[1]方　巍,王淏西.融合时空重构单元和Transformer的雷达回波外推算法[J].郑州大学学报(工学版),2025,46(05):137-144.[doi:10.13705/j.issn.1671-6833.2025.02.007]
　FANG Wei,WANG Haoxi.Radar Echo Extrapolation Algorithm Integrating Spatiotemporal Reconstruction Unit and Transformer[J].Journal of Zhengzhou University (Engineering Science),2025,46(05):137-144.[doi:10.13705/j.issn.1671-6833.2025.02.007]
点击复制

融合时空重构单元和Transformer的雷达回波外推算法()
分享到：

《郑州大学学报(工学版)》[ISSN:1671-6833/CN:41-1339/T]

卷:
46
期数:
2025年05期
页码:
137-144
栏目:
出版日期:
2025-08-10

文章信息/Info

Title:
Radar Echo Extrapolation Algorithm Integrating Spatiotemporal Reconstruction Unit and Transformer
文章编号:
1671-6833(2025)05-0137-08
作者:
方　巍1; 2; 3; 4;  王淏西1
1.南京信息工程大学 计算机学院,江苏 南京 210044;2.南京信息工程大学 软件学院,江苏 南京 210044;3.中国气象局武汉暴雨研究所 中国气象局流域强降水重点开放实验室/暴雨监测预警湖北省重点实验室,湖北 武汉 430205;4.中国气象科学研究院 灾害天气国家重点实验室,北京 100081
Author(s):
FANG Wei1; 2; 3; 4;  WANG Haoxi1
1. School of Computer Science, Nanjing University of Information Science & Technology, Nanjing 210044, China; 2.School of Software, Nanjing University of Information Science & Technology, Nanjing 210044, China; 3.China Meteorological Administration Basin Heavy Rainfall Key Laboratory/Hubei Key Laboratory for Heavy Rain Monitoring and Warning Research, Wuhan Research Institute of Heavy Rain, China Meteorological Administration, Wuhan 430205,China;4.State Key Laboratory of Severe Weather, Chinese Academy of Meteorological Sciences, Beijing 100081, China
关键词:
深度学习;  雷达回波外推;  Transformer;  时空重构单元;  全局平均池化
Keywords:
deep learning;  radar echo extrapolation;  Transformer;  spatiotemporal reconstruction unit;  global average pooling
分类号:
TP399
DOI:
10.13705/j.issn.1671-6833.2025.02.007
文献标志码:
A
摘要:
针对现有基于深度学习的雷达回波外推算法时空特征提取能力不足和建模能力有限的问题,提出了一种融合时空重构单元(SRU)和Transformer的雷达回波外推模型SRU-Former。首先,在模型的编码器和解码器中引入新设计的时空重构单元,通过分离、变换和重构的策略来提取雷达图像精细化时空特征;其次,在编码器和解码器之间引入Transformer的变体架构模型Poolformer,用全局平均池化操作代替自注意力机制,帮助模型对高度动态变化的雷达序列进行建模;最后,在江苏省气象雷达数据集和上海市气象雷达数据集上训练和测试,与目前主流的深度学习模型进行对比。实验结果表明:在2 h外推任务中,CSI、FAR、MSE和SSIM 4个指标均取得最优值,在江苏省数据集上CSI提升了0.020,上海市中数据集上CSI提升了0.048;SRU-Former能够有效提升模型的预报准确率,外推后期对强回波区域的捕捉更加精确,细节纹理更加丰富清晰。
Abstract:
Addressing the limitations of existing deep learning-based radar echo extrapolation algorithms in spatialtemporal feature extraction and long-term dependency modeling, a novel SRU-Former model that integrated spatialtemporal reconstruction unit (SRU) and Transformer was proposed for radar echo extrapolation. Firstly, a newly designed SRU was introduced into the model′s encoder and decoder to extract fine-grained spatiotemporal features from radar images via separation, transformation, and reconstruction. Secondly, a variant architecture model of Transformer, Poolformer, was introduced between the encoder and decoder, using global average pooling to replace the self-attention mechanism, thereby assisting the model in modeling highly dynamic radar sequences. Finally, SRU-Former was trained and tested on two meteorological radar datasets from Jiangsu Province and Shanghai City, respectively, and compared with current mainstream deep learning models. In the 2-hour extrapolation task, SRUFormer achieved optimal values in four metrics: CSI, FAR, MSE, and SSIM. Specifically, CSI was improved by 0.020 on the Jiangsu Province dataset and by 0.048 on the Shanghai City dataset. Experimental results showed that SRU-Former effectively improved model prediction accuracy, with more precise capture of strong echo regions and clearer detail textures in later extrapolation stages.

