ACE-climSST-EAMv2

Ai2 Climate Emulator (ACE) is a family of models designed to simulate atmospheric variability from the time scale of days to centuries.

Disclaimer: ACE models are research tools and should not be used for operational climate predictions.

ACE-climSST-EAMv2 is the model described in Application of the AI2 Climate Emulator to E3SMv2's Global Atmosphere Model, With a Focus on Precipitation Fidelity. It is trained on output from the E3SMv2's atmosphere model (i.e. EAMv2) forced with annually-repeating climatological sea surface temperature.

Quick links:

• 📃 Paper
• 💻 Code
• 💬 Docs
• 📂 All Models

Briefly, the strengths of ACE-climSST-EAMv2 are:

• long-term stability
• highly accurate time-mean climate compared to its target dataset
• faithful emulation of the precipitation distribution and tropical variability in EAMv2

Some known weaknesses are:

• responses to El Niño-like sea surface temperature and long-term warming trends are not accurately captured
• small but non-zero drifts in total dry air mass of the atmosphere

Note the checkpoint provided here is the same as the one here, just with the optimizer state removed to decrease the checkpoint size.
The full training data is publicly available via Guest Collections on Globus under ACE-EAM-data. This data is hosted through NERSC SHARE.