perturbation.HemisphericCentredBredVector

Import path: earth2studio.perturbation.HemisphericCentredBredVector

View source on GitHub

Documentation

Bred Vector perturbation method, following the approach introduced in 'Huge Ensembles Part I: Design of Ensemble Weather Forecasts using Spherical Fourier Neural Operators'. The vector is bred by advancing in time. The bred vector is scaled seperately in the northern and southern extra-tropics and interpolated in the tropics. Additionally, it applies a centred perturbation, ie generating two perturbed stated by adding and subtracting the bred vector, respecitvely.

Parameters:

• model (PrognosticModel) –

  Dynamical model, typically this is the prognostic AI model

• data (DataSource) –

  data source for obtaining warmup time steps

• seeding_perturbation_method (Perturbation) –

  Method to seed the Bred Vector perturbation that will be applied to the initial input of the model.

• noise_amplitude (float | Tensor, default: 0.35 ) –

  Noise amplitude, by default 0.05. If a tensor, this must be broadcastable with the input data

• integration_steps (int, default: 3 ) –

  Number of integration steps to use in forward call, by default 3

Note

For additional information:

• arxiv.org/abs/2408.03100
• journals.ametsoc.org/view/journals/bams/74/12/1520-0477_1993_074_2317_efantg_2_0_co_2.xml
• en.wikipedia.org/wiki/Bred_vector

__call__

__call__(
    x: Tensor, coords: CoordSystem
) -> tuple[Tensor, CoordSystem]

Apply perturbation method

Parameters:

• x (Tensor) –

  Input tensor intended to apply perturbation on, not used in this perturbation method

• coords (CoordSystem) –

  Ordered dict representing coordinate system that describes the tensor. Must contain coordinates (Any, "time", "lead_time", "variable", "lat", "lon"). Time and lead_time must have size 1.

Returns:

• tuple[torch.Tensor, CoordSystem]: –

  Output tensor and respective coordinate system dictionary

Examples using earth2studio.perturbation.HemisphericCentredBredVector

Huge Ensembles (HENS) CheckpointsBasic multi-checkpoint Huge Ensembles (HENS) inference workflow.