PAT = "your_personal_access_token"

#e.g. PAT="edh_pat_44bbb7e9192a4c6bb47ddf07d07564eee5d17de8dfc48f7118f88e3bc4a4157f8fe2403f5aa0a2d53441b6922ea9a33a"

import xarray as xr

ds = xr.open_dataset(
    f"https://edh:{PAT}@data.earthdatahub.destine.eu/era5/reanalysis-era5-single-levels-v0.zarr",
    chunks={},
    engine="zarr",
)
ds

<xarray.Dataset> Size: 256TB
Dimensions:           (valid_time: 742824, latitude: 721, longitude: 1440)
Coordinates:
    entireAtmosphere  float32 4B ...
  * latitude          (latitude) float64 6kB 90.0 89.75 89.5 ... -89.75 -90.0
  * longitude         (longitude) float64 12kB 0.0 0.25 0.5 ... 359.5 359.8
    number            int64 8B ...
    surface           float64 8B ...
  * valid_time        (valid_time) datetime64[ns] 6MB 1940-01-01 ... 2024-09-...
Data variables: (12/83)
    alnid             (valid_time, latitude, longitude) float32 3TB dask.array<chunksize=(4320, 64, 64), meta=np.ndarray>
    alnip             (valid_time, latitude, longitude) float32 3TB dask.array<chunksize=(4320, 64, 64), meta=np.ndarray>
    aluvd             (valid_time, latitude, longitude) float32 3TB dask.array<chunksize=(4320, 64, 64), meta=np.ndarray>
    aluvp             (valid_time, latitude, longitude) float32 3TB dask.array<chunksize=(4320, 64, 64), meta=np.ndarray>
    blh               (valid_time, latitude, longitude) float32 3TB dask.array<chunksize=(4320, 64, 64), meta=np.ndarray>
    cdir              (valid_time, latitude, longitude) float32 3TB dask.array<chunksize=(4320, 64, 64), meta=np.ndarray>
    ...                ...
    viiwe             (valid_time, latitude, longitude) float32 3TB dask.array<chunksize=(4320, 64, 64), meta=np.ndarray>
    viiwn             (valid_time, latitude, longitude) float32 3TB dask.array<chunksize=(4320, 64, 64), meta=np.ndarray>
    vilwd             (valid_time, latitude, longitude) float32 3TB dask.array<chunksize=(4320, 64, 64), meta=np.ndarray>
    vilwe             (valid_time, latitude, longitude) float32 3TB dask.array<chunksize=(4320, 64, 64), meta=np.ndarray>
    vilwn             (valid_time, latitude, longitude) float32 3TB dask.array<chunksize=(4320, 64, 64), meta=np.ndarray>
    z                 (valid_time, latitude, longitude) float32 3TB dask.array<chunksize=(4320, 64, 64), meta=np.ndarray>
Attributes:
    Conventions:             CF-1.7
    GRIB_centre:             ecmf
    GRIB_centreDescription:  European Centre for Medium-Range Weather Forecasts
    GRIB_edition:            1
    GRIB_subCentre:          0
    history:                 2024-10-02T12:52 GRIB to CDM+CF via cfgrib-0.9.1...
    institution:             European Centre for Medium-Range Weather Forecasts

[1 values with dtype=float32]

array([ 90.  ,  89.75,  89.5 , ..., -89.5 , -89.75, -90.  ])

array([0.0000e+00, 2.5000e-01, 5.0000e-01, ..., 3.5925e+02, 3.5950e+02,
       3.5975e+02])

[1 values with dtype=int64]

[1 values with dtype=float64]

array(['1940-01-01T00:00:00.000000000', '1940-01-01T01:00:00.000000000',
       '1940-01-01T02:00:00.000000000', ..., '2024-09-26T21:00:00.000000000',
       '2024-09-26T22:00:00.000000000', '2024-09-26T23:00:00.000000000'],
      dtype='datetime64[ns]')

PandasIndex(Index([  90.0,  89.75,   89.5,  89.25,   89.0,  88.75,   88.5,  88.25,   88.0,
        87.75,
       ...
       -87.75,  -88.0, -88.25,  -88.5, -88.75,  -89.0, -89.25,  -89.5, -89.75,
        -90.0],
      dtype='float64', name='latitude', length=721))

PandasIndex(Index([   0.0,   0.25,    0.5,   0.75,    1.0,   1.25,    1.5,   1.75,    2.0,
         2.25,
       ...
        357.5, 357.75,  358.0, 358.25,  358.5, 358.75,  359.0, 359.25,  359.5,
       359.75],
      dtype='float64', name='longitude', length=1440))

