Metrics¶
CentroidErrorPerForecastDay
¶
Bases: BaseErrorMetricDaily
Euclidean distance (in pixels) between the predicted and target centroids.
The centroid of a (batch, time) frame is its value-weighted center of mass over the spatial dimensions, summed across channels. Frames whose target has (near-)zero total mass have an undefined centroid and are excluded from the average.
MAEPerForecastDay
¶
Bases: BaseErrorMetricDaily
Mean Absolute Error per forecast lead time.
RMSEPerForecastDay
¶
Bases: BaseErrorMetricDaily
Root Mean Squared Error per forecast lead time.
IceNetAccuracy
¶
SIEError
¶
Bases: Metric
Sea Ice Extent error metric (in km^2) for use at multiple lead times.
leadtimes_to_evaluate = leadtimes_to_evaluate
instance-attribute
¶
pixel_size = pixel_size
instance-attribute
¶
update(preds, target, _sample_weight=None)
¶
Update the SIE accumulators.
Parameters¶
preds : torch.Tensor Model predictions. target : torch.Tensor Ground truth values. sample_weight : Optional[torch.Tensor] Ignored (present for API compatibility).
compute()
¶
Compute the final Sea Ice Extent error in km².
SeaIceExtentErrorPerForecastDay
¶
Bases: Metric
Sea Ice Extent error (SIEError) metric (in km^2) for use at multiple lead times.
The SIE error is calculated as the absolute difference between the predicted and true sea ice extent for each forecast day. Sea ice presence is defined by having a probability greater than the threshold value.
sum_errors
instance-attribute
¶
sample_count
instance-attribute
¶
pixel_size = pixel_size
instance-attribute
¶
update(preds, target, _sample_weight=None)
¶
Update the SIE accumulators.
Parameters¶
preds : torch.Tensor Model predictions of shape (B, T, H, W). target : torch.Tensor Ground truth values of shape (B, T, H, W). _sample_weight : Optional[torch.Tensor] Ignored (present for API compatibility).
compute()
¶
Compute the final Sea Ice Extent error in km².