MDA-MIM:一种融合多尺度特征与双重注意力机制的雷达回波图预测模型  

MDA-MIM:a radar echo map prediction model integrating multi-scale feature fusion and dual attention mechanism

作　　者：胡强[1] 高雅婷 尹宾礼 渠连恩 HU Qiang;GAO Yating;YIN Binli;QU Lianen(School of Information Science and Technology,Qingdao University of Science and Technology,Qingdao 266000,China;Qingdao Radio and Television Station,Qingdao 266000,China;College of Information Engineering,Xinjiang Institute of Engineering,Urumqi 830023,China)

机构地区：[1]青岛科技大学信息科学技术学院,山东青岛266000 [2]青岛广播电视台,山东青岛266000 [3]新疆工程学院信息工程学院,新疆乌鲁木齐830023

出　　处：《通信学报》2025年第3期248-257,共10页Journal on Communications

基　　金：国家自然科学基金资助项目(No.61973180);山东省重点研发计划(软科学)基金资助项目(No.2023RKY01009)。

摘　　要：为提升雷达回波图中时空特征的提取质量,提出了一种基于多尺度特征融合和双重注意力机制的MIM改进(MDA-MIM)模型。该模型基于空洞卷积实现多尺度特征提取与融合。通过在MIM模型中的非平稳模块集成自注意力机制,调整不同时间步长和空间位置的权重,更精确地捕捉雷达回波数据中的非平稳性特征。在平稳模块引入局部注意力机制,以聚焦于局部区域内的特征关联,增强对平稳性特征的捕捉能力。真实数据集上的实验结果表明,MDA-MIM具有优秀的预测性能,在MSE、MAE、SSIM和PSNR等指标上均优于对比模型。To obtain high-quality spatiotemporal features from radar echo maps,an improved MIM(memory in memory)model,MDA-MIM(multi-scale feature fusion and dual attention mechanism MIM)was proposed.Multi-scale feature fusion and a dual attention mechanism were incorporated in MDA-MIM.Dilated convolution was used to extract and integrate multi-scale features.To better capture the non-stationary characteristics of radar echo data,a self-attention mechanism was introduced into the non-stationary module of the MIM model,dynamically adjusting the weights of different time steps and spatial positions.Meanwhile,a local attention mechanism was incorporated into the stationary module,enabling the model to focus on feature correlations within local regions and enhance its ability to extract stationary features.Experiments conducted on real-world datasets demonstrate that MDA-MIM achieves state-of-the-art predictive performance,consistently outperforming baseline models across multiple evaluation metrics,including MSE,MAE,SSIM,and PSNR.

关 键 词：雷达回波图 时空预测 注意力机制 多尺度特征 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]