Function for taking CRPS skill scores of ensemble forecasts stored in long data tables.
The skill score needs a climatological forecast as reference. This is so far always based on the leave-one-year-out climatology.
Usage
CRPSS(dt, f, o = "obs", by = by_cols_ens_fc_score(), pool = c("year"), ...)
Value
A data table with the scores
Arguments
dt
Data table containing predictions and observations.
f
column name of the prediction.
o
column name of the observations.
by
column names of grouping variables, all of which need to be columns in dt. A separate CRPS is computed for each value of the grouping variables.
Default is to group by all instances of month, season, lon, lat, system and lead_time that are columns in dt.
pool
column name(s) for the variable(s) along which is averaged. Needs to contain 'year' since the reference climatology forecast is leave-one-year-out.
...
passed on to CRPS_ens_fc, in particular mem and dim.check