weatherbench2.metrics.EnsembleMeanMSE

class weatherbench2.metrics.EnsembleMeanMSE(ensemble_dim='realization')

Mean square error between the ensemble mean and ground truth.

Suppose we have a size n ensemble, {Xₖ}, each an iid copy of X having with mean μ and variance σ². Let Y be the ground truth. This class estimates E(X - Y)² with a bias equal to σ² / n.

Parameters:

ensemble_dim (str) –

__init__(ensemble_dim='realization')
Parameters:

ensemble_dim (str) –

Return type:

None

Methods

__init__([ensemble_dim])

compute(forecast, truth[, region])

Evaluate this metric on datasets with full temporal coverages.

compute_chunk(forecast, truth[, region])

EnsembleMeanRMSE, averaged over space, for a time chunk of data.

Attributes

ensemble_dim