Meteorological conditions significantly influence the frequency and duration of air pollution events, making the prediction of seasonal variations of PM2.5 concentration crucial for air quality control. This study analyzed the spatiotemporal variations of PM2.5 concentration anomalies over the past 39 years (1980–2018) in winter (November to January) over eastern China based on the empirical orthogonal function (EOF) method. Regression analysis is conducted on external forcing factors such as sea ice, sea temperature, and snow cover in the pre-autumn (September to October) using the time series of the first three modes. Nine key factors were selected, which further led to establishing a model for predicting winter PM2.5 concentration in eastern China using the long short-term memory deep learning algorithm (LSTM). Independent verification revealed that the predicted and observed PM2.5 concentration distributions were consistent, with the absolute value of deviation within 15 μg·m−3 between 2016 and 2018. The correlation coefficients between the predicted and observed values were between 0.42 and 0.93 over eight key cities in the past 10 years (2009–2018). The contribution rates of the nine factors to PM2.5 concentration were calculated to explore their impact on PM2.5 concentration during winter. The Arctic sea ice (ASI) was found to be the key contributor to the winter PM2.5 concentration in eastern China. The predictors can be monitored in real time; hence, the model provides a real-time predictive tool, improving the prospects of predicting seasonal PM2.5 pollution, especially in vulnerable regions such as eastern China.