[A-CG40] Earth System Observation Impacts on Climate and Ocean Predictions

[ACG40-P07] Subseasonal-to-Seasonal Antarctic Sea Ice Prediction with A Convolutional Long Short-Term Memory Network

*Yafei Nie¹ (1.Southern Marine Science and Engineering Guangdong Laboratory, Zhuhai, China)

Keywords:Antarctic Sea Ice, Subseasonal-to-Seasonal Prediction, Deep Learning

Antarctic sea ice predictions are becoming increasingly important scientifically and operationally due to climate change and increased human activities in the region. Conventional numerical models typically require extensive computational resources and exhibit limited predictive skill on the subseasonal-to-seasonal scale. In this study, a convolutional long short-term memory (ConvLSTM) deep neural network is constructed to predict the 60-day future Antarctic sea ice evolution using only satellite-derived sea ice concentration (SIC) from 1989 to 2016. The network is skillful for approximately one month in predicting the daily spatial distribution of Antarctic SIC between 2018 and 2022, with the best predictive skill found in austral autumn (MAM) and winter (JJA). The seasonal-scale prediction model was further constructed by simply changing the training data from daily observations to monthly averaged observations. The reforecast experiments demonstrate that ConvLSTM captures the interannual and interseasonal variability of Antarctic sea ice successfully, and performs better than the European Centre for Medium-Range Weather Forecasts. Based on this, we present the prediction from December 2023 to June 2024, indicating that the Antarctic sea ice will remain low, but may not create a new record low. These results suggest substantial potential for applying machine learning techniques for skillful Antarctic sea ice prediction.