一种融合多要素时空特征的数值预报风场订正模型  

A Model for Correcting Numerical Wind Field Forecast with Multifactor Spatiotemporal Features

作　　者：谢凯文 杨昊 邹茂扬[2] 徐虹[1] 马亚宇 XIE Kaiwen;YANG Hao;ZOU Maoyang;XU Hong;MA Yayu(School of Computer Science,Chengdu University of Information Technology,Chengdu 610225,China;College of Blockchain Industry,Chengdu University of Information Technology,Chengdu 610225,China)

机构地区：[1]成都信息工程大学计算机学院,四川成都610225 [2]成都信息工程大学区块链产业学院,四川成都610225

出　　处：《软件导刊》2024年第11期84-92,共9页Software Guide

基　　金：四川省科技计划项目(2022YFS0542,2023JDZH0034)。

摘　　要：目前,数值天气预报产品已广泛应用于气象预报业务中。针对数值预报模式本身不足导致的预报误差,为进一步提高其预报准确率,提出一种融合多要素时空特征的基于U-net和3D注意力机制的风场订正模型。采用该模型对中国气象局研发的国家气象中心GRAPES-3KM模式预报的近地面10 m风场进行偏差订正,以RMSE、MAE作为评价指标,与原数值预报产品、传统订正方法以及U-net、CU-net模型进行比较。实验结果表明,经过所提模型订正后的10 m纬向风RMSE相较原预报数据、LASSO回归、U-net、CU-net模型降低了4.19%~42.67%,MAE降低了6.06%~45.29%;10 m经向风RMSE指标降低了8.55%~41.35%,MAE降低了6.54%~40.82%;10 m全风速RMSE降低了6.14%~29.41%,MAE降低了1.5%~21.08%。所提模型相较对照模型有更好的订正效果,同时未出现订正结果过于平滑的情况。At present,numerical weather forecasting products have been widely used in meteorological forecasting operations.A wind field correction model based on U-net and 3D attention mechanism that integrates multiple spatiotemporal features is proposed to further improve the accuracy of numerical forecasting models due to their inherent shortcomings.This model is used to correct the deviation of the near ground 10 meter wind field forecast by the GRAPES-3KM model developed by the China Meteorological Administration.RMSE and MAE are used as evaluation indicators to compare with the original numerical forecast products,traditional correction methods,and U-net and CU net models.The experimental results show that the RMSE of the 10 m meridional wind corrected by the proposed model has decreased by 4.19%to 42.67%compared to the original forecast data,LASSO regression,U-net,and CU net models,and the MAE has decreased by 6.06%to 45.29%;The RMSE index of the 10 meter meridional wind decreased by 8.55%~41.35%,and the MAE decreased by 6.54%~40.82%;The RMSE of 10 m full wind speed decreased by 6.14%~29.41%,and the MAE decreased by 1.5%~21.08%.The proposed model has better correction effect com⁃pared to the control model,and there is no situation where the correction results are too smooth.

关 键 词：数值天气预报 深度学习 偏差订正 多要素融合 3D注意力 

分 类 号：TP181[自动化与计算机技术—控制理论与控制工程]