Using monthly and daily reanalysis data from the NCEP/NCAR and ERA-5 spanning 1980 to 2025, this study investigates the key preceding forcing factors influencing winter temperatures in the Bohai Sea and northern Yellow Sea (BSNYS) region. The analysis reveals that autumn sea ice anomalies in the Barents–Kara Seas serve as an important predictor for winter temperature anomalies in this region. Sea ice anomalies in this region typically persist from autumn to winter, continuously feeding back to the atmosphere and altering the temperature gradient. This induces lower-tropospheric baroclinic instability, which in turn drives atmospheric circulation adjustments through the feedback of transient eddies onto the mean flow, further strengthens the Eurasian (EU)-like teleconnection pattern, and ultimately affects the climate in the BSNYS region. Furthermore, the correlation between autumn Barents–Kara sea ice and winter temperature anomalies in the BSNYS region shifts from insignificant to significant when comparing the longer period (1950–2025) with the study period, likely due to the enhanced interannual variability of autumn sea ice in this region. This study reveals the key physical processes through which autumn Arctic sea ice influences the winter climate in the mid-latitude BSNYS region, and serves as a useful benchmark for seasonal prediction of winter temperatures in this region.

Even under a warming climate, winter sea ice in the Bohai Sea continues to threaten ships and offshore/coastal infrastructure. Reliable pre-season prediction of the overall wintertime sea ice condition in the Bohai Sea, as represented by the Bohai Sea Ice Grade (BSIG), is therefore important for disaster preparedness and mitigation. Based on the 1979–2024 BSIG record, this study compares seven statistical and AI-based seasonal prediction methods: analog year analysis, multiple linear regression, stepwise regression, Principal Component Regression, a cross-correlation-based regression model, support vector regression, and the Bayesian Ensemble Bohai Ice Grade Net (BE-BIGNet). As potential precursors, we considered sea ice extent in 14 Arctic regions together with 114 large-scale atmospheric and oceanic circulation indices. The results suggest substantial differences in predictive skill among the methods. Among the tested approaches, BE-BIGNet, which combines Bayesian regularization with bootstrap median ensembling, achieves strong full-period performance and stable skill during the independent test period, suggesting that it may provide a useful framework for operational BSIG forecasting in the Bohai Sea.