openSaveThetao.ipynb

%time col = intake.open_esm_datastore(col_url)

col_url = "/pool/data/Catalogs/dkrz_cmip6_disk.json"

sourceIds = ['CAMS-CSM1-0', 'CMCC-CM2-SR5', 'CMCC-ESM2', 'ACCESS-ESM1-5', 'ACCESS-CM2', 'MPI-ESM1-2-LR']

cat = col.search(member_id='r1i1p1f1',
                 experiment_id='historical',
                 activity_id='CMIP',
                 table_id='Omon',
                 variable_id='thetao',
                 grid_label='gn',
                 source_id=sourceIds)

with dask.config.set(**{'array.slicing.split_large_chunks': True}):
       data_dict = cat.to_dataset_dict(cdf_kwargs={"chunks": {"time": -1}, 
        "use_cftime": True}, preprocess=combined_preprocessing)