PandasIndex(DatetimeIndex(['1940-01-01 00:00:00', '1940-01-01 01:00:00',
               '1940-01-01 02:00:00', '1940-01-01 03:00:00',
               '1940-01-01 04:00:00', '1940-01-01 05:00:00',
               '1940-01-01 06:00:00', '1940-01-01 07:00:00',
               '1940-01-01 08:00:00', '1940-01-01 09:00:00',
               ...
               '2024-09-26 14:00:00', '2024-09-26 15:00:00',
               '2024-09-26 16:00:00', '2024-09-26 17:00:00',
               '2024-09-26 18:00:00', '2024-09-26 19:00:00',
               '2024-09-26 20:00:00', '2024-09-26 21:00:00',
               '2024-09-26 22:00:00', '2024-09-26 23:00:00'],
              dtype='datetime64[ns]', name='valid_time', length=742824, freq=None))

xr.set_options(keep_attrs=True)

t2m = ds.t2m.astype("float32") - 273.15
t2m.attrs["units"] = "°C"
t2m_germany= t2m.sel(**{"latitude": slice(55, 47), "longitude": slice(5, 16)})
t2m_germany

<xarray.DataArray 't2m' (valid_time: 742824, latitude: 33, longitude: 45)> Size: 4GB
dask.array<getitem, shape=(742824, 33, 45), dtype=float32, chunksize=(4320, 33, 44), chunktype=numpy.ndarray>
Coordinates:
    entireAtmosphere  float32 4B ...
  * latitude          (latitude) float64 264B 55.0 54.75 54.5 ... 47.25 47.0
  * longitude         (longitude) float64 360B 5.0 5.25 5.5 ... 15.5 15.75 16.0
    number            int64 8B ...
    surface           float64 8B ...
  * valid_time        (valid_time) datetime64[ns] 6MB 1940-01-01 ... 2024-09-...
Attributes: (12/31)
    GRIB_NV:                                  0
    GRIB_Nx:                                  1440
    GRIB_Ny:                                  721
    GRIB_cfName:                              unknown
    GRIB_cfVarName:                           t2m
    GRIB_dataType:                            an
    ...                                       ...
    GRIB_typeOfLevel:                         surface
    GRIB_units:                               K
    last_restart_dim_updated:                 742824
    long_name:                                2 metre temperature
    standard_name:                            unknown
    units:                                    °C

[1 values with dtype=float32]

array([55.  , 54.75, 54.5 , 54.25, 54.  , 53.75, 53.5 , 53.25, 53.  , 52.75,
       52.5 , 52.25, 52.  , 51.75, 51.5 , 51.25, 51.  , 50.75, 50.5 , 50.25,
       50.  , 49.75, 49.5 , 49.25, 49.  , 48.75, 48.5 , 48.25, 48.  , 47.75,
       47.5 , 47.25, 47.  ])

array([ 5.  ,  5.25,  5.5 ,  5.75,  6.  ,  6.25,  6.5 ,  6.75,  7.  ,  7.25,
        7.5 ,  7.75,  8.  ,  8.25,  8.5 ,  8.75,  9.  ,  9.25,  9.5 ,  9.75,
       10.  , 10.25, 10.5 , 10.75, 11.  , 11.25, 11.5 , 11.75, 12.  , 12.25,
       12.5 , 12.75, 13.  , 13.25, 13.5 , 13.75, 14.  , 14.25, 14.5 , 14.75,
       15.  , 15.25, 15.5 , 15.75, 16.  ])

[1 values with dtype=int64]

[1 values with dtype=float64]

array(['1940-01-01T00:00:00.000000000', '1940-01-01T01:00:00.000000000',
       '1940-01-01T02:00:00.000000000', ..., '2024-09-26T21:00:00.000000000',
       '2024-09-26T22:00:00.000000000', '2024-09-26T23:00:00.000000000'],
      dtype='datetime64[ns]')

PandasIndex(Index([ 55.0, 54.75,  54.5, 54.25,  54.0, 53.75,  53.5, 53.25,  53.0, 52.75,
        52.5, 52.25,  52.0, 51.75,  51.5, 51.25,  51.0, 50.75,  50.5, 50.25,
        50.0, 49.75,  49.5, 49.25,  49.0, 48.75,  48.5, 48.25,  48.0, 47.75,
        47.5, 47.25,  47.0],
      dtype='float64', name='latitude'))

PandasIndex(Index([  5.0,  5.25,   5.5,  5.75,   6.0,  6.25,   6.5,  6.75,   7.0,  7.25,
         7.5,  7.75,   8.0,  8.25,   8.5,  8.75,   9.0,  9.25,   9.5,  9.75,
        10.0, 10.25,  10.5, 10.75,  11.0, 11.25,  11.5, 11.75,  12.0, 12.25,
        12.5, 12.75,  13.0, 13.25,  13.5, 13.75,  14.0, 14.25,  14.5, 14.75,
        15.0, 15.25,  15.5, 15.75,  16.0],
      dtype='float64', name='longitude'))

