Fig. 3: Global RMSE between the time-mean of ACE2 and its reference dataset (ERA5 or SHiELD).
From: ACE2: accurately learning subseasonal to decadal atmospheric variability and forced responses
The global RMSE of the time-mean (Eq. (9)) for a 2-meter air temperature, b surface precipitation rate, c total water path and d 500 hPa geopotential height. Error bars indicate the 95% confidence interval based on the IC ensemble. Also included are NeuralGCM error against ERA5, SHiELD reference variability, the error of ACE-climSST evaluated against the SHiELD dataset, and the error of the SHiELD simulations against ERA5. ACE-climSST did not predict 2-meter temperature or 500 hPa height. NeuralGCM13 results are only available for total water path for a single year (2020), and so we also show 2020-only results of ACE2-ERA5.
