Applying the ACE2 Emulator to SST Green's Functions for the E3SMv3 Global Atmosphere Model

TL;DR

This study trains the ACE2 emulator on EAMv3 SST simulations to generate Green's functions, demonstrating comparable results to the original model with significantly reduced computational time, thus offering an efficient climate modeling tool.

Contribution

The paper introduces the application of ACE2 to SST Green's functions in the E3SMv3 model, showing it can replicate responses efficiently and accurately.

Findings

ACE2 Green's functions match EAMv3 responses reasonably well.

ACE2 achieves results approximately 100 times faster than EAMv3.

Discrepancies in sensitivity over the northeast Pacific suggest sampling limitations.

Abstract

Green's functions are a useful technique for interpreting atmospheric state responses to changes in the spatial pattern of sea surface temperature (SST). Here we train version 2 of the Ai2 Climate Emulator (ACE2) on reference historical SST simulations of the US Department of Energy's EAMv3 global atmosphere model. We compare how well the SST Green's functions generated by ACE2 match those of EAMv3, following the protocol of the Green's Function Model Intercomparison Project (GFMIP). The spatial patterns of top-of-atmosphere (TOA) radiative response from the individual GFMIP SST patch simulations are similar for ACE and the EAMv3 reference. The derived sensitivity of global net TOA radiation sensitivity to SST patch location is qualitatively similar in ACE as in EAMv3, but there are statistically significant discrepancies for some SST patches, especially over the subtropical northeast Pacific. These discrepancies may reflect insufficient diversity in the SST patterns sampled over the course of the EAMv3 AMIP simulation used for training ACE. Both ACE and EAMv3 Green's functions reconstruct the historical record of the global annual-mean TOA radiative flux from a reference EAMv3 AMIP simulation reasonably well. Notably, under our configuration and compute resources, ACE achieves these results approximately 100 times faster in wall-clock time compared to EAMv3, highlighting its potential as a powerful and efficient tool for tackling other computationally intensive problems in climate science.