data.GFS

Global

Import path: earth2studio.data.GFS

View source on GitHub

Documentation

The global forecast service (GFS) initial state data source provided on an equirectangular grid. GFS is a weather forecast model developed by NOAA. This data source is provided on a 0.25 degree lat lon grid at 6-hour intervals spanning from Jan 1st 2021 to present date.

Parameters:

• source (str, default: 'aws' ) –

  Data store location to pull from. Options are [aws, ncep], by default aws

• cache (bool, default: True ) –

  Cache data source on local memory, by default True

• verbose (bool, default: True ) –

  Print download progress, by default True

• async_timeout (int, default: 600 ) –

  Time in sec after which download will be cancelled if not finished successfully, by default 600

• async_workers (int, default: None ) –

  Maximum number of concurrent downloads. By default None, which autoscales to the number of download tasks (capped at 64)

• retries (int, default: 3 ) –

  Number of retries for each download task on transient errors, by default 3

Warning

This is a remote data source and can potentially download a large amount of data to your local machine for large requests.

Note

This data source only fetches the initial state of GFS and does not fetch an predicted time steps. See [GFS_FX][earth2studio.data.GFS_FX] for fetching predicted data from this forecast system.

Note

Additional information on the data repository can be referenced here:

• registry.opendata.aws/noaa-gfs-bdp-pds/
• www.emc.ncep.noaa.gov/emc/pages/numerical_forecast_systems/gfs.php

__call__

__call__(
    time: datetime | list[datetime] | TimeArray,
    variable: str | list[str] | VariableArray,
) -> DataArray

Retrieve GFS initial state / analysis data

Parameters:

• time (datetime | list[datetime] | TimeArray) –

  Timestamps to return data for (UTC).

• variable (str | list[str] | VariableArray) –

  String, list of strings or array of strings that refer to variables to return. Must be in the GFS lexicon.

Returns:

• DataArray –

  GFS weather data array

fetch async

fetch(
    time: datetime | list[datetime] | TimeArray,
    variable: str | list[str] | VariableArray,
) -> DataArray

Async function to get data

Parameters:

• time (datetime | list[datetime] | TimeArray) –

  Timestamps to return data for (UTC).

• variable (str | list[str] | VariableArray) –

  String, list of strings or array of strings that refer to variables to return. Must be in the GFS lexicon.

Returns:

• DataArray –

  GFS weather data array

available classmethod

available(time: datetime | datetime64) -> bool

Checks if given date time is avaliable in the GFS object store. Uses S3 store

Parameters:

• time (datetime | datetime64) –

  Date time to access

Returns:

• bool –

  If date time is avaiable

Examples using earth2studio.data.GFS

Running Deterministic InferenceBasic deterministic inference workflow. Running Diagnostic InferenceBasic prognostic + diagnostic inference workflow. Running Ensemble InferenceSimple ensemble inference workflow. Single Variable Perturbation MethodIntermediate ensemble inference using a custom perturbation method. Model Hook Injection: PerturbationAdding model noise by using custom hooks. Huge Ensembles (HENS) CheckpointsBasic multi-checkpoint Huge Ensembles (HENS) inference workflow. Temporal InterpolationTemporal Interpolation inference using InterpModAFNO model. Generative DownscalingGenerative downscaling over Taiwan using CorrDiff diffusion model. Ensemble Forecasting with DownscalingCustom ensembling workflow with generative downscaling using CorrDiff. Statistical InferenceSimple seasonal statistic inference workflow. IO Backend PerformanceLeverage different IO backends for storing inference results. Extending Prognostic ModelsImplementing a custom prognostic model Extending Diagnostic ModelsImplementing a custom diagnostic model