load slice of era5 for local use

era5.py

import xarray

variables = [
    'u_component_of_wind',
    'v_component_of_wind',
    'geopotential',
    'temperature',
    # ... full list of variables here: https://console.cloud.google.com/storage/browser/gcp-public-data-arco-era5/ar/1959-2022-full_37-1h-0p25deg-chunk-1.zarr-v2;tab=objects?pli=1&prefix=&forceOnObjectsSortingFiltering=false
]

# Loading ERA5 data from Google Cloud arco project
era5_path = 'gs://gcp-public-data-arco-era5/ar/full_37-1h-0p25deg-chunk-1.zarr-v3'
full_era5_ds = xarray.open_zarr(era5_path, chunks=None)

full_era5_ds = full_era5_ds[variables]

start_time = '2020-02-14'
end_time = '2020-02-18'
data_inner_steps = 12  # process every 12th hour

era5_ds = full_era5_ds.sel(time=slice(start_time, end_time))
era5_ds = era5_ds.thin(time=data_inner_steps)

# here, era5_ds will be much smaller, and you can then materialize it/save it/etc.
era5_ds.to_netcdf(f'{start_time}_{end_time}_era5_slice.nc')

dependencies:

gcsfs
fsspec
xarray
zarr
netcdf4

name: era5
channels:

• defaults
  dependencies:
• python=3.11
• bottleneck
• dask
• netcdf4
• xarray
• zarr