"]     = minimum
+    clim["sst_maximum"]     = maximum
+
+
+    clim = clim.chunk({
+        "dayofyear": 30,
+        "latitude": 721,
+        "longitude": 1440
+    })
+
+    # Save output
+    clim.to_netcdf(output)
+
+    print(f"Climatology saved to {output}")
+
+
+if __name__ == "__main__":
+    parser = argparse.ArgumentParser(description="Compute SST daily climatology")
+    parser.add_argument("start_year", type=int, help="Start year (e.g. 2000)")
+    parser.add_argument("end_year", type=int, help="End year (e.g. 2010)")
+    parser.add_argument("--data_path", default=".", help="Directory containing SST files")
+    parser.add_argument("--output", default="sst_climatology.nc", help="Output file")
+
+    args = parser.parse_args()
+
+    main(args.start_year, args.end_year, args.data_path, args.output)

OceanDataStore/data/ERA5/create_ERA5_daily_mean.py

@@ -0,0 +1,69 @@
+# =========================================================
+# create_ERA5_daily_mean.py
+#
+# Script to calculate daily mean, minimum, maximum, and
+# variance for ERA5 sea surface temperature data.
+#
+# Created By: Adam Blaker (atb299@noc.ac.uk)
+# =========================================================
+import logging
+import xarray as xr
+import numpy as np
+
+from OceanDataStore.cli import initialise_logging
+
+logger = logging.getLogger(__name__)
+
+
+def main(filepath: str, outpath: str) -> None:
+    # ========== Initialise OceanDataStore Logging ========== #
+    initialise_logging()
+
+    # ========== Calculate Daily Mean, Min, Max, and Variance ========== #
+    logging.info(f"In Progress: Calculating ERA5 SST daily mean, min, max and variance for {year}-{month:02d}...")
+    ds = xr.open_dataset(filepath, chunks={"time": -1, "latitude": -1, "longitude": -1})
+    logging.info(f"Completed: Read ERA5 Hourly SST data from {filepath}.")
+
+    # Experimental: see https://confluence.ecmwf.int/pages/viewpage.action?pageId=173385064
+    if 'expver' in [i for i in ds.dims]:
+        print(f"Dimension 'expver' present in {filepath}")
+        ds = ds.reduce(np.nansum,dim='expver')
+
+    # Catch and rename the time dimension for consistency
+    if "valid_time" in ds.dims:
+        ds = ds.rename({"valid_time": "time"})
+
+    ds2 = ds.resample(time='1D').mean()
+
+    for var in ds.data_vars:
+        ds2[var+'_min'] = ds[var].resample(time='1D').min()
+        ds2[var+'_max'] = ds[var].resample(time='1D').max()
+        ds2[var+'_var'] = ds[var].resample(time='1D').var()
+
+    vv = [i for i in ds2.data_vars]
+    z_chunks={vv[0]: {'chunksizes': (1, 24, 24), "zlib": True, "complevel": 1},
+            vv[1]: {'chunksizes': (1, 24, 24), "zlib": True, "complevel": 1},
+            vv[2]: {'chunksizes': (1, 24, 24), "zlib": True, "complevel": 1},
+            vv[3]: {'chunksizes': (1, 24, 24), "zlib": True, "complevel": 1}
+    }
+
+    logging.info(f"In Progress: Writing ERA5 Daily SST data to {outpath}...")
+    ds2.to_netcdf(outpath, encoding=z_chunks)
+    logging.info(f"Completed: ERA5 Daily SST data saved to {outpath}.")
+
+
+if __name__ == "__main__":
+    # ====== Inputs ====== #
+    # Define year and month:
+    year = 2026
+    month = 6
+
+    # Define ERA5[T] source - [original, original_latest]:
+    source = "original_latest"
+
+    # Define path to hourly ERA5 SST data and output path for daily mean, min, max, and variance:
+    filepath = f"/dssgfs01/scratch/npd/forcing/ERA5/{source}/{year}/sea_surface_temperature/sea_surface_temperature_{year}-{month:02d}.nc"
+    outpath = f"/dssgfs01/scratch/otooth/npd_data/observations/ERA5/daily/sst_y{year}m{month:02d}_daily.nc"
+
+    # ====== Calculate ERA5 Daily Mean ====== #
+    main(filepath, outpath)

