ENSO's impact on Antarctic sea ice predictability at subseasonal timescale

ENSO's far-reaching impact on climate variability has been well documented globally. In the Southern Ocean, ENSO significantly influences Antarctic sea ice variability, particularly in the West Antarctic, through the atmosphere teleconnection bridge. However, the extent of ENSO-related ice variability's contribution to sea ice's predictability still needs to be investigated, particularly concerning nonlinear ice predictability. This study uses deep-learning models to quantify Antarctic sea ice's linear and nonlinear predictability attributed to ENSO. The results reveal that ENSO events deliver cross-timescale influences on ice subseasonal predictability. Ice persistence is the primary source of predictability within 3-week lead times. Beyond that, ENSO becomes a significant source of ice predictability, with El Niño contributing more than La Niña. El Niño primarily influences linear predictability, enhancing overall ice predictability by 25.6%, 19.6%, and 30.4% in the A-B Sea, Ross Sea, and Indian Ocean, respectively, at an 8-week lead time. La Niña mainly enhances nonlinear predictability, particularly in the Ross Sea. We confirm that ENSO provides additional sources for ice predictability primarily by generating more extensive sea ice anomalies.