Dynamic Residual Attention UNet for Precipitation Nowcasting Based on WGAN

doi:10.1109/CAC59555.2023.10450446

IR > 图书馆

	Dynamic Residual Attention UNet for Precipitation Nowcasting Based on WGAN
	Li, Ce; Huang, Fan; Zhang, Jianwei; Ma, Lin; Chen, Huizhong; Li, Chaoyue
	2023
会议名称	2023 China Automation Congress, CAC 2023
会议录名称	Proceedings - 2023 China Automation Congress, CAC 2023
页码	6265-6270
会议日期	November 17, 2023 - November 19, 2023
会议地点	Chongqing, China
出版者	Institute of Electrical and Electronics Engineers Inc.
摘要	In recent years, using radar echo maps for precipitation nowcasting has been a research hotspot. How to use deep learning methods to forecast precipitation is a challenge. Radar echo map contains rich temporal and spatial information, capturing the location distribution and intensity characteristics of radar echo is a key problem in precipitation prediction. To tackle these challenges, the paper presents a novel approach called the Dynamic Residual Attention UNet model(DRA-UNet). This model incorporates Decoupled Dynamic Filter(DDF) and Dynamic Residual Attention Modules(DRAM) while leveraging the Wasserstein GAN training strategy to perform generative adversarial training. A decoupled Dynamic Filter can adaptively adjust the convolution kernel in the feature extraction stage, effectively reducing blank areas in the feature maps. By exploring the correlation between residual paths and input image statistics, and appropriately weighting each residual path, the model's focus on precipitation positions is enhanced. Moreover, the utilization of the Wasserstein GAN(WGAN) strategy during model training enhances the image generation quality when facing the discriminator in adversarial training. This advancement ensures that the model's outputs closely approximate real results, leading to further improvements in overall model performance. We comprehensively evaluate the performance of our model on the KNMI dataset, and a large number of experimental results show that our method achieves remarkable results on the precipitation prediction task. © 2023 IEEE.
关键词	Deep learning Forecasting Large datasets Learning systems Decoupled dynamic filter Dynamic filter Dynamic residual attention Hotspots Learning methods Nowcasting Precipitation nowcasting Precipitation predictions Radar echoes Wasserstein GAN
DOI	10.1109/CAC59555.2023.10450446
收录类别	EI
语种	英语
EI入藏号	20241515852553
EI主题词	Image enhancement
EI分类号	461.4 Ergonomics and Human Factors Engineering ; 723.2 Data Processing and Image Processing
原始文献类型	Conference article (CA)
引用统计	无
文献类型	会议论文
条目标识符	https://ir.lut.edu.cn/handle/2XXMBERH/170546
专题	图书馆外国语学院
通讯作者	Li, Ce
作者单位	School of Electrical Engineering and Information Engineering, Lanzhou University of Technology, Lanzhou, China
第一作者单位	兰州理工大学
通讯作者单位	兰州理工大学
推荐引用方式 GB/T 7714	Li, Ce,Huang, Fan,Zhang, Jianwei,et al. Dynamic Residual Attention UNet for Precipitation Nowcasting Based on WGAN[C]:Institute of Electrical and Electronics Engineers Inc.,2023:6265-6270.