PandasIndex(DatetimeIndex(['1940-01-01 00:00:00', '1940-01-01 01:00:00',
               '1940-01-01 02:00:00', '1940-01-01 03:00:00',
               '1940-01-01 04:00:00', '1940-01-01 05:00:00',
               '1940-01-01 06:00:00', '1940-01-01 07:00:00',
               '1940-01-01 08:00:00', '1940-01-01 09:00:00',
               ...
               '2024-09-26 14:00:00', '2024-09-26 15:00:00',
               '2024-09-26 16:00:00', '2024-09-26 17:00:00',
               '2024-09-26 18:00:00', '2024-09-26 19:00:00',
               '2024-09-26 20:00:00', '2024-09-26 21:00:00',
               '2024-09-26 22:00:00', '2024-09-26 23:00:00'],
              dtype='datetime64[ns]', name='valid_time', length=742824, freq=None))

t2m_germany_october_2023 = t2m_germany.sel(valid_time="2023-10")
t2m_germany_october_2023

<xarray.DataArray 't2m' (valid_time: 744, latitude: 33, longitude: 45)> Size: 4MB
dask.array<getitem, shape=(744, 33, 45), dtype=float32, chunksize=(480, 33, 44), chunktype=numpy.ndarray>
Coordinates:
    entireAtmosphere  float32 4B ...
  * latitude          (latitude) float64 264B 55.0 54.75 54.5 ... 47.25 47.0
  * longitude         (longitude) float64 360B 5.0 5.25 5.5 ... 15.5 15.75 16.0
    number            int64 8B ...
    surface           float64 8B ...
  * valid_time        (valid_time) datetime64[ns] 6kB 2023-10-01 ... 2023-10-...
Attributes: (12/31)
    GRIB_NV:                                  0
    GRIB_Nx:                                  1440
    GRIB_Ny:                                  721
    GRIB_cfName:                              unknown
    GRIB_cfVarName:                           t2m
    GRIB_dataType:                            an
    ...                                       ...
    GRIB_typeOfLevel:                         surface
    GRIB_units:                               K
    last_restart_dim_updated:                 742824
    long_name:                                2 metre temperature
    standard_name:                            unknown
    units:                                    °C

[1 values with dtype=float32]

array([55.  , 54.75, 54.5 , 54.25, 54.  , 53.75, 53.5 , 53.25, 53.  , 52.75,
       52.5 , 52.25, 52.  , 51.75, 51.5 , 51.25, 51.  , 50.75, 50.5 , 50.25,
       50.  , 49.75, 49.5 , 49.25, 49.  , 48.75, 48.5 , 48.25, 48.  , 47.75,
       47.5 , 47.25, 47.  ])

array([ 5.  ,  5.25,  5.5 ,  5.75,  6.  ,  6.25,  6.5 ,  6.75,  7.  ,  7.25,
        7.5 ,  7.75,  8.  ,  8.25,  8.5 ,  8.75,  9.  ,  9.25,  9.5 ,  9.75,
       10.  , 10.25, 10.5 , 10.75, 11.  , 11.25, 11.5 , 11.75, 12.  , 12.25,
       12.5 , 12.75, 13.  , 13.25, 13.5 , 13.75, 14.  , 14.25, 14.5 , 14.75,
       15.  , 15.25, 15.5 , 15.75, 16.  ])

[1 values with dtype=int64]

[1 values with dtype=float64]

array(['2023-10-01T00:00:00.000000000', '2023-10-01T01:00:00.000000000',
       '2023-10-01T02:00:00.000000000', ..., '2023-10-31T21:00:00.000000000',
       '2023-10-31T22:00:00.000000000', '2023-10-31T23:00:00.000000000'],
      dtype='datetime64[ns]')

PandasIndex(Index([ 55.0, 54.75,  54.5, 54.25,  54.0, 53.75,  53.5, 53.25,  53.0, 52.75,
        52.5, 52.25,  52.0, 51.75,  51.5, 51.25,  51.0, 50.75,  50.5, 50.25,
        50.0, 49.75,  49.5, 49.25,  49.0, 48.75,  48.5, 48.25,  48.0, 47.75,
        47.5, 47.25,  47.0],
      dtype='float64', name='latitude'))

PandasIndex(Index([  5.0,  5.25,   5.5,  5.75,   6.0,  6.25,   6.5,  6.75,   7.0,  7.25,
         7.5,  7.75,   8.0,  8.25,   8.5,  8.75,   9.0,  9.25,   9.5,  9.75,
        10.0, 10.25,  10.5, 10.75,  11.0, 11.25,  11.5, 11.75,  12.0, 12.25,
        12.5, 12.75,  13.0, 13.25,  13.5, 13.75,  14.0, 14.25,  14.5, 14.75,
        15.0, 15.25,  15.5, 15.75,  16.0],
      dtype='float64', name='longitude'))

