Skip to content

AIFSENS

GlobalMRF202548 GBECMWFPyTorch

Import path: earth2studio.models.px.AIFSENS

View source on GitHub View install commands

Documentation

Bases: Module, AutoModelMixin, PrognosticMixin

Artificial Intelligence Forecasting System Ensemble (AIFS ENS v1.0), a probabilistic, ensemble-based forecast model from the European Centre for Medium-Range Weather Forecasts (ECMWF). AIFS ENS uses a GNN encoder/decoder with a sliding-window transformer processor, trained on ERA5 reanalysis and operational NWP analyses, and is run four times daily with a 6-hour time step. The model is trained with a CRPS objective over a small ensemble to provide calibrated probabilistic output.

Note

This model uses the checkpoints provided by ECMWF. For additional information see the following resources:

Parameters:

  • model (Module) –

    Core PyTorch module with the pretrained AIFSENS weights loaded.

  • latitudes (Tensor) –

    Latitude values for the native model grid, registered as a buffer for interpolation.

  • longitudes (Tensor) –

    Longitude values for the native model grid, registered as a buffer for interpolation.

  • interpolation_matrix (Tensor) –

    CSR sparse matrix mapping ERA5 lat/lon inputs onto the native model grid.

  • inverse_interpolation_matrix (Tensor) –

    CSR sparse matrix mapping outputs from the native model grid back to ERA5 lat/lon.

  • invariants (Tensor) –

    Tensor of shape [4, 721, 1440] containing the invariant fields "lsm", "sdor", "slor" and "z"

Warning

We encourage users to familiarize themselves with the license restrictions of this model's checkpoints.

__call__ 

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

Runs prognostic model 1 step.

Parameters:

  • x (Tensor) –

    Input tensor

  • coords (CoordSystem) –

    Input coordinate system

Returns:

  • tuple[Tensor, CoordSystem] –

    Output tensor and coordinate system 6 hours in the future

create_iterator 

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

Creates a iterator which can be used to perform time-integration of the prognostic model. Will return the initial condition first (0th step).

Parameters:

  • x (Tensor) –

    Input tensor

  • coords (CoordSystem) –

    Input coordinate system

Yields:

  • Iterator[tuple[Tensor, CoordSystem]] –

    Iterator that generates time-steps of the prognostic model container the output data tensor and coordinate system dictionary.

load_default_package classmethod 

load_default_package() -> Package

Load prognostic package

load_model classmethod 

load_model(package: Package) -> PrognosticModel

Load prognostic from package