利用深度学习开展偏振雷达定量降水估测研究  

A study on polarization radar quantitative precipitation estimation using deep learning

作　　者：皇甫江 胡志群[2,3] 郑佳锋[1] 朱永杰 尹晓燕 左园园 HUANGFU Jiang;HU Zhiqun;ZHENG Jiafeng;ZHU Yongjie;YIN Xiaoyan;ZUO Yuanyuan(School of Atmospheric Sciences,Chengdu University of Information Technology,Chengdu 610225,China;Chinese Academy of Meteorological Sciences,Beijing 100081,China;Key Laboratory of Atmosphere Sounding,CMA,Chengdu 610225,China)

机构地区：[1]成都信息工程大学大气科学学院,成都610225 [2]中国气象科学研究院灾害天气国家重点实验室,北京100081 [3]中国气象局大气探测重点开放实验室,成都610225

出　　处：《气象学报》2022年第4期565-577,共13页Acta Meteorologica Sinica

基　　金：国家重点研发计划项目(2019YFC1510304);广东省重点领域研发计划项目(2020B1111200001);中国气象局大气探测重点开放实验室开放课题(U2021Z05);青年科学基金项目(42105141)。

摘　　要：利用2018—2020年经偏振升级改造后的广州S波段双偏振雷达(CINRAD/SAD)82892个体扫的0.5°仰角数据,以及雷达100 km探测范围内1109个雨量站共计538560个分钟雨量数据,分别构建了单参量、三参量雷达定量降水估测(QPE)深度学习网络架构(Z-Rnet、K_(DP)-Rnet、Pol-Rnet),并以K_(DP)=0.5°/km为阈值分别训练得到大雨、小雨、总体等9个定量降水估测模型。在常用的均方误差作为损失函数的基础上,对不同降水强度采用不同权重提出了自定义损失函数,并利用比率偏差、相对偏差、均方差、平均绝对误差和平均相对误差作为评价指标对模型进行评估。通过对以积层混合云为主、以对流云为主和以层状云为主的3次降水过程的模型验证结果表明,利用深度学习训练的模型有较好的定量降水估测效果,区分雨强的小雨、大雨模型比不区分雨强的总体模型的效果要好。采用自定义损失函数模型效果更好,其均方差、平均绝对误差和平均相对误差分别较采用传统均方误差损失函数提升了8.62%、12.52%、16.34%。自定义损失函数中,采用Z_(H)-Z_(DR)-K_(DP)三参量网络架构训练得到的定量降水估测模型效果最好,其均方差、平均绝对误差和平均相对误差分别较采用Z_(H)的单参量Z-Rnet架构提升6.82%、8.43%、7.22%;较采用K_(DP)的单参量K_(DP)-Rnet架构提升12.33%、17.61%、17.26%。Using 82892 volume scanning data at 0.5°elevation angle from the S-band dual polarization radar deployed in Guangzhou(CINRAD/SAD)and 5385601-minute rainfall data from 1109 stations within the radar's 100 km detection range from 2018 to 2020,three deep learning networks(Z-Rnet,K_(DP)-Rnet and Pol-Rnet)are designed for radar quantitative precipitation estimation(QPE)based on single and three radar moments,respectively.Furthermore,based on the three networks and with K_(DP)=0.5°/km as the threshold to divide the training dataset as heavy,light,and all rain data,a total of 9 QPE models are built.On the basis of using the common mean square error as the loss function,a self-defined loss function is proposed by adjusting the weight for different precipitation intensity.Several indexes including ratio deviation,relative deviation,mean square error(MSE),mean absolute error(MAE)and mean relative error(MRE)are then used to evaluate the performance of the models.Finally,three precipitation processes that are respectively dominated by cumulus-stratiform mixed,convective and stratiform clouds are used to test the effect of QPE.The results suggest that the models fitted by deep learning have better QPE results,and the QPE accuracy for the data that are divided into heavy and light rain is better than that for the data that includes all types of rainfall.The MSE,MAE and MRE with the self-defined loss function are improved by 8.62%,12.52%,16.34%than that with the traditional mean square error loss function.Among them,the QPE with Pol-Rnet,i.e.,Z_(H),Z_(DR)and K_(DP) are used as input factors,is the best,and the above indexes are respectively increased by 6.82%,8.43%,7.22%than that with Z-Rnet,and by 12.33%,17.61%,17.26%than that with K_(DP)-Rnet.

关 键 词：深度学习 偏振雷达 定量降水估测 单参量架构 三参量架构 

分 类 号：P415[天文地球—大气科学及气象学]