PandasIndex(DatetimeIndex(['2023-10-01 00:00:00', '2023-10-01 01:00:00',
               '2023-10-01 02:00:00', '2023-10-01 03:00:00',
               '2023-10-01 04:00:00', '2023-10-01 05:00:00',
               '2023-10-01 06:00:00', '2023-10-01 07:00:00',
               '2023-10-01 08:00:00', '2023-10-01 09:00:00',
               ...
               '2023-10-31 14:00:00', '2023-10-31 15:00:00',
               '2023-10-31 16:00:00', '2023-10-31 17:00:00',
               '2023-10-31 18:00:00', '2023-10-31 19:00:00',
               '2023-10-31 20:00:00', '2023-10-31 21:00:00',
               '2023-10-31 22:00:00', '2023-10-31 23:00:00'],
              dtype='datetime64[ns]', name='valid_time', length=744, freq=None))

import costing

costing.estimate_download_size(t2m, t2m_germany_october_2023)

estimated_needed_chunks: 4
estimated_memory_size: 0.283 GB
estimated_download_size: 0.028 GB

%%time

t2m_germany_october_2023_computed = t2m_germany_october_2023.compute()

CPU times: user 1.05 s, sys: 691 ms, total: 1.74 s
Wall time: 1.15 s

t2m_germany_october_2023_monthly_mean = t2m_germany_october_2023_computed.mean(dim="valid_time")
t2m_germany_october_2023_monthly_mean

<xarray.DataArray 't2m' (latitude: 33, longitude: 45)> Size: 6kB
array([[13.325453 , 13.389966 , 13.424911 , ..., 12.257616 , 12.284496 ,
        12.304321 ],
       [13.614086 , 13.664152 , 13.679943 , ..., 12.537507 , 12.4921465,
        12.512643 ],
       [13.858366 , 13.903055 , 13.91448  , ..., 12.575477 , 12.505922 ,
        12.191089 ],
       ...,
       [13.5314245, 14.038129 , 14.431263 , ..., 10.0140505, 10.73885  ,
        11.996536 ],
       [14.110707 , 14.629511 , 15.010548 , ..., 11.550653 , 12.272733 ,
        12.732729 ],
       [14.843212 , 15.05759  , 15.260543 , ..., 13.064035 , 13.677259 ,
        13.871476 ]], dtype=float32)
Coordinates:
    entireAtmosphere  float32 4B 0.0
  * latitude          (latitude) float64 264B 55.0 54.75 54.5 ... 47.25 47.0
  * longitude         (longitude) float64 360B 5.0 5.25 5.5 ... 15.5 15.75 16.0
    number            int64 8B 0
    surface           float64 8B 0.0
Attributes: (12/31)
    GRIB_NV:                                  0
    GRIB_Nx:                                  1440
    GRIB_Ny:                                  721
    GRIB_cfName:                              unknown
    GRIB_cfVarName:                           t2m
    GRIB_dataType:                            an
    ...                                       ...
    GRIB_typeOfLevel:                         surface
    GRIB_units:                               K
    last_restart_dim_updated:                 742824
    long_name:                                2 metre temperature
    standard_name:                            unknown
    units:                                    °C

array([[13.325453 , 13.389966 , 13.424911 , ..., 12.257616 , 12.284496 ,
        12.304321 ],
       [13.614086 , 13.664152 , 13.679943 , ..., 12.537507 , 12.4921465,
        12.512643 ],
       [13.858366 , 13.903055 , 13.91448  , ..., 12.575477 , 12.505922 ,
        12.191089 ],
       ...,
       [13.5314245, 14.038129 , 14.431263 , ..., 10.0140505, 10.73885  ,
        11.996536 ],
       [14.110707 , 14.629511 , 15.010548 , ..., 11.550653 , 12.272733 ,
        12.732729 ],
       [14.843212 , 15.05759  , 15.260543 , ..., 13.064035 , 13.677259 ,
        13.871476 ]], dtype=float32)

array(0., dtype=float32)

array([55.  , 54.75, 54.5 , 54.25, 54.  , 53.75, 53.5 , 53.25, 53.  , 52.75,
       52.5 , 52.25, 52.  , 51.75, 51.5 , 51.25, 51.  , 50.75, 50.5 , 50.25,
       50.  , 49.75, 49.5 , 49.25, 49.  , 48.75, 48.5 , 48.25, 48.  , 47.75,
       47.5 , 47.25, 47.  ])

array([ 5.  ,  5.25,  5.5 ,  5.75,  6.  ,  6.25,  6.5 ,  6.75,  7.  ,  7.25,
        7.5 ,  7.75,  8.  ,  8.25,  8.5 ,  8.75,  9.  ,  9.25,  9.5 ,  9.75,
       10.  , 10.25, 10.5 , 10.75, 11.  , 11.25, 11.5 , 11.75, 12.  , 12.25,
       12.5 , 12.75, 13.  , 13.25, 13.5 , 13.75, 14.  , 14.25, 14.5 , 14.75,
       15.  , 15.25, 15.5 , 15.75, 16.  ])

array(0)

array(0.)

