Dual-Level Contextual Attention Generative Adversarial Network for Reconstructing SAR Wind Speeds in Tropical Cyclones
Authors:Han, Xinhai Li, Xiaohui Yang, Jingsong Wang, Jiuke Zheng, Gang Ren, Lin Chen, Peng Fang, He Xiao, Qingmei
Volume:15
Published:2023
Document Type:Article
Abstract:Synthetic Aperture Radar (SAR) imagery plays an important role in observing tropical cyclones (TCs). However, the C-band attenuation caused by rain bands and the problem of signal saturation at high wind speeds make it impossible to retrieve the fine structure of TCs effectively. In this paper, a dual-level contextual attention generative adversarial network (DeCA-GAN) is tailored for reconstructing SAR wind speeds in TCs. The DeCA-GAN follows an encoder-neck-decoder architecture, which works well for high wind speeds and the reconstruction of a large range of low-quality data. A dual-level encoder comprising a convolutional neural network and a self-attention mechanism is designed to extract the local and global features of the TC structure. After feature fusion, the neck explores the contextual features to form a reconstructed outline and up-samples the features in the decoder to obtain the reconstructed results. The proposed deep learning model has been trained and validated using the European Centre for Medium-Range Weather Forecasts (ECMWF) atmospheric model product and can be directly used to improve the data quality of SAR wind speeds. Wind speeds are reconstructed well in regions of low-quality SAR data. The root mean square error of the model output and ECMWF in these regions is halved in comparison with the existing SAR wind speed product for the test set. The results indicate that deep learning methods are effective for reconstructing SAR wind speeds.
Author Information
Corresponding Author:Yang, JS (corresponding author), Shanghai Jiao Tong Univ, Sch Oceanog, Shanghai 200030, Peoples R China.;Yang, JS (corresponding author), Minist Nat Resources, Inst Oceanog 2, State Key Lab Satellite Ocean Environm Dynam, Hangzhou 310012, Peoples R China.
Reprint Address:Yang, JS (corresponding author), Shanghai Jiao Tong Univ, Sch Oceanog, Shanghai 200030, Peoples R China.;Yang, JS (corresponding author), Minist Nat Resources, Inst Oceanog 2, State Key Lab Satellite Ocean Environm Dynam, Hangzhou 310012, Peoples R China.
Addresses:[Han, Xinhai; Yang, Jingsong] Shanghai Jiao Tong Univ, Sch Oceanog, Shanghai 200030, Peoples R China; [Han, Xinhai; Li, Xiaohui; Yang, Jingsong; Zheng, Gang; Ren, Lin; Chen, Peng; Xiao, Qingmei] Minist Nat Resources, Inst Oceanog 2, State Key Lab Satellite Ocean Environm Dynam, Hangzhou 310012, Peoples R China; [Yang, Jingsong; Zheng, Gang; Ren, Lin; Chen, Peng] Southern Marine Sci & Engn Guangdong Lab Zhuhai, Zhuhai 519082, Peoples R China; [Wang, Jiuke] Natl Marine Environm Forecasting Ctr, Beijing 100081, Peoples R China; [Fang, He] Zhejiang Climate Ctr, Hangzhou 310017, Peoples R China
E-mail Addresses:jsyang@sio.org.cn