Tre

extract_input_target_forcings add option for left-justification of train/eval

2

Provides optionality for a left-justified evaluation and training with kwarg justify = 'left' or 'right'. Changes are from lines 281 - 322, line 361, and line 381. Per issue discussion...

Different loss values for seemingly same forecast

6

I performed "1 Eval Step" forecast with Graphcast small using dataset_source-era5_date-2022-01-01_res-1.0_levels-13_steps-01.nc, steps-12.nc, and steps-40.nc. The loss is different for each case even though we are only performing a 6 hr...

Forecasting beyond 10 days

21

There's seems to be some default setting that won't allow a forecast beyond 10 days. I've tried identifying where in the code that might be and have not been able...