PandasIndex(Index([ 55.0, 54.75,  54.5, 54.25,  54.0, 53.75,  53.5, 53.25,  53.0, 52.75,
        52.5, 52.25,  52.0, 51.75,  51.5, 51.25,  51.0, 50.75,  50.5, 50.25,
        50.0, 49.75,  49.5, 49.25,  49.0, 48.75,  48.5, 48.25,  48.0, 47.75,
        47.5, 47.25,  47.0],
      dtype='float64', name='latitude'))

PandasIndex(Index([  5.0,  5.25,   5.5,  5.75,   6.0,  6.25,   6.5,  6.75,   7.0,  7.25,
         7.5,  7.75,   8.0,  8.25,   8.5,  8.75,   9.0,  9.25,   9.5,  9.75,
        10.0, 10.25,  10.5, 10.75,  11.0, 11.25,  11.5, 11.75,  12.0, 12.25,
        12.5, 12.75,  13.0, 13.25,  13.5, 13.75,  14.0, 14.25,  14.5, 14.75,
        15.0, 15.25,  15.5, 15.75,  16.0],
      dtype='float64', name='longitude'))

import display
import matplotlib.pyplot as plt
from cartopy import crs

display.map(
    t2m_germany_october_2023_monthly_mean, 
    projection=crs.Miller(), 
    vmax=None, 
    cmap="YlOrRd", 
    title="Mean Surface Temperature, Oct 2023"
);

t2m_germany_octobers_1991_2020 = t2m_germany.sel(valid_time=t2m_germany["valid_time.month"] == 10).sel(valid_time=slice("1991", "2020"))
t2m_germany_octobers_1991_2020

<xarray.DataArray 't2m' (valid_time: 22320, latitude: 33, longitude: 45)> Size: 133MB
dask.array<getitem, shape=(22320, 33, 45), dtype=float32, chunksize=(4318, 33, 44), chunktype=numpy.ndarray>
Coordinates:
    entireAtmosphere  float32 4B ...
  * latitude          (latitude) float64 264B 55.0 54.75 54.5 ... 47.25 47.0
  * longitude         (longitude) float64 360B 5.0 5.25 5.5 ... 15.5 15.75 16.0
    number            int64 8B ...
    surface           float64 8B ...
  * valid_time        (valid_time) datetime64[ns] 179kB 1991-10-01 ... 2020-1...
Attributes: (12/31)
    GRIB_NV:                                  0
    GRIB_Nx:                                  1440
    GRIB_Ny:                                  721
    GRIB_cfName:                              unknown
    GRIB_cfVarName:                           t2m
    GRIB_dataType:                            an
    ...                                       ...
    GRIB_typeOfLevel:                         surface
    GRIB_units:                               K
    last_restart_dim_updated:                 742824
    long_name:                                2 metre temperature
    standard_name:                            unknown
    units:                                    °C

[1 values with dtype=float32]

array([55.  , 54.75, 54.5 , 54.25, 54.  , 53.75, 53.5 , 53.25, 53.  , 52.75,
       52.5 , 52.25, 52.  , 51.75, 51.5 , 51.25, 51.  , 50.75, 50.5 , 50.25,
       50.  , 49.75, 49.5 , 49.25, 49.  , 48.75, 48.5 , 48.25, 48.  , 47.75,
       47.5 , 47.25, 47.  ])

array([ 5.  ,  5.25,  5.5 ,  5.75,  6.  ,  6.25,  6.5 ,  6.75,  7.  ,  7.25,
        7.5 ,  7.75,  8.  ,  8.25,  8.5 ,  8.75,  9.  ,  9.25,  9.5 ,  9.75,
       10.  , 10.25, 10.5 , 10.75, 11.  , 11.25, 11.5 , 11.75, 12.  , 12.25,
       12.5 , 12.75, 13.  , 13.25, 13.5 , 13.75, 14.  , 14.25, 14.5 , 14.75,
       15.  , 15.25, 15.5 , 15.75, 16.  ])

[1 values with dtype=int64]

[1 values with dtype=float64]

array(['1991-10-01T00:00:00.000000000', '1991-10-01T01:00:00.000000000',
       '1991-10-01T02:00:00.000000000', ..., '2020-10-31T21:00:00.000000000',
       '2020-10-31T22:00:00.000000000', '2020-10-31T23:00:00.000000000'],
      dtype='datetime64[ns]')

PandasIndex(Index([ 55.0, 54.75,  54.5, 54.25,  54.0, 53.75,  53.5, 53.25,  53.0, 52.75,
        52.5, 52.25,  52.0, 51.75,  51.5, 51.25,  51.0, 50.75,  50.5, 50.25,
        50.0, 49.75,  49.5, 49.25,  49.0, 48.75,  48.5, 48.25,  48.0, 47.75,
        47.5, 47.25,  47.0],
      dtype='float64', name='latitude'))

