IceBench-S2S: A Benchmark of Deep Learning for Challenging Subseasonal-to-Seasonal Daily Arctic Sea Ice Forecasting in Deep Latent Space

TL;DR

IceBench-S2S addresses the need for true subseasonal-to-seasonal (S2S) daily Arctic sea ice forecasting by introducing a deep latent-space benchmark. The Sea Ice Forecasting Engine (SIFE) compresses daily SIC data into a latent representation $\mathbf{z}_t \in \mathbb{R}^{1024}$ with compression $\gamma = 133$, and uses diverse time-series backbones to forecast horizons $\Delta \in \{7,15,30,180\}$ days. Evaluated on the NSIDC G02202 SIC dataset (16,686 days, 1979–2024), reconstruction achieves $\text{SSIM} \approx 0.90$, $\text{NSE} > 0.96$, and latent-space robustness across retrievals; S2S forecasting reveals that combining subsequence decomposition with hybrid linear models helps mitigate melting-season forecast loss, with SIFE-Ensemble-Rank-1 delivering strong performance. The work demonstrates that a unified DL benchmark, rolling autoregressive strategies, and ensemble approaches can push DL Arctic SIC forecasting toward practical 180-day horizons, while identifying the spring prediction barrier as a key challenge for future study.

Abstract

Arctic sea ice plays a critical role in regulating Earth's climate system, significantly influencing polar ecological stability and human activities in coastal regions. Recent advances in artificial intelligence have facilitated the development of skillful pan-Arctic sea ice forecasting systems, where data-driven approaches showcase tremendous potential to outperform conventional physics-based numerical models in terms of accuracy, computational efficiency and forecasting lead times. Despite the latest progress made by deep learning (DL) forecasting models, most of their skillful forecasting lead times are confined to daily subseasonal scale and monthly averaged values for up to six months, which drastically hinders their deployment for real-world applications, e.g., maritime routine planning for Arctic transportation and scientific investigation. Extending daily forecasts from subseasonal to seasonal (S2S) scale is scientifically crucial for operational applications. To bridge the gap between the forecasting lead time of current DL models and the significant daily S2S scale, we introduce IceBench-S2S, the first comprehensive benchmark for evaluating DL approaches in mitigating the challenge of forecasting Arctic sea ice concentration in successive 180-day periods. It proposes a generalized framework that first compresses spatial features of daily sea ice data into a deep latent space. The temporally concatenated deep features are subsequently modeled by DL-based forecasting backbones to predict the sea ice variation at S2S scale. IceBench-S2S provides a unified training and evaluation pipeline for different backbones, along with practical guidance for model selection in polar environmental monitoring tasks.

Figures (6)

• Figure 1: Variation of Arctic sea ice: (a) Annual trend of averaged Arctic sea ice concentration and sea ice extent over the last few decades. (b) Monthly average of sea ice concentration in September 1980 and 2023.
• Figure 2: IceBench-S2S. (a) Forecasting Approach: Deep Latent Space Compression for spatial representation, proposed generic framework Sea Ice Forecasting Engine and autoregressive roll-out prediction for S2S Arctic Sea Ice Forecasting, n and p represent the input and predicted time steps, respectively; (b) Key components include the model Training Environments, challenging Tasks, and comprehensive Evaluations.
• Figure 3: Main results of S2S forecasting. DL models along with conventional baselines, which are commonly used for validating numerical and statistical models, are evaluated under metrics outlined in Table \ref{['tab:metrics']} on the test dataset. Most of the DL models suffer from predictive skill loss once the forecasting lead time surpasses one month.
• Figure 4: S2S forecasting of calendar months over testing period. During the melting season, when sea ice concentration fluctuates the most, the performance of all models drops abruptly, indicating the unsolved challenge of finding predictive skills throughout the summertime.
• Figure 5: Comparison between S2S forecasting adopting the 7-day rolling approach and the 15-day rolling-based training strategy. The forecasting skill (ACC) of longer rolling windows is more stable than that of shorter ones.