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.

The East Asian summer monsoon (EASM) exhibits complex intraseasonal variability under global warming, with critical implications for regional hydroclimate. Using simulations from the Coupled Model Intercomparison Project Phase 6 (CMIP6) and Carbon Dioxide Removal Model Intercomparison Project (CDRMIP), this study investigates EASM rainfall responses to symmetric CO₂ forcing under equivalent global mean warming of 3°C. The results reveal pronounced asymmetry: EASM rainfall over the Meiyu region (25°–40°N, 105°–150°E) is significantly enhanced during CO₂ ramp-down compared to ramp-up, primarily driven by intensified late summer (July–August) rainfall, while early-summer (May–June) rainfall shows slight decreases, resulting in a delayed annual cycle of EASM rainfall over the Meiyu region. Moisture budget analysis indicates that dynamic effects associated with monsoon circulation changes dominate this intraseasonal asymmetry, as thermodynamic moisture contributions are nearly identical between the two periods under equivalent global-mean warming. The distinct intraseasonal dynamics arise from contrasting sea surface temperature evolution in the Indo-western North Pacific region. In late summer, enhanced warming over the northern tropical Indian Ocean generates easterly wind changes across the western North Pacific, subsequently establishing an anticyclonic circulation. These circulation changes strengthen southwesterly moisture transport and ascending motion over the Meiyu region, amplifying late summer rainfall.