FloeNet: A mass-conserving global sea ice emulator that generalizes across climates

TL;DR

FloeNet is a novel machine-learning model that accurately emulates sea ice dynamics across different climates while conserving mass, improving climate modeling and understanding polar processes.

Contribution

It introduces FloeNet, a mass-conserving emulator trained on a global sea ice model, capable of generalizing across climate scenarios and providing physically interpretable outputs.

Findings

Outperforms non-conservative models in reproducing sea ice states

Achieves high correlation in volume anomalies across climates

Produces high-fidelity coupling variables for climate processes

Abstract

We introduce FloeNet, a machine-learning emulator trained on the Geophysical Fluid Dynamics Laboratory global sea ice model, SIS2. FloeNet is a mass-conserving model, emulating 6-hour mass and area budget tendencies related to sea ice and snow-on-sea-ice growth, melt, and advection. We train FloeNet using simulated data from a reanalysis-forced ice-ocean simulation and test its ability to generalize to pre-industrial control and 1% CO2 climates. FloeNet outperforms a non-conservative model at reproducing sea ice and snow-on-sea-ice mean state, trends, and inter-annual variability, with volume anomaly correlations above 0.96 in the Antarctic and 0.76 in the Arctic, across all forcings. FloeNet also produces the correct thermodynamic vs dynamic response to forcing, enabling physical interpretability of emulator output. Finally, we show that FloeNet outputs high-fidelity coupling-related variables, including ice-surface skin temperature, ice-to-ocean salt flux, and melting energy fluxes. We hypothesize that FloeNet will improve polar climate processes within existing atmosphere and ocean emulators.