基于GRU深度学习的短时临近降水预报订正方法  

Short-term Precipitation Correction Based on GRU Deep Learning

作　　者：曾小团 邹晨曦 范娇 王庆国 黄大剑 梁潇 丁禹钦 谭肇 Zeng Xiaotuan;Zou Chenxi;Fan Jiao;Wang Qingguo;Huang Dajian;Liang Xiao;Ding Yuqin;Tan Zhao(Guangxi Meteorological Observatory,Nanning 530022;Beijing Spider Information Technology Co.,Ltd.,Beijing 100088)

机构地区：[1]广西壮族自治区气象台,南宁530022 [2]北京思湃德信息技术有限公司,北京100081

出　　处：《应用气象学报》2024年第5期513-525,共13页Journal of Applied Meteorological Science

基　　金：广西自然科学基金项目(2022GXNSFAA035482);桂气科重点项目(2024201)。

摘　　要：为提高短时临近降水预报准确率,提出一种订正广西对流尺度数值预报模式(GRAPES-GX)降水预报产品的深度学习方法。该方法通过神经网络对实况进行时空特征提取,以门控循环网络(GRU)为基础框架,针对降水产品进行改进,并用于GRAPES-GX降水预报产品订正。在此基础上,设计了大气物理规律适配模块,通过物理条件匹配机制订正模式预报降水强度与落区的系统性误差,增强训练样本中预报产品和实况的特征相关性,并协同优化模型参数,获得更优的订正效果。广西区域试验结果表明:订正模型在各预报时效、各降水强度等级的TS(threat score)评分均得到正技巧,总体TS技巧评分为2.21%。对于不低于0.1 mm·h^(-1)、不低于2 mm·h^(-1)、不低于7 mm·h^(-1)、不低于15 mm·h^(-1)、不低于25 mm·h^(-1)和不低于40 mm·h^(-1)降水强度预报TS技巧评分分别为5.67%、3.59%、2.18%、1.46%、1.01%和0.46%。0~2 h、2~4 h和4~6 h时效预报TS技巧评分分别为4.77%、1.28%和0.91%。To improve the accuracy of short-term precipitation forecasts,a deep learning method is proposed to correct numerical model precipitation forecast products.This method extracts spatiotemporal features from numerical model forecasts and observations using a neural network and performs corrections based on a gated recurrent unit(GRU)framework.Additionally,an atmospheric physics adaptor module is meticulously designed to address systematic errors in the intensity and displacement of numerical model forecast by leveraging physical condition mechanisms.The module plays a crucial role within the overarching model framework,which consists of three integrated components:Feature network,recurrent-revising network,and physical adaptor.The feature network extracts precipitation intensity,distribution,motion characteristics and other related atmospheric physical features from precipitation in situ and numerical model forecast data,serving as input to the recurrent-revising network.Recurrent-revising network utilizes a recurrent neural network structure to adjust grid point forecast results on a time-step basis.Deep neural networks are used to extract spatiotemporal variation features from numerical model forecast data and historical observations,learning systematic errors in the evolution processes to correct the precipitation magnitude and distribution.The physical adaptor is an atmospheric physics adaptation module,which preprocesses numerical model forecast data using frequency distribution fitting and distribution deviation correction methods.In Guangxi convective-scale model precipitation forecast data,when there are significant differences between numerous samples and the precipitation in situ,the feature correlation is low,making it a challenge to capture systematic error characteristics during neural network training.By preprocessing the samples with the physical adaptor,differences between forecasts and observations are reduced,enhancing feature correlation between training input datasets and observations,thus facil

关 键 词：预报订正 深度学习 门控循环网络 

分 类 号：P457.6[天文地球—大气科学及气象学]