参考文献/References:

[1]薛丰昌, 章超钦, 王文硕, 等. 基于自注意力和门控循环神经网络的雷达回波外推算法研究[J]. 气象学报, 2024, 82(1): 127-135. 

XUE F C, ZHANG C Q, WANG W S, et al. Improving radar echo extrapolation algorithms based on selfattention and gated recurrent neural networks[J]. Acta Meteorologica Sinica, 2024, 82(1): 127-135. 
[2]黄旋旋, 朱科锋, 赵坤. 改进后TREC外推方法在台风临近降雨预报中的应用[J]. 气象科学, 2017, 37 (5): 610-618. 
HUANG X X, ZHU K F, ZHAO K. The improved TREC algorithm and its application to the precipitation now-casting for landfall typhoon[J]. Journal of the Meteorological Sciences, 2017, 37(5): 610-618. 
[3]DEL MORAL A, RIGO T, LLASAT M C. A radar-based centroid tracking algorithm for severe weather surveillance: identifying split/merge processes in convective systems[J]. Atmospheric Research, 2018, 213: 110-120. 
[4]吴剑坤, 陈明轩. 基于雷达回波区域跟踪算法的临近预报技术进展[J]. 气象科技, 2018, 46(5): 899-909. 
WU J K, CHEN M X. Advances in nowcasting techniques based on radar echo area tracking algorithm[J]. Meteorological Science and Technology, 2018, 46(5): 899-909. 
[5]SHI X J, CHEN Z R, WANG H, et al. Convolutional LSTM network: a machine learning approach for precipitation nowcasting[J]. Advances in Neural Information Processing Systems, 2015, 2015: 802-810. 
[6]WANG Y B, WU H X, ZHANG J J, et al. PredRNN: recurrent neural networks for predictive learning using spatiotemporal LSTMs[C]∥ Proceedings of the 31st International Conference on Neural Information Processing Systems. Long Beach: Curran Associates,2017: 879-888. 
[7]WANG Y B, GAO Z F, LONG M S, et al. PredRNN++: towards a resolution of the deep-in-time dilemma in spatiotemporal predictive learning[EB/OL]. (2018-04-17) [2024-10-16]. https:∥doi. org/10. 48550/arXiv. 1804.06300. 
[8]方巍, 庞林, 易伟楠. 基于深度时空融合网络的雷达回波外推模型[J]. 电子学报, 2023, 51(9): 2526-2538. 
FANG W, PANG L, YI W N. Radar echo extrapolation model based on deep spatio-temporal fusion neural network[J]. Acta Electronica Sinica, 2023, 51(9): 25262538. 
[9]刘颖, 杨鹏飞, 张立军, 等. 前馈神经网络和循环神经网络的鲁棒性验证综述[J]. 软件学报, 2023, 34 (7): 3134-3166. . 
LIU Y, YANG P F, ZHANG L J, et al. Survey on robustness verification of feedforward neural networks and recurrent neural networks[J]. Journal of Software, 2023, 34(7): 3134-3166. 
[10] RONNEBERGER O, FISCHER P, BROX T. U-Net: convolutional networks for biomedical image segmentation [C]∥Lecture Notes in Computer Science. Cham: Springer, 2015: 234-241. 
[11]王善昊, 胡志群, 王福增, 等. 基于ConvLSTM融合RMAPS-NOW数据的雷达回波外推研究[J]. 气象学报, 2024, 82(4): 554-567. 
WANG S H, HU Z Q, WANG F Z, et al. Extrapolation of radar echo based on ConvLSTM with fusion of RMAPSNOW data[J]. Acta Meteorologica Sinica, 2024, 82 (4): 554-567. 
