Automatic Identification of Clear-Air Echoes Based on Millimeter-wave Cloud Radar Measurements  

作　　者：Ling YANG Yun WANG Zhongke WANG Qian YANG Xingang FAN Fa TAO Xiaoqiong ZHEN Zhipeng YANG 

机构地区：[1]Electronic Engineering College,Chengdu University of Information Technology,Chengdu 610225,China [2]Information Security Engineering College,Chengdu University of Information Technology,Chengdu 610225,China [3]Department of Geography and Geology,Western Kentucky University,Bowling Green,KY 42101,USA [4]Institute of Atmospheric Physics,Chinese Academy of Sciences,Beijing 100029,China [5]CMA Key Laboratory of Atmospheric Sounding,Chengdu University of Information Technology,Chengdu 610225,China [6]Collaborative Innovation Center on Forecast and Evaluation of Meteorological Disasters,Nanjing University of Information Science and Technology,Nanjing,210044,China [7]Meteorological Observation Centre,CMA,Beijing 100081,China

出　　处：《Advances in Atmospheric Sciences》2020年第8期912-924,共13页大气科学进展（英文版）

基　　金：supported by the National Key R&D Program of China(Grant No.2018YFC1506605);Sichuan Provincial Department of Education Scientific research projects(Grant No.16ZB0211);Chengdu University of Information Technology research and development projects(Grant No.CRF201705)。

摘　　要：Millimeter-wave cloud radar(MMCR)provides the capability of detecting the features of micro particles inside clouds and describing the internal microphysical structure of the clouds.Therefore,MMCR has been widely applied in cloud observations.However,due to the influence of non-meteorological factors such as insects,the cloud observations are often contaminated by non-meteorological echoes in the clear air,known as clear-air echoes.It is of great significance to automatically identify the clear-air echoes in order to extract effective meteorological information from the complex weather background.The characteristics of clear-air echoes are studied here by combining data from four devices:an MMCR,a laser-ceilometer,an L-band radiosonde,and an all-sky camera.In addition,a new algorithm,which includes feature extraction,feature selection,and classification,is proposed to achieve the automatic identification of clear-air echoes.The results show that the recognition algorithm is fairly satisfied in both simple and complex weather conditions.The recognition accuracy can reach up to 95.86%for the simple cases when cloud echoes and clear-air echoes are separate,and 88.38%for the complicated cases when low cloud echoes and clear-air echoes are mixed.

关 键 词：millimeter-wave cloud radar clear-air echoes neural network laser ceilometer all-sky camera feature extraction feature selection 

分 类 号：P412.25[天文地球—大气科学及气象学]