PandasIndex(Index([  5.0,  5.25,   5.5,  5.75,   6.0,  6.25,   6.5,  6.75,   7.0,  7.25,
         7.5,  7.75,   8.0,  8.25,   8.5,  8.75,   9.0,  9.25,   9.5,  9.75,
        10.0, 10.25,  10.5, 10.75,  11.0, 11.25,  11.5, 11.75,  12.0, 12.25,
        12.5, 12.75,  13.0, 13.25,  13.5, 13.75,  14.0, 14.25,  14.5, 14.75,
        15.0, 15.25,  15.5, 15.75,  16.0],
      dtype='float64', name='longitude'))

PandasIndex(DatetimeIndex(['1991-10-01 00:00:00', '1991-10-01 01:00:00',
               '1991-10-01 02:00:00', '1991-10-01 03:00:00',
               '1991-10-01 04:00:00', '1991-10-01 05:00:00',
               '1991-10-01 06:00:00', '1991-10-01 07:00:00',
               '1991-10-01 08:00:00', '1991-10-01 09:00:00',
               ...
               '2020-10-31 14:00:00', '2020-10-31 15:00:00',
               '2020-10-31 16:00:00', '2020-10-31 17:00:00',
               '2020-10-31 18:00:00', '2020-10-31 19:00:00',
               '2020-10-31 20:00:00', '2020-10-31 21:00:00',
               '2020-10-31 22:00:00', '2020-10-31 23:00:00'],
              dtype='datetime64[ns]', name='valid_time', length=22320, freq=None))

import costing

costing.estimate_download_size(t2m, t2m_germany_octobers_1991_2020)

estimated_needed_chunks: 12
estimated_memory_size: 0.849 GB
estimated_download_size: 0.085 GB

%%time

t2m_germany_octobers_1991_2020_computed = t2m_germany_octobers_1991_2020.compute()

CPU times: user 16.9 s, sys: 9.91 s, total: 26.8 s
Wall time: 7.49 s

t2m_germany_octobers_1991_2020_mean = t2m_germany_octobers_1991_2020_computed.mean(dim="valid_time")

anomaly = t2m_germany_october_2023_monthly_mean - t2m_germany_octobers_1991_2020_mean
anomaly

<xarray.DataArray 't2m' (latitude: 33, longitude: 45)> Size: 6kB
array([[0.94561386, 0.9775305 , 0.9818058 , ..., 1.1062622 , 1.1509447 ,
        1.18295   ],
       [1.058692  , 1.0717936 , 1.0788851 , ..., 1.3152046 , 1.3094378 ,
        1.3461571 ],
       [1.1612654 , 1.169033  , 1.1861801 , ..., 1.4496317 , 1.4415836 ,
        1.3800087 ],
       ...,
       [2.637679  , 2.6654654 , 2.8324194 , ..., 3.3936133 , 3.5344958 ,
        3.6796694 ],
       [2.7071152 , 2.7365713 , 2.8895226 , ..., 3.2909975 , 3.426055  ,
        3.5746298 ],
       [2.8477697 , 2.828455  , 2.91681   , ..., 3.4293985 , 3.4998322 ,
        3.638671  ]], dtype=float32)
Coordinates:
    entireAtmosphere  float32 4B 0.0
  * latitude          (latitude) float64 264B 55.0 54.75 54.5 ... 47.25 47.0
  * longitude         (longitude) float64 360B 5.0 5.25 5.5 ... 15.5 15.75 16.0
    number            int64 8B 0
    surface           float64 8B 0.0
Attributes: (12/31)
    GRIB_NV:                                  0
    GRIB_Nx:                                  1440
    GRIB_Ny:                                  721
    GRIB_cfName:                              unknown
    GRIB_cfVarName:                           t2m
    GRIB_dataType:                            an
    ...                                       ...
    GRIB_typeOfLevel:                         surface
    GRIB_units:                               K
    last_restart_dim_updated:                 742824
    long_name:                                2 metre temperature
    standard_name:                            unknown
    units:                                    °C

array([[0.94561386, 0.9775305 , 0.9818058 , ..., 1.1062622 , 1.1509447 ,
        1.18295   ],
       [1.058692  , 1.0717936 , 1.0788851 , ..., 1.3152046 , 1.3094378 ,
        1.3461571 ],
       [1.1612654 , 1.169033  , 1.1861801 , ..., 1.4496317 , 1.4415836 ,
        1.3800087 ],
       ...,
       [2.637679  , 2.6654654 , 2.8324194 , ..., 3.3936133 , 3.5344958 ,
        3.6796694 ],
       [2.7071152 , 2.7365713 , 2.8895226 , ..., 3.2909975 , 3.426055  ,
        3.5746298 ],
       [2.8477697 , 2.828455  , 2.91681   , ..., 3.4293985 , 3.4998322 ,
        3.638671  ]], dtype=float32)

array(0., dtype=float32)

