Fig. 1: Global and annual-mean time series of ACE2 and reference datasets over 1940–2020.
From: ACE2: accurately learning subseasonal to decadal atmospheric variability and forced responses
Global- and annual-mean series for a 2-meter air temperature and c total water path over 81-year evaluations of ACE2-ERA5 and ACE2-SHiELD. For each ACE2 evaluation, a three-member initial condition (IC) ensemble of the model (each initialized 1 day apart) is shown in solid lines, and the reference dataset is shown in dashed lines (e.g., ACE2-ERA5 vs. ERA5 itself). The validation and test periods are shaded in dark gray and light gray, respectively. As a baseline, the ACE-climSST model21 forced with the historical SST is also shown for total water path (2-meter air temperature was not predicted by this model). The “forced SST” in a is the prescribed SST averaged over 45°S to 45°N in the SHiELD simulation (ERA5 SSTs are similar though not identical). The R2 of the 81-year series are shown in (b) and (d). For ACE2-SHiELD, the skill metrics for each of four trained models are shown. Error bars indicate the range over three IC ensemble members for each model. The “SHiELD reference” bar in (b) and (d) is the R2 computed between the two SHiELD ensemble members which differed only in initial condition.
