Predicting the Daily Sea Ice Concentration on a Subseasonal Scale of the Pan-Arctic During the Melting Season by a Deep Learning Model

During the melting season, predicting the daily sea ice concentration (SIC) of the Pan-Arctic at a subseasonal scale is strongly required for economic activities and a challenging task for current studies. We propose a deep-learning-based data driven model to predict the 90 days SIC of the Pan-Arctic, named SICNet90. SICNet90 takes the historical 60 days' SIC and its anomaly and outputs the SIC of the next 90 days. We design a physically constrained loss function, normalized integrated ice-edge error (NIIEE), to constrain the SICNet(90's) optimization by the spatial morphology of SIC. The satellite-observed SIC trains (1991-2011/1997-2017) and tests the model (2012/2018-2020). For each test year, a 90-day SIC prediction is made daily from May 1 to July 2. The binary accuracy (BACC) of sea ice extent (SIC > 15%) and the mean absolute error (MAE) are evaluation metrics. Experiments show that SICNet90 significantly outperforms the Climatology benchmark on 90 days prediction, with a BACC/MAE improvement/reduction of 5.41%/1.35%. The data-driven model shows a late-spring-early-summer predictability barrier (around June 20) and a prediction challenge (around July 10), consistent with SIC's autocorrelation. The NIIEE loss optimizes the predictability barrier/challenge with a BACC increase of 4%. Using a 60 days historical SIC to predict 90 days SIC is better than a historical SIC of 30/90 days. The historical 2-m surface air temperature shows positive contributions to the prediction made from May 1 to mid-June, but negative contributions to the prediction made after mid-June. The historical sea surface temperature and 500 hp geopotential height show negative contributions.

Automated summary

Predicting the daily sea ice concentration (SIC) of the Pan-Arctic during the melting season is crucial but challenging. In this study, we propose a deep-learning-based data driven model, SICNet90, which utilizes historical SIC data to predict the SIC of the next 90 days. We also design a physically constrained loss function to optimize the model's prediction accuracy. Experimental results show that SICNet90 outperforms the Climatology benchmark, achieving a significant improvement in binary accuracy and mean absolute error. Additionally, the model exhibits a predictability barrier and challenge, which aligns with the autocorrelation of SIC. The use of historical SIC data and other environmental factors contribute to the prediction accuracy.