OceanDataStore/data/ERA5/create_ERA5_monthly_mean.py

@@ -0,0 +1,74 @@
+# =========================================================
+# create_ERA5_monthly_mean.py
+#
+# Script to calculate monthly mean, minimum, maximum, and
+# variance for ERA5 sea surface temperature data.
+#
+# Created By: Adam Blaker (atb299@noc.ac.uk)
+# =========================================================
+import logging
+import xarray as xr
+import numpy as np
+
+from OceanDataStore.cli import initialise_logging
+
+logger = logging.getLogger(__name__)
+
+
+def main(filepath: str, outpath: str, var_out: str) -> None:
+    # ========== Initialise OceanDataStore Logging ========== #
+    initialise_logging()
+
+    # ========== Calculate Monthly Mean, Min, Max, and Variance ========== #
+    logging.info(f"In Progress: Calculating ERA5 {var_out} monthly mean, min, max and variance for {year}-{month:02d}...")
+    ds = xr.open_dataset(filepath, chunks={"time": -1, "latitude": -1, "longitude": -1})
+    logging.info(f"Completed: Read ERA5 Hourly {var_out} data from {filepath}.")
+
+    # Experimental: see https://confluence.ecmwf.int/pages/viewpage.action?pageId=173385064
+    if 'expver' in [i for i in ds.dims]:
+        print(f"Dimension 'expver' present in {filepath}")
+        ds = ds.reduce(np.nansum,dim='expver')
+
+    # Catch and rename the time dimension for consistency
+    if "valid_time" in ds.dims:
+        ds = ds.rename({"valid_time": "time"})
+
+    ds2 = ds.resample(time='1ME').mean()
+
+    for var in ds.data_vars:
+        ds2[var+'_min'] = ds[var].resample(time='1ME').min()
+        ds2[var+'_max'] = ds[var].resample(time='1ME').max()
+        ds2[var+'_var'] = ds[var].resample(time='1ME').var()
+
+    vv = [i for i in ds2.data_vars]
+    z_chunks={vv[0]: {'chunksizes': (1, 24, 24), "zlib": True, "complevel": 1},
+              vv[1]: {'chunksizes': (1, 24, 24), "zlib": True, "complevel": 1},
+              vv[2]: {'chunksizes': (1, 24, 24), "zlib": True, "complevel": 1},
+              vv[3]: {'chunksizes': (1, 24, 24), "zlib": True, "complevel": 1}
+    }
+
+    logging.info(f"In Progress: Writing ERA5 Monthly {var_out} data to {outpath}...")
+    ds2.to_netcdf(outpath, encoding=z_chunks)
+    logging.info(f"Completed: ERA5 Monthly {var_out} data saved to {outpath}.")
+
+
+if __name__ == "__main__":
+    # ====== Inputs ====== #
+    # Define year and month:
+    year = 2026
+    month = 5
+
+    # Define ERA5 variable:
+    var_in = "sea_ice_cover"
+    var_out = "siconc"
+
+    # Define ERA5[T] source - [original, original_latest]:
+    # source = "original"
+    source = "original_latest"
+
+    # Define path to hourly ERA5 SST data and output path for monthly mean, min, max, and variance:
+    filepath = f"/dssgfs01/scratch/npd/forcing/ERA5/{source}/{year}/{var_in}/{var_in}_{year}-{month:02d}.nc"
+    outpath = f"/dssgfs01/scratch/otooth/npd_data/observations/ERA5/monthly/{var_out}_y{year}m{month:02d}_monthly.nc"
+
+    # ====== Calculate ERA5 Monthly Mean ====== #
+    main(filepath, outpath, var_out)

OceanDataStore/data/ERA5/run_create_ERA5_daily_climatology.slurm

@@ -0,0 +1,54 @@
+#!/bin/bash
+#SBATCH --job-name=era5_daily_climatology
+#SBATCH --time=12:00:00
+#SBATCH --partition=compute
+#SBATCH --nodes=1
+#SBATCH --mem=0
+#SBATCH --exclusive
+##SBATCH --mem-per-cpu=4G
+##SBATCH --ntasks-per-node=64
+##SBATCH --ntasks-per-socket=32
+##SBATCH --ntasks-per-core=1
+
+module load NEMO/prg-env
+#============================
+export I_MPI_SHM=icx
+
+source /dssgfs01/working/atb299/miniforge3/bin/activate
+conda activate Sci
+
+# ==============================================================
+# run_create_ERA5_daily_climatology.slurm
+#
+# Description: SLURM script to create the ERA5 daily 
+# climatology datasets.
+#
+# Created By: Adam Blaker (atb299@noc.ac.uk)
+# Created On: 2026-06-25
+#
+# ==============================================================
+
+#============================
+TIME1=`date +%s`
+
+dpath="/dssgfs01/scratch/atb299/ERA5_daily/ERA5_daily_fields/"
+
+Ystart=1996
+Yend=$((Ystart+29))
+
+ofile="/dssgfs01/scratch/otooth/npd_data/observations/ERA5/climatology/ERA5_sst_climatology_${Ystart}-${Yend}.nc"
+
+echo "Start year  : " $Ystart
+echo "End year    : " $Yend
+echo "Output file : " $ofile
+
+python create_ERA5_daily_climatology.py $Ystart $Yend --data_path $dpath --output $ofile
+
+#============================
+# Job timing
+
+TIME2=`date +%s`
+DIFFSEC=`expr ${TIME2} - ${TIME1}`
+echo Took ${DIFFSEC} seconds.
+echo Took `date +%H:%M:%S -ud @${DIFFSEC}`
+

OceanDataStore/data/ERA5/run_send_ERA5_daily_climatology_to_os.slurm

@@ -0,0 +1,32 @@
+#!/bin/bash
+#SBATCH --job-name=era5_daily_climatology
+#SBATCH --partition=compute
+#SBATCH --time=02:00:00
+#SBATCH --ntasks-per-core=1
+#SBATCH --ntasks-per-node=64
+#SBATCH --ntasks-per-socket=32
+#SBATCH --nodes=1
+
+# ==============================================================
+# run_send_ERA5_daily_climatology_to_os.slurm
+#
+# Description: SLURM script to send the ERA5 daily 
+# climatology datasets to Icechunk repository.
+#
+# Created By: Ollie Tooth (oliver.tooth@noc.ac.uk)
+# Created On: 2026-06-25
+#
+# ==============================================================
+set -euo pipefail
+
+# -- Python Environment -- #
+# Activate miniconda environment:
+source /dssgfs01/working/otooth/miniforge3/bin/activate
+conda activate env_ods
+
+# -- Send ERA5 daily climatology datasets to JASMIN OS -- #
+echo "In Progress: Sending ERA5 daily climatology to Icechunk..."
+
+python3 send_ERA5_daily_climatology_to_os.py
+
+echo "Completed: Sent ERA5 daily climatology to Icechunk."