Skip to content

cmip6

CMIP6 Data Extraction

extract_cmip6(cmip6_source: list[str], cmip6_experiment: list[str], cmip6_variable: list[str], output_dir: str, queue: str, overwrite: bool) -> None

Extract CMIP6 data.

Extracts CMIP6 data for the given source, experiment, and variable. We use the the table at https://www.nature.com/articles/s41597-023-02549-6/tables/3 to determine which CMIP6 source_ids to include. See ClimateData.load_koppen_geiger_model_inclusion to load and examine this table. The extraction criteria does not completely capture model inclusion criteria as it does not account for the year range avaialable in the data. This determiniation is made when we proccess the data in later steps.

Source code in src/climate_data/extract/cmip6.py 
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
@click.command()
@clio.with_cmip6_source(allow_all=True)
@clio.with_cmip6_experiment(allow_all=True)
@clio.with_cmip6_variable(allow_all=True)
@clio.with_output_directory(cdc.MODEL_ROOT)
@clio.with_queue()
@clio.with_overwrite()
def extract_cmip6(
    cmip6_source: list[str],
    cmip6_experiment: list[str],
    cmip6_variable: list[str],
    output_dir: str,
    queue: str,
    overwrite: bool,
) -> None:
    """Extract CMIP6 data.

    Extracts CMIP6 data for the given source, experiment, and variable. We use the
    the table at https://www.nature.com/articles/s41597-023-02549-6/tables/3 to determine
    which CMIP6 source_ids to include. See `ClimateData.load_koppen_geiger_model_inclusion`
    to load and examine this table. The extraction criteria does not completely
    capture model inclusion criteria as it does not account for the year range avaialable
    in the data. This determiniation is made when we proccess the data in later steps.
    """
    overwrite_arg = {"overwrite": None} if overwrite else {}

    jobmon.run_parallel(
        runner="cdtask",
        task_name="extract cmip6",
        node_args={
            "cmip6-source": cmip6_source,
            "cmip6-experiment": cmip6_experiment,
            "cmip6-variable": cmip6_variable,
        },
        task_args={
            "output-dir": output_dir,
            **overwrite_arg,
        },
        task_resources={
            "queue": queue,
            "cores": 1,
            "memory": "10G",
            "runtime": "3000m",
            "project": "proj_rapidresponse",
        },
        max_attempts=1,
        concurrency_limit=50,
    )

load_cmip_data(zarr_path: str) -> xr.Dataset

Loads a CMIP6 dataset from a zarr path.

Source code in src/climate_data/extract/cmip6.py 
22
23
24
25
26
27
28
29
30
31
def load_cmip_data(zarr_path: str) -> xr.Dataset:
    """Loads a CMIP6 dataset from a zarr path."""
    gcs = gcsfs.GCSFileSystem(token="anon")  # noqa: S106
    mapper = gcs.get_mapper(zarr_path)
    ds = xr.open_zarr(mapper, consolidated=True)
    ds = ds.drop_vars(
        ["lat_bnds", "lon_bnds", "time_bnds", "height", "time_bounds", "bnds"],
        errors="ignore",
    )
    return ds  # type: ignore[no-any-return]