pysteps.utils.pca.pca_backtransform

pysteps.utils.pca.pca_backtransform#

pysteps.utils.pca.pca_backtransform(forecast_ens_pc: ndarray, pca_params: dict)#

Reconstruct ensemble forecasts from principal component (PC) space back into physical space.

Parameters:

  • forecast_ens_pc (np.ndarray) – Array of shape (n_components, n_ens) containing the ensemble forecasts represented in PC space.

  • pca_params (dict) –

    Parameters of the PCA transformation. The dictionary contains the following keys:

    principal_componentsnp.ndarray

    Array of shape (n_components, n_features) containing the principal component vectors in feature space.

    meannp.ndarray

    Array of shape (n_features,) containing the per-feature empirical mean estimated from the training data.

Returns:

forecast_ens – Array of shape (n_ens, n_features) containing the ensemble forecasts reconstructed in physical space.

Return type:

np.ndarray

Contents