Affiliation:
1. School of Oceanography, Shanghai Jiao Tong University, Shanghai 200030, China
2. State Key Laboratory of Satellite Ocean Environment Dynamics, Second Institute of Oceanography, Ministry of Natural Resources, Hangzhou 310012, China
3. Southern Marine Science and Engineering Guangdong Laboratory (Zhuhai), Zhuhai 519082, China
4. National Marine Environmental Forecasting Center, Beijing 100081, China
5. Zhejiang Climate Centre, Hangzhou 310017, China
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.
Funder
Oceanic Interdisciplinary Program of Shanghai Jiao Tong University
Scientific Research Fund of the Second Institute of Oceanography, Ministry of Natural Resources of China
China Postdoctoral Science Foundation
preferential support for postdoctoral research projects in Zhejiang Province
Innovation Group Project of Southern Marine Science and Engineering Guangdong Laboratory
Zhejiang Provincial Natural Science Foundation of China
Project of State Key Laboratory of Satellite Ocean Environment Dynamics, Second Institute of Oceanography, Ministry of Natural Resources of China
Science and Technology Project of Zhejiang Meteorological Bureau
open fund of the State Key Laboratory of Satellite Ocean Environment Dynamics