run.ensemble

Import path: earth2studio.run.ensemble

View source on GitHub

Documentation

Built in ensemble workflow.

Parameters:

• time (list[str] | list[datetime] | list[datetime64]) –

  List of string, datetimes or np.datetime64

• nsteps (int) –

  Number of forecast steps

• nensemble (int) –

  Number of ensemble members to run inference for.

• prognostic (PrognosticModel) –

  Prognostic models

• data (DataSource) –

  Data source

• io (IOBackend) –

  IO object

• perturbation (Perturbation) –

  Method to perturb the initial condition to create an ensemble.

• batch_size (int | None, default: None ) –

  Number of ensemble members to run in a single batch, by default None.

• output_coords (CoordSystem, default: OrderedDict({}) ) –

  IO output coordinate system override, by default OrderedDict({})

• device (device, default: None ) –

  Device to run inference on, by default None

• verbose (bool, default: True ) –

  Print inference progress, by default True

• checkpoint (Checkpoint, default: NullCheckpoint() ) –

  Checkpoint manager or checkpoint session used to record and resume workflow progress, by default no checkpoint

Returns:

• IOBackend –

  Output IO object

Examples using earth2studio.run.ensemble

Running Ensemble InferenceSimple ensemble inference workflow. Single Variable Perturbation MethodIntermediate ensemble inference using a custom perturbation method. Ensemble Forecasting with DownscalingCustom ensembling workflow with generative downscaling using CorrDiff. Running StormCast Ensemble InferenceEnsemble StormCast inference workflow. IO Backend PerformanceLeverage different IO backends for storing inference results.