Abstract
<jats:p>Neural network&ndash;based emulators can reproduce atmospheric dynamics at a far lower computational cost than physics based models, and similar advances are now emerging for sea ice. We develop and assess a deterministic sea-ice emulator, intended for future coupling to an ocean model. It uses a U-Net architecture with physics-informed loss enforcing cross-variable consistency and is trained on coupled sea ice&ndash;ocean simulations.<br />We examine emulator performance across lead times from hourly to daily and under different ocean forcings. Forcing with surface currents consistently causes instabilities, likely because the sea-ice fields already encode an implicit representation of ocean state. In contrast, forcing with sub-surface currents plus sea surface height, salinity, and temperature greatly improves stability and skill for sea-ice volume, concentration, drift, and snow thickness. Among the temporal resolutions tested, the 6-hourly emulator best balances accuracy and stability, outperforming both finer and coarser configurations as well as previously developed sea-ice emulators relying on atmospheric forcing alone. This configuration remains stable over multiple years, faithfully reproduces the seasonal cycle, large-scale drift patterns, Fram Strait export, and achieves a correlation with satellite-derived sea-ice concentration of 77.9%, compared to 78.6% for the NANUQ reference itself. <br />We further test robustness to changes in atmospheric forcing and find degraded performance&mdash;especially for sea-ice drift and in regions with strong atmospheric variability&mdash;when switching reanalysis products, driven by differences in forcing statistics. <br />Our results highlight the critical role of ocean forcing choice and temporal resolution in building stable sea-ice emulators suitable for coupled short-term and climate prediction systems.</jats:p>