A deep learning-based fusion correction model for cold wave forecasting over the Qingzang Plateau

In the past two decades, both numerical weather prediction (NWP) models and AI-based large meteorological models have significantly improved the accuracy of medium-range weather forecasting. However, due to inherent model uncertainties and inadequate simulations over complex terrain areas, these models systematically underestimate extreme weather intensity in topographically challenging regions like the Qingzang Plateau. This study evaluates the performance of traditional NWP models, large meteorological models, and multi-model ensemble forecasts in predicting near-surface air temperature based on the case study of the 14 December 2023 cold wave event. Results indicate that while traditional NWP and large meteorological models effectively capture spatial patterns of temperature anomalies, they consistently underestimate extreme cold intensity. Although the multi-model ensemble mean can improve the spatial correlation coefficient to some extent, its performance in predicting the scope and intensity of extreme low temperatures still needs improvement. To address these limitations, we propose a swin transformer fusion (STF) model that incorporates positional encoding. This framework enables synergistic optimization of multi-model forecasts by systematically extracting and integrating the strengths of NWP and large meteorological models at specific spatiotemporal scales. During the cold wave's peak phase, STF reduces the forecast root mean square error by up to 39.62%, with notable improvements particularly in error-sensitive regions. The model's dynamic preference-error hedging mechanism effectively combines the multi-model advantages, enhancing both forecast accuracy and operational robustness for extreme weather events. This work advances cold wave early warning systems for high-altitude regions, introduces novel methodologies for extreme weather prediction, and demonstrates promising practical applications.