面向降雨预报的雷达回波预测序列外推方法  

Research on extrapolation of radar echo prediction sequence for rainfall prediction

作　　者：罗健文 邹茂扬[1] 杨昊[1] 陈敏 杨康权[3] Luo Jianwen;Zou Maoyang;Yang Hao;Chen Min;Yang Kangquan(Chengdu University of Information Technology,Chengdu 610225,China;Chinese Academy of Sciences,Chengdu Institute of Computer Applications,Chengdu 610041,China;Sichuan Meteorological Observatory,Chengdu 610072,China)

机构地区：[1]成都信息工程大学,成都610225 [2]中国科学院成都计算机应用研究所,成都610041 [3]四川省气象台,成都610072

出　　处：《计算机应用研究》2024年第4期1138-1142,共5页Application Research of Computers

基　　金：四川省自然科学基金资助项目(2023NSFSC0482);四川省科技计划资助项目(2022YFS0542);成都信息工程大学科技创新能力提升计划资助项目(KYTD202324)。

摘　　要：雷达回波外推方法广泛应用于降雨预报中。针对雷达回波中的预测精度不够高的问题,提出了一种基于循环神经网络的深度学习模型DIPredRNN。该模型通过引入空间和通道的双注意力机制,将长时间的时间信息和通道信息结合起来,提高了时间记忆的长期依赖;通过引入隐藏状态和输入的交互框架,保留了更多的特征,提高了时间记忆的短期依赖。该模型在HKO-7数据集和四川数据集上同经典模型以及诸多先进模型进行实验对比,该模型从外推图像、MSE、SSIM、CSI-30~50 dbz多个指标对比中都取得最佳效果。实验证明了DIPredRNN提高了雷达回波预测效果,拥有先进的性能。The radar echo extrapolation method is widely used in rainfall forecasting.Addressing the issue of insufficient prediction accuracy in radar echoes,this paper proposed a deep learning model DIPredRNN based on recurrent neural networks.This model combined long-term temporal and channel information by introducing a dual attention mechanism of space and channel,improved the long-term dependence of time memory.By introducing an interactive framework of hidden states and inputs,it retained more features and improved the short-term dependence of temporal memory.This model was experimentally compared with classical models and many advanced models on the HKO-7 and Sichuan datasets.The model achieved the best results in comparing multiple indicators such as extrapolated images,MSE,SSIM,CSI-30~50 dbz.The experiment proves that the proposed DIPredRNN network improves the radar echo prediction performance and has advanced performance.

关 键 词：雷达回波外推 深度学习 循环神经网络 

分 类 号：TN957.51[电子电信—信号与信息处理] P457.6[电子电信—信息与通信工程]