array([55.  , 54.75, 54.5 , 54.25, 54.  , 53.75, 53.5 , 53.25, 53.  , 52.75,
       52.5 , 52.25, 52.  , 51.75, 51.5 , 51.25, 51.  , 50.75, 50.5 , 50.25,
       50.  , 49.75, 49.5 , 49.25, 49.  , 48.75, 48.5 , 48.25, 48.  , 47.75,
       47.5 , 47.25, 47.  ])

array([ 5.  ,  5.25,  5.5 ,  5.75,  6.  ,  6.25,  6.5 ,  6.75,  7.  ,  7.25,
        7.5 ,  7.75,  8.  ,  8.25,  8.5 ,  8.75,  9.  ,  9.25,  9.5 ,  9.75,
       10.  , 10.25, 10.5 , 10.75, 11.  , 11.25, 11.5 , 11.75, 12.  , 12.25,
       12.5 , 12.75, 13.  , 13.25, 13.5 , 13.75, 14.  , 14.25, 14.5 , 14.75,
       15.  , 15.25, 15.5 , 15.75, 16.  ])

array(0)

array(0.)

PandasIndex(Index([ 55.0, 54.75,  54.5, 54.25,  54.0, 53.75,  53.5, 53.25,  53.0, 52.75,
        52.5, 52.25,  52.0, 51.75,  51.5, 51.25,  51.0, 50.75,  50.5, 50.25,
        50.0, 49.75,  49.5, 49.25,  49.0, 48.75,  48.5, 48.25,  48.0, 47.75,
        47.5, 47.25,  47.0],
      dtype='float64', name='latitude'))

PandasIndex(Index([  5.0,  5.25,   5.5,  5.75,   6.0,  6.25,   6.5,  6.75,   7.0,  7.25,
         7.5,  7.75,   8.0,  8.25,   8.5,  8.75,   9.0,  9.25,   9.5,  9.75,
        10.0, 10.25,  10.5, 10.75,  11.0, 11.25,  11.5, 11.75,  12.0, 12.25,
        12.5, 12.75,  13.0, 13.25,  13.5, 13.75,  14.0, 14.25,  14.5, 14.75,
        15.0, 15.25,  15.5, 15.75,  16.0],
      dtype='float64', name='longitude'))

display.map(
    anomaly,
    vmax=None,
    projection=crs.Miller(),
    cmap="YlOrRd", 
    title="Mean Surface Temperature anomaly (ref 1991-2020), Oct 2013"
);

t2m_Berlin = t2m.sel(**{"latitude": 52.5, "longitude": 13.4}, method="nearest")
t2m_Berlin

<xarray.DataArray 't2m' (valid_time: 742824)> Size: 3MB
dask.array<getitem, shape=(742824,), dtype=float32, chunksize=(4320,), chunktype=numpy.ndarray>
Coordinates:
    entireAtmosphere  float32 4B ...
    latitude          float64 8B 52.5
    longitude         float64 8B 13.5
    number            int64 8B ...
    surface           float64 8B ...
  * valid_time        (valid_time) datetime64[ns] 6MB 1940-01-01 ... 2024-09-...
Attributes: (12/31)
    GRIB_NV:                                  0
    GRIB_Nx:                                  1440
    GRIB_Ny:                                  721
    GRIB_cfName:                              unknown
    GRIB_cfVarName:                           t2m
    GRIB_dataType:                            an
    ...                                       ...
    GRIB_typeOfLevel:                         surface
    GRIB_units:                               K
    last_restart_dim_updated:                 742824
    long_name:                                2 metre temperature
    standard_name:                            unknown
    units:                                    °C

[1 values with dtype=float32]

array(52.5)

array(13.5)

[1 values with dtype=int64]

[1 values with dtype=float64]

array(['1940-01-01T00:00:00.000000000', '1940-01-01T01:00:00.000000000',
       '1940-01-01T02:00:00.000000000', ..., '2024-09-26T21:00:00.000000000',
       '2024-09-26T22:00:00.000000000', '2024-09-26T23:00:00.000000000'],
      dtype='datetime64[ns]')

PandasIndex(DatetimeIndex(['1940-01-01 00:00:00', '1940-01-01 01:00:00',
               '1940-01-01 02:00:00', '1940-01-01 03:00:00',
               '1940-01-01 04:00:00', '1940-01-01 05:00:00',
               '1940-01-01 06:00:00', '1940-01-01 07:00:00',
               '1940-01-01 08:00:00', '1940-01-01 09:00:00',
               ...
               '2024-09-26 14:00:00', '2024-09-26 15:00:00',
               '2024-09-26 16:00:00', '2024-09-26 17:00:00',
               '2024-09-26 18:00:00', '2024-09-26 19:00:00',
               '2024-09-26 20:00:00', '2024-09-26 21:00:00',
               '2024-09-26 22:00:00', '2024-09-26 23:00:00'],
              dtype='datetime64[ns]', name='valid_time', length=742824, freq=None))

costing.estimate_download_size(t2m, t2m_Berlin)

estimated_needed_chunks: 172
estimated_memory_size: 12.174 GB
estimated_download_size: 1.217 GB