[12] TREBING K, STAN `CZYK T, MEHRKANOON S. SmaAt-UNet: precipitation nowcasting using a small attention-UNet architecture[J]. Pattern Recognition Letters, 2021, 145: 178-186. 
[13] GAO Z Y, TAN C, WU L R, et al. SimVP: simpler yet better video prediction[C]∥2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). Piscataway: IEEE, 2022: 3160-3170. 
[14]李卫军, 张新勇, 高庾潇, 等. 基于门控时空注意力的视频帧预测模型[J]. 郑州大学学报(工学版), 2024, 45(1): 70-77, 121. 
LI W J, ZHANG X Y, GAO Y X, et al. Video frame prediction model based on gated spatio-temporal attention [J]. Journal of Zhengzhou University (Engineering Science), 2024, 45(1): 70-77, 121. 
[15] VASWANI A, SHAZEER N, PARMAR N, et al. Attention is all you need[EB/OL].(2017-07-12)[2024-1016].https:∥doi.org/10.48550/arXiv.1706.03762. 
[16]方巍, 齐媚涵. 基于深度学习的高时空分辨率降水临近预报方法[J]. 地球科学与环境学报, 2023, 45 (3): 706-718. 
FANG W, QI M H. Precipitation nowcasting method with high spatio-temporal resolution based on deep learning [J]. Journal of Earth Sciences and Environment, 2023, 45(3): 706-718. 
[17] LIU Z, LIN Y T, CAO Y, et al. Swin Transformer: hierarchical vision Transformer using shifted windows[C]∥ 2021 IEEE/CVF International Conference on Computer Vision. Piscataway: IEEE, 2021: 9992-10002. 
[18] BI K F, XIE L X, ZHANG H H, et al. Pangu-weather: a 3D high-resolution model for fast and accurate global weather forecast[EB/OL]. (2022-11-03)[2024-1016]. https:∥doi.org/10.48550/arXiv.2211.02556. 
[19] DALMAZ O, YURT M, CUKUR T. ResViT: residual vision transformers for multimodal medical image synthesis [J]. IEEE Transactions on Medical Imaging, 2022, 41(10): 2598-2614. 
[20] YU W H, LUO M, ZHOU P, et al. MetaFormer is actually what you need for vision[C]∥2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition.Piscataway:IEEE, 2022: 10809-10819. 
[21]魏明军, 王镆涵, 刘亚志, 等. 基于特征融合和混合注意力的小目标检测[J]. 郑州大学学报(工学版), 2024, 45(3): 72-79. 
WEI M J, WANG M H, LIU Y Z, et al. Small object detection based on feature fusion and mixed attention[J]. Journal of Zhengzhou University (Engineering Science), 2024, 45(3): 72-79. 
[22] LI J F, WEN Y, HE L H. SCConv: spatial and channel reconstruction convolution for feature redundancy[C]∥ 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition.Piscataway: IEEE, 2023: 6153-6162. 
[23] SMITH L N. Cyclical learning rates for training neural networks[C]∥2017 IEEE Winter Conference on Applications of Computer Vision. Piscataway: IEEE, 2017: 464-472. 
[24] LIU Z, MAO H Z, WU C Y, et al. A ConvNet for the 2020s[C]∥2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE, 2022: 11966-11976. 
[25] LI K C, WANG Y L, ZHANG J H, et al. UniFormer: unifying convolution and self-attention for visual recognition[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2023, 45(10): 12581-1260.

