ACE2-ERA5 Sample Output

Full spatial and temporal variables output from a 2-year inference using the ACE2-ERA5 checkpoint initialized on 2001-01-01T00:00:00. The outputs have been written out as 20 segments to avoid large file sizes. The 2-year inference with 6-hourly has 2920 timesteps, so each segment has 146 timesteps. Each segment_00** folder contains a netCDF file (autoregressive_predictions.nc) containing all output variables for that segment.

The sensitivity of the radiative flux at the top of the atmosphere to surface temperature perturbations cannot be directly observed. The relationship between sea surface temperature and top-of-atmosphere radiation can be estimated with Green's function simulations by locally perturbing the sea surface temperature boundary conditions in atmospheric climate models. We perform such simulations with the Ai2 Climate Emulator (ACE), a machine learning-based emulator trained on ERA5 reanalysis data (ACE2-ERA5). This produces a sensitivity map of the top-of-atmosphere radiative response to surface warming that aligns with our physical understanding of radiative feedback. However, ACE2-ERA5 likely underestimates the radiative response to historical warming. We argue that Green's function experiments can be used to evaluate the performance and limitations of machine learning-based climate emulators by examining if causal physical relationships are correctly represented and testing their capability for out-of-distribution predictions.