CEMA-LSTM:Enhancing Contextual Feature Correlation for Radar Extrapolation Using Fine-Grained Echo Datasets  

作　　者：Zhiyun Yang Qi Liu HaoWu Xiaodong Liu Yonghong Zhang 

机构地区：[1]School of Computer and Software,Engineering Research Center of Digital Forensics,Ministry of Education,Nanjing University of Information Science and Technology,Nanjing,210044,China [2]School of Computing,Edinburgh Napier University,Edinburgh,EH105DT,UK [3]School of Automation,Nanjing University of Information Science Technology,Nanjing,210044,China

出　　处：《Computer Modeling in Engineering & Sciences》2023年第4期45-64,共20页工程与科学中的计算机建模（英文）

基　　金：funding from the Key Laboratory Foundation of National Defence Technology under Grant 61424010208;National Natural Science Foundation of China(Nos.62002276,41911530242 and 41975142);5150 Spring Specialists(05492018012 and 05762018039);Major Program of the National Social Science Fund of China(Grant No.17ZDA092);333 High-LevelTalent Cultivation Project of Jiangsu Province(BRA2018332);Royal Society of Edinburgh,UK andChina Natural Science Foundation Council(RSE Reference:62967)_Liu)_2018)_2)under their Joint International Projects Funding Scheme and Basic Research Programs(Natural Science Foundation)of Jiangsu Province(BK20191398 and BK20180794).

摘　　要：Accurate precipitation nowcasting can provide great convenience to the public so they can conduct corresponding arrangements in advance to deal with the possible impact of upcoming heavy rain.Recent relevant research activities have shown their concerns on various deep learning models for radar echo extrapolation,where radar echo maps were used to predict their consequent moment,so as to recognize potential severe convective weather events.However,these approaches suffer from an inaccurate prediction of echo dynamics and unreliable depiction of echo aggregation or dissipation,due to the size limitation of convolution filter,lack of global feature,and less attention to features from previous states.To address the problems,this paper proposes a CEMA-LSTM recurrent unit,which is embedded with a Contextual Feature Correlation Enhancement Block(CEB)and a Multi-Attention Mechanism Block(MAB).The CEB enhances contextual feature correlation and supports its model to memorize significant features for near-future prediction;the MAB uses a position and channel attention mechanism to capture global features of radar echoes.Two practical radar echo datasets were used involving the FREM and CIKM 2017 datasets.Both quantification and visualization of comparative experimental results have demonstrated outperformance of the proposed CEMA-LSTMover recentmodels,e.g.,PhyDNet,MIM and PredRNN++,etc.In particular,compared with the second-rankedmodel,its average POD,FAR and CSI have been improved by 3.87%,1.65%and 1.79%,respectively on the FREM,and by 1.42%,5.60%and 3.16%,respectively on the CIKM 2017.

关 键 词：Radar echo extrapolation attention mechanism long short-term memory deep learning 

分 类 号：TN959[电子电信—信号与信息处理]