Mid- and long-term predictions of Arctic sea ice concentration (SIC) are important for the safety and security of the Arctic waterways. To date, SIC predictions mainly rely on numerical models, which have the disadvantages of a short prediction time and high computational complexity. Another common forecasting approach is based on a data-driven model, which is generally based on traditional statistical analysis or simple machine learning models, and achieves prediction by learning the relationships between data. Although the prediction performance of such methods has been improved in recent years, it is still difficult to find a balance between unstable model structures and complex spatio-temporal data. In this study, a classical statistical method and a deep learning model are combined to construct a data-driven rolling forecast model of SIC in the Arctic, named the EOF–LSTM–DNN (abbreviated as ELD) model. This model uses the empirical orthogonal function (EOF) method to extract the temporal and spatial features of the Arctic SIC, then the long short-term memory (LSTM) network is served as a feature extraction tool to effectively encode the time series, and, finally, the feature decoding is realized by the deep neural network (DNN). Comparisons of the model with climatology results, persistence predictions, other data-driven model results, and the hybrid coordinate ocean model (HYCOM) forecasts show that the ELD model has good prediction performance for the Arctic SIC on mid- and long-term time scales. When the forecast time is 100 days, the forecast root-mean-square error (RMSE), Pearson correlation coefficient (PCC), and anomaly correlation coefficient (ACC) of the ELD model are 0.2, 0.77, and 0.74, respectively.

Physics-based dynamical models can successfully predict short-term sea ice trends, but they struggle to provide reliable subseasonal sea ice predictions over shorter time periods and are not flexible enough to provide real-time/quasi-real-time predictions. Therefore, we use deep learning to establish a purely remote sensing data-driven Arctic sea ice prediction system, IceFormer. IceFormer is trained by high-quality Arctic reanalysis data and remote sensing observations. It can provide daily sea ice concentration (SIC) and sea ice thickness (SIT) predictions for the pan-Arctic region with 45 days lead time. We show that IceFormer advances lightweight multivariate forecasting of Arctic sea ice. Driven by remote sensing data, the prediction performance of IceFormer is far superior to traditional baseline models and machine learning models. The root mean square error (RMSE) and spatial anomaly correlation coefficient (SACC) of SIC (averaged within 45 days) are 6.62% and 0.80, respectively. The RMSE and SACC of SIT (averaged within 45 days) are 0.04m and 0.93, respectively. IceFormer can successfully capture the sea ice evolution on a seasonal scale (especially in the melting season) and the monthly average SACC is stable at around 0.70. After comparison, the SIC prediction performance of IceFormer is better than that of a Coupled Ensemble Numerical Forecast Model (SEAS5) from May to November. The information transfer analysis shows that the simultaneous prediction of SIC and SIT can effectively improve the predictability and explainability of sea ice.

Data-driven predictions of marine environmental variables are typically focused on single variables. However, in real marine environments, there are correlations among different oceanic variables. Additionally, sea–air interactions play a significant role in influencing the evolution of the marine environment. Both internal dynamics and external drivers contribute to these changes. In this study, a data-driven model is proposed using sea surface height anomaly (SSHA), sea surface temperature (SST), and sea surface wind (SSW) in the Bohai Sea. This model combines multivariate empirical orthogonal functions (MEOFs) with long and short-term memory (LSTM). MEOF analysis is used on the multivariate dataset of SSHA and SST, considering the correlation among sea surface variables. SSW is introduced as a predictor to enhance the predictability of the multivariate sea surface model. In the case of the Bohai Sea, the comparative tests of the model without wind field effect, the fully coupled model, and the proposed prediction model were carried out. MEOF analysis is employed in comparative experiments for oceanic variables, atmospheric variables, and combined atmospheric and oceanic variables. The results demonstrate that using wind field as a predictor can improve the forecast accuracy of SSHA and SST in the Bohai Sea. The root mean square errors (RMSE) for SSHA and SST in a 7-day forecast are 0.016 m and 0.3200 °C, respectively.

An interpretable deep inference forecasting model is designed to improve the forecasting capability of sea surface variables. By incorporating the air‐sea coupling mechanism as a dynamic constraint, the interpretability and forecasting performance of the model are improved. More specifically, our findings underscore the critical role of air‐sea interactions in forecasting sea surface variables, especially sea surface temperature (SST) variations induced by tropical cyclones (TCs). Additionally, Liang‐Kleeman information flow (IF), a causal inference method, is introduced to optimize the selection of predictors. Using satellite remote sensing data, our study demonstrates the model's capability in realizing sea surface multivariate forecasts in the South China Sea (SCS) within 10 days. More importantly, the experimental results prove the applicability of the model in both normal and extreme weather conditions, highlighting its effectiveness in enhancing sea surface variables forecasting.

On ensemble‐based coupled data assimilation, cross‐component parameter estimation (CPE), has not been as extensively developed and applied as weakly coupled state and parameter estimation along with cross‐component state estimation. This discrepancy is partially attributed to the lack of emphasis on the instantaneous response of coupled model states with respect to parameters across different components. We define so‐called response as the instantaneous parameter sensitivity (IPS). Under the framework of sequential assimilation, the prior information heavily relies on the IPS of coupled states with different time scales. Based on the IPS analysis for an intermediate coupled model, a series of twin experiments of state and parameter estimation are conducted, in which an IPS‐inspired adaptive inflation scheme for parameter ensemble is introduced. Results show that the success of a parameter estimation strategy is closely tied to the significant IPS of the observed state to the parameter targeted for optimization, as it maintains a high signal‐to‐noise ratio in the error covariance between parameter and prior state, thereby enhancing parameter estimation. An interesting finding in the context of IPS‐based CPE is: an atmospheric parameter can be successfully estimated by assimilating observations from slow‐varying oceanic component, but not vice versa. In comparison with cross‐component state estimation, successful CPE significantly enhances the estimation accuracy of coupled states by mitigating model bias.

This study introduces two distinct post-processing strategies to address systematic biases in sea surface temperature (SST) numerical forecasts, thereby enhancing SST predictive accuracy. The first strategy implements a spatiotemporal four-dimensional multi-grid analysis (4D-MGA) scheme within a three-dimensional variational (3D-Var) data assimilation framework. The second strategy establishes a hybrid deep learning architecture integrating empirical orthogonal function (EOF) analysis, empirical mode decomposition (EMD), and a backpropagation (BP) neural network (designated as EE–BP). The 4D-MGA strategy dynamically corrects systematic biases through a temporally coherent extrapolation of analysis increments, leveraging its inherent capability to characterize intrinsic temporal correlations in model error evolution. In contrast, the EE–BP strategy develops a bias correction model by learning the systematic biases of the SST numerical forecasts. Utilizing a satellite fusion SST dataset, this study conducted bias correction experiments that specifically addressed the daily SST numerical forecasts with 7-day lead times in the Kuroshio region south of Japan during 2017, systematically quantifying the respective error reduction potentials of both strategies. Quantitative verification reveals that EE–BP delivers enhanced predictive skill across all forecast horizons, achieving 18.1–22.7% root–mean–square error reduction compared to 1.2–9.1% attained by 4D-MGA. This demonstrates deep learning’s unique advantage in capturing nonlinear bias evolution patterns.