气象学报2026，Vol.84Issue(3)：550-561,12.DOI:10.11676/qxxb2026.20250099
青藏高原寒潮预报的深度学习融合订正模型
A deep learning-based fusion correction model for cold wave forecasting over the Qingzang Plateau
摘要
Abstract
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.关键词
深度学习/青藏高原/寒潮/天气预报Key words
Deep learning/Qingzang Plateau/Cold wave/Weather forecasting分类
天文与地球科学引用本文复制引用
王妍凤,赵博文,黄平,葛书豪..青藏高原寒潮预报的深度学习融合订正模型[J].气象学报,2026,84(3):550-561,12.基金项目
国家自然科学基金项目(42425504、42205035)、中国博士后科学基金项目(2023T160632、2022M723096)、中国科学院稳定支持基础研究领域青年团队计划(YSBR-137)、上海市科技计划项目(23DZ1204704). （42425504、42205035）