相似文献/References:

[1]袁航,钟发海,聂上上,等.基于卷积神经网络的道路拥堵识别研究[J].郑州大学学报(工学版),2019,40(02):21.[doi:10.13705/j.issn.1671-6833.2019.02.008]
　LUO Ronghui,YUAN Hang,ZHONG Fahai,et al.The Research of Traffic Jam Detection Based on Convolutional Neural Network[J].Journal of Zhengzhou University (Engineering Science),2019,40(05):21.[doi:10.13705/j.issn.1671-6833.2019.02.008]
[2]朱俊丞,杨之乐,郭媛君,等.深度学习在电力负荷预测中的应用综述[J].郑州大学学报(工学版),2019,40(05):12.[doi:10.13705/j.issn.1671-6833.2019.05.005]
　Zhu Juncheng,Young Joy,Guo Yuanjun,et al.A review of the application of deep learning in power load forecasting[J].Journal of Zhengzhou University (Engineering Science),2019,40(05):12.[doi:10.13705/j.issn.1671-6833.2019.05.005]
[3]黄文锋,徐珊珊,孙燚,等.基于多分辨率卷积神经网络的火焰检测[J].郑州大学学报(工学版),2019,40(05):79.[doi:10.13705/j.issn.1671-6833.2019.05.022]
　Huang Wenfeng,Susan Hsu,Sun Yi,et al.Fire Detection Based on Multi-resolution Convolution Neural Network in Various Scenes[J].Journal of Zhengzhou University (Engineering Science),2019,40(05):79.[doi:10.13705/j.issn.1671-6833.2019.05.022]
[4]陈义飞,郭胜,潘文安,等.基于多源传感器数据融合的三维场景重建[J].郑州大学学报(工学版),2021,42(02):81.[doi:10.13705/j.issn.1671-6833.2021.02.008]
　Chen Yifei,Guo Sheng,Pan Wenan,et al.3D Scene Reconstruction Based on Multi-source Sensor Data Fusion[J].Journal of Zhengzhou University (Engineering Science),2021,42(05):81.[doi:10.13705/j.issn.1671-6833.2021.02.008]
[5]李学相,曹淇,刘成明.基于无配对生成对抗网络的图像超分辨率重建[J].郑州大学学报(工学版),2021,42(05):1.[doi:10.13705/j.issn.1671-6833.2021.05.018]
　LI Xuexiang,CAO Qi,LIU Chengming.Image Super-resolution Based on No Match Generative Adversarial Network[J].Journal of Zhengzhou University (Engineering Science),2021,42(05):1.[doi:10.13705/j.issn.1671-6833.2021.05.018]
[6]王希鹏,李永,李智,等.融合图像深度的抗遮挡目标跟踪算法[J].郑州大学学报(工学版),2021,42(05):19.[doi:10.13705/j.issn.1671-6833.2021.05.011]
　Wang Xipeng,Li Yong,Li Zhi,et al.Anti-occlusion Target Tracking Algorithm Based on Image Depth[J].Journal of Zhengzhou University (Engineering Science),2021,42(05):19.[doi:10.13705/j.issn.1671-6833.2021.05.011]
[7]卢晨辉,冯硕,易爱华,等.基于深度学习的加油站销量预测与营销策略应用研究[J].郑州大学学报(工学版),2022,43(01):1.[doi:10.13705/j.issn.1671-6833.2022.01.014]
　LU Chenhui,FENG Shuo,YI Aihua,et al.Gasoline Station Sales Prediction Method Based on Deep Learning and Its Application of Promotion Strategy[J].Journal of Zhengzhou University (Engineering Science),2022,43(05):1.[doi:10.13705/j.issn.1671-6833.2022.01.014]
[8]陈浩杰,黄锦,左兴权,等.基于宽度&深度学习的基站网络流量预测方法[J].郑州大学学报(工学版),2022,43(01):7.[doi:10.13705/j.issn.1671-6833.2022.01.011]
　CHEN Haojie,HUANG Jin,ZUO Xingquan,et al.Base Station Network Traffic Prediction Method Based on Wide & Deep Learning[J].Journal of Zhengzhou University (Engineering Science),2022,43(05):7.[doi:10.13705/j.issn.1671-6833.2022.01.011]
[9]成科扬,荣兰,蒋森林,等.基于深度学习的遥感图像超分辨率重建技术综述[J].郑州大学学报(工学版),2022,43(05):8.[doi:10.13705/j.issn.1671-6833.2022.05.013]
　CHENG Keyang,RONG Lan,JIANG Senlin,et al.Overview of Methods for Remote Sensing Image Super-resolution Reconstruction Based on Deep Learning[J].Journal of Zhengzhou University (Engineering Science),2022,43(05):8.[doi:10.13705/j.issn.1671-6833.2022.05.013]
[10]院老虎,常玉坤,刘家夫.基于改进YOLOv5s的雾天场景车辆检测方法[J].郑州大学学报(工学版),2023,44(03):37.[doi:10.13705/j.issn.1671-6833.2023.03.005]
　YUAN Laohu,CHANG Yukun,LIU Jiafu.Vehicle Detection Method Based on Improved YOLOv5s in Foggy Scene[J].Journal of Zhengzhou University (Engineering Science),2023,44(05):37.[doi:10.13705/j.issn.1671-6833.2023.03.005]

更新日期/Last Update: 2025-09-19