%%time

t2m_Berlin_computed = t2m_Berlin.compute()

CPU times: user 32.5 s, sys: 18.9 s, total: 51.4 s
Wall time: 14.2 s

t2m_Berlin_climatology_mean = t2m_Berlin_computed.sel(valid_time=slice("1991", "2020")).groupby("valid_time.month").mean(dim="valid_time")
t2m_Berlin_climatology_std = t2m_Berlin_computed.sel(valid_time=slice("1991", "2020")).groupby("valid_time.month").std(dim="valid_time")

t2m_Berlin_2023_monthly_means = t2m_Berlin_computed.sel(valid_time="2023").resample(valid_time="1ME").mean(dim="valid_time")
t2m_Berlin_2023_monthly_means

<xarray.DataArray 't2m' (valid_time: 12)> Size: 48B
array([ 4.1796923,  3.010704 ,  5.551641 ,  7.8618503, 13.801259 ,
       19.066559 , 19.860262 , 19.305855 , 18.504393 , 11.931021 ,
        5.609091 ,  3.6396573], dtype=float32)
Coordinates:
    entireAtmosphere  float32 4B 0.0
    latitude          float64 8B 52.5
    longitude         float64 8B 13.5
    number            int64 8B 0
    surface           float64 8B 0.0
  * valid_time        (valid_time) datetime64[ns] 96B 2023-01-31 ... 2023-12-31
Attributes: (12/31)
    GRIB_NV:                                  0
    GRIB_Nx:                                  1440
    GRIB_Ny:                                  721
    GRIB_cfName:                              unknown
    GRIB_cfVarName:                           t2m
    GRIB_dataType:                            an
    ...                                       ...
    GRIB_typeOfLevel:                         surface
    GRIB_units:                               K
    last_restart_dim_updated:                 742824
    long_name:                                2 metre temperature
    standard_name:                            unknown
    units:                                    °C

array([ 4.1796923,  3.010704 ,  5.551641 ,  7.8618503, 13.801259 ,
       19.066559 , 19.860262 , 19.305855 , 18.504393 , 11.931021 ,
        5.609091 ,  3.6396573], dtype=float32)

array(0., dtype=float32)

array(52.5)

array(13.5)

array(0)

array(0.)

array(['2023-01-31T00:00:00.000000000', '2023-02-28T00:00:00.000000000',
       '2023-03-31T00:00:00.000000000', '2023-04-30T00:00:00.000000000',
       '2023-05-31T00:00:00.000000000', '2023-06-30T00:00:00.000000000',
       '2023-07-31T00:00:00.000000000', '2023-08-31T00:00:00.000000000',
       '2023-09-30T00:00:00.000000000', '2023-10-31T00:00:00.000000000',
       '2023-11-30T00:00:00.000000000', '2023-12-31T00:00:00.000000000'],
      dtype='datetime64[ns]')

PandasIndex(DatetimeIndex(['2023-01-31', '2023-02-28', '2023-03-31', '2023-04-30',
               '2023-05-31', '2023-06-30', '2023-07-31', '2023-08-31',
               '2023-09-30', '2023-10-31', '2023-11-30', '2023-12-31'],
              dtype='datetime64[ns]', name='valid_time', freq='ME'))

plt.figure(figsize=(10, 5))
t2m_Berlin_climatology_mean.plot(label="Mean", color="#3498db")
plt.errorbar(
    t2m_Berlin_climatology_mean.month, 
    t2m_Berlin_climatology_mean, 
    yerr=t2m_Berlin_climatology_std, 
    fmt="o", 
    label="Standard Deviation",
    color="#a9a9a9"
)
for month in range (1, 11):
    t2m_point = t2m_Berlin_2023_monthly_means.sel(valid_time=t2m_Berlin_2023_monthly_means["valid_time.month"]==month)
    label = None
    if month == 1:
        label = "2023"
    plt.scatter(month, t2m_point, color="#ff6600", label=label)
plt.title("Surface Temperature climatology in Berlin (DE), 1991-2020")
plt.xticks(t2m_Berlin_climatology_mean.month)
plt.xlabel("Month")
plt.ylabel("Surface Temperature [°C]")
plt.legend()
plt.grid(alpha=0.3)
plt.show()

How to work with ERA5 single levels on Earth Data Hub: climatological analysis of temperature in Germany¶

Goal of this tutorial¶

What you will learn:¶

Working with EDH data¶

1. Data access¶

Average 2 metre temperature in Germany, October 2023¶

2. Data selection¶

3. Data download¶

4. Data reduction¶

5. Visualization¶

2 metre temperature anomaly in Germany, October 2023¶

2 metre temperature climatology (1991-2020) in Berlin vs 2023 montly mean¶