Stochastic Emulation of a Fully Coupled Preindustrial E3SMv3 Simulation
This work provides a high-fidelity, computationally efficient tool for climate scientists to study long-timescale variability in Earth system models, addressing the challenge of accurately representing internal climate dynamics.
This paper developed a stochastic coupled emulator for the E3SMv3 climate model, which accurately reproduces the mean climate state with biases smaller than model-to-observation differences. It successfully maintains internal variability across various timescales, including ENSO and sea ice, and captures daily precipitation up to the 99.99th percentile.
We present a stochastic coupled emulator of E3SM version 3, built on the SamudrACE framework, which couples an atmosphere emulator (ACE2) with a full-depth ocean emulator (Samudra). We replace the deterministic atmosphere emulator with its stochastic counterpart, ACE2S, and fine-tune the coupled system with a probabilistic objective, so that the atmosphere acts as a source of internal variability for the ocean. Trained on 105 years of a pre-industrial control simulation and evaluated on an independent 400 years, the emulator reproduces E3SMv3's mean climate state with biases much smaller than existing model-to-observation differences. Relative to a deterministic baseline, stochastic training maintains internal variability across timescales, most notably in the ENSO power spectrum, eddy-rich SST anomalies, and sea ice variability in the marginal ice zone. The emulator captures daily precipitation accurately up to the 99.99th percentile, but underestimates the rarest tropical extremes. These results show that stochastic coupled emulators can reproduce long-timescale variability with high fidelity, while extrapolation to unseen extremes remains a key challenge.