基于高分辨率数值预报和深度学习的地面气温预报研究  

Research on Surface Temperature Prediction Based on High-Resolution Numerical Prediction Products and Deep Learning

作　　者：李浙华 肖安 郑丽君[1] LI Zhehua;XIAO An;ZHENG Lijun(Shangrao Meteorological Bureau of Jiangxi Province,Shangrao 334000,Jiangxi,China;Jiangxi Meteorological Observatory,Nanchang 330096,Jiangxi,China;Weather Forecast open laboratory of Jiangxi Meteorological Bureau,Nanchang 330096,Jiangxi,China)

机构地区：[1]江西省上饶市气象局,江西上饶334000 [2]江西省气象台,江西南昌330096 [3]江西省气象局天气预报开放实验室,江西南昌330096

出　　处：《高原气象》2024年第2期464-477,共14页Plateau Meteorology

基　　金：中国气象局创新发展专项(CXFZ2021Z012);江西省气象局重点项目(JX2020Z04);江西省气象局面上项目(JX2020M19);江西省气象局预报员专项(JX2022Y01)。

摘　　要：基于2020-2021年的中国气象局(CMA)陆面数据同化系统(CLDAS)逐小时地面气温(T2m)产品,融合CMA上海快速更新循环数值预报(CMA-SH3)的T2m预报数据,构建深度学习语义分割模型(MT-Cunet),实现逐小时滚动更新的24 h T2m网格预报,并对2022年预报结果进行了检验评估。结果表明,在研究范围内,MT-Cunet在3~9 h时效订正效果最好,平均MAE和平均RMSE分别降低42.4%、40.89%;10~24 h时效的订正效果较好,平均MAE和平均RMSE分别下降26.7%、26.3%。低温(≤0℃)和高温(≥35℃)事件检验评估表明,MT-Cunet在高温预报整体表现为正偏差,而低温整体为负偏差,但误差幅度远低于CMA-SH3;空间尺度上,MT-Cunet能较大幅度减少复杂地形下的T2m预报误差,降低CMA-SH3的MAE离散度,使预报误差分布较为稳定。通过对2022年2月和3月的区域性增温、寒潮过程分别进行检验评估发现,MT-Cunet能较好预报出增(降)温转折时间和增(降)温幅度。在增温和寒潮过程中,MT-Cunet的MAE比CMA-SH3分别降低28.9%和33.8%,表明MT-Cunet模型在转折性天气过程中同样具有较好的预报能力。因此,利用可以快速增加预报样本数量的快速更新循环数值预报,经过语义分割深度学习模型客观方法订正,就能较大幅度降低数值模式预报误差,解决常规数值预报由于数据量太少,深度学习训练效果较差的问题,这对充分利用国产模式资源,更广泛地开展国产模式后处理和应用提出了一个新的思路。This study utilized the 2020-2021 China Meteorological Administration(CMA)Land Data Assimilation System(CLDAS)hourly surface air temperature(T2m)product in combination with the T2m forecast data from the CMA Shanghai Rapid Update Cycle Numerical Forecast(CMA-SH3).A deep learning semantic segmentation model called MT-Cunet was developed to achieve a 24-hour T2m grid forecast that is updated on an hourly basis.The forecast results for 2022 were then tested and evaluated.Results showed that:MT-Cunet has demonstrated the most effective revision during the 3~9 h time horizon in the study range.It shows a significant reduction of 42.4%and 40.9%in the mean MAE and mean RMSE,respectively.The revision effect during the 10~24 h time horizon is also noteworthy,with a reduction of 26.7%and 26.3%in the mean MAE and mean RMSE,respectively.When evaluating low-temperature(≤0℃)and high-temperature(≥35℃)events,MT-Cunet exhibits a positive bias in high-temperature forecasts while showing a negative bias in low-temperature forecasts,and the magnitude of error is much smaller compared to CMA-SH3.On the spatial scale,MT-Cunet can substantially reduce the T2m forecast error in complex terrain and decrease the MAE dispersion of CMA-SH3,resulting in a more stable distribution of forecast errors.By examining and assessing the regional warming and cold wave processes in February and March 2022,it has been found that MT-Cunet demonstrates superior capability in predicting the timing and magnitude of temperature increases and decreases.In both warming and cold wave processes,the MAE of MT-Cunet is 28.9%and 33.8%lower than that of CMA-SH3,respectively.This suggests that the MT-Cunet model exhibits improved forecasting skills in transitional weather processes.Therefore,by employing a fast-updating cycle numerical model,it is possible to rapidly increase the number of forecast samples.Additionally,by refining the objective method of the semantic segmentation deep learning model,this approach effectively addresses the issue of poor perfo

关 键 词：CMA-SH3 CLDAS 2 m地面温度 偏差订正 深度学习 

分 类 号：P456.1[天文地球—大气科学及气象学]