自注意力机制改进U-Net网络的强积冰云层预测

doi:10.3778/j.issn.1002-8331.2104-0106

摘要/Abstract

摘要： 针对传统时空序列的雷达回波外推方法易出现低层信息及强回波区信息丢失的问题，提出了一种适用于任意尺寸特征图输入的新型GC-ResUNet网络预测模型。模型主框架采用U-Net神经网络解决了低层信息丢失的问题，同时引入GCNet自注意力机制解决了强回波区特征丢失的问题。以2018—2020年间沿海雷达回波拼图为数据样本，以临界成功指数、探测率、虚警率为评价标准进行实验。仿真结果表明，该模型对于未来1?h内的中低强度回波的预测成功率相比于传统光流法提升20%左右，对于强回波的预测成功率提升33%~70%。

关键词: GC-ResUNet, 雷达回波外推, 自注意力机制, 积冰云层预测, 时空序列预测

Abstract: Aiming at the problem that the traditional method of radar echo extrapolation of spatio-temporal series is easy to lose the information of low level and strong echo region, a new prediction model of GC-ResUNet network is proposed, which is suitable for the input of feature images of any size. The main framework of the model uses U-Net neural network to solve the problem of information loss at the lower level, and introduces GCNet self-attention mechanism to solve the problem of feature loss in the strong echo region. Taking the 2018—2020 coastal radar echo puzzle as the data sample, and the critical success index, detection rate and false alarm rate as the evaluation criteria, the experiment is carried out. The simulation results show that compared with the traditional optical flow method, the prediction success rate of the model for medium and low intensity echoes within 1 h in the future is improved by about 20%, and the prediction success rate for strong echoes is improved by 33%~70%.

Key words: GC-ResUNet, radar echo extrapolation, self-attention mechanism, ice cloud prediction, spatio-temporal series prediction

翟辰飞, 董文瀚, 张晓敏, 李大东, 陈晓军. 自注意力机制改进U-Net网络的强积冰云层预测[J]. 计算机工程与应用, 2022, 58(22): 297-304.

ZHAI Chenfei, DONG Wenhan, ZHANG Xiaomin, LI Dadong, CHEN Xiaojun. Prediction of Strong Cumulus Clouds by Improved U-Net Network and Self-Attention Mechanism[J]. Computer Engineering and Applications, 2022, 58(22): 297-304.

参考文献

[1] 桂业伟，周志宏，李颖晖，等.关于飞机结冰的多重安全边界问题[J].航空学报，2017，38（2）：6-17.
GUI Y W，ZHOU Z H，LI Y H，et al.Multiple safety boundaries protection on aircraft icing[J].Acta Aeronautica et Astronautica Sinica，2017，38（2）：6-17.
[2] 丁建军，胡文东，赵光平，等.基于雷达跟踪外推及Google Maps的强对流天气临近预报[J].气象科技，2011，39（6）：779-784.
DING J J，HU W D，ZHAO G P，et al.Severe weather nowcasting based on radar tracking and extrapolation and Google Maps[J].Meteorological Science and Technology，2011，39（6）：779-784.
[3] 曹春燕，陈元昭，刘东华，等.光流法及其在临近预报中的应用[J].气象学报，2015，73（3）：471-480.
CAO C Y，CHEN Y Z，LIU D H，et al.The optical flow method and its application to nowcasting[J].Acta Meteorologica Sinica，2015，73（3）：471-480.
[4] SHI X J，CHEN Z R，WANG H，et al.Convolutional LSTM network：a machine learning approach for precipitation nowcasting[C]//Proceedings of the 28th International Conference on Neural Information Processing Systems，Montreal，2015：802-810.
[5] WANG Y，ZHANG J，ZHU H，et al.Memory in memory：a predictive neural network for learning higher-order non-stationarity from spatiotemporal dynamics[C]//Proceedings of the 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition，Long Beach，2019：9154-9162.
[6] XU Z，DU J，WANG J J，et al.Satellite image prediction relying on GAN and LSTM neural networks[C]//Proceedings of the 2019 IEEE International Conference on Communications，2019：1-6.
[7] GENG Y A，LI Q Y，LIN T Y，et al.LightNet：a dual spatiotemporal encoder network model for lightning prediction[C]//Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining，2019：2439-2447.
[8] SHI X J，GAO Z H，LAUSEN L，et al.Deep learning for precipitation nowcasting：a benchmark and a new model[C]//Proceedings of the 31st International Conference on Neural Information Processing Systems，Red Hook，2017：5622-5632.
[9] RONNEBERGER O，FISCHER P，BROX T.U-Net：convolutional networks for biomedical image segmentation[C]//LNCS 9351：Proceedings of the 18th International Conference on Medical Image Computing and Computer-Assisted Intervention，Munich，2015：234-241.
[10] VASWANI A，SHAZEER N，PARMAR N，et al.Attention is all you need[C]//Proceedings of the 31st International Conference on Neural Information Processing Systems，Red Hook，2017：6000-6010.
[11] 梁海河，张沛源，牛昉，等.全国天气雷达数据处理系统[J].应用气象学报，2002（6）：749-754.
LIANG H H，ZHANG P Y，NIU F，et al.China operational weather radar data processing system[J].Journal of Applied Meteorological Science，2002（6）：749-754.
[12] 李红艳，李春庚，安居白，等.注意力机制改进卷积神经网络的遥感图像目标检测[J].中国图象图形学报，2019，24（8）：1400-1408.
LI H Y，LI C G，AN J B，et al.Attention mechanism improves CNN remote sensing image object detection[J].Journal of Image and Graphics，2019，24（8）：1400-1408.
[13] 李华，柳云雷，韩冰，等.天气雷达回波信号去噪中小波分析应用[J].气象科技，2015，43（2）：196-201.
LI H，LIU Y L，HAN B，et al.Application of wavelet analysis in denoising of weather radar echo signals[J].Meteorological Science and Technology，2015，43（2）：196-201.
[14] 苏健民，杨岚心，景维鹏.基于U-Net的高分辨率遥感图像语义分割方法[J].计算机工程与应用，2019，55（7）：207-213.
SU J M，YANG L X，JING W P.U-Net based semantic segmentation method for high resolution remote sensing image[J].Computer Engineering and Applications，2019，55（7）：207-213.
[15] 鞠思博，徐晶，李岩芳.基于自注意力机制的文本生成单目标图像方法[J].计算机工程与应用2022，58（3）：249-258.
JU S B，XU J，LI Y F.Text-to-single image method based on self-attention[J].Computer Engineering and Applications，2022，58（3）：249-258.
[16] CAO Y，XU J R，LIN S，et al.GCNet：non-local networks meet squeeze-excitation networks and beyond[C]//Proceedings of the 2019 IEEE/CVF International Conference on Computer Vision Workshops，Seoul，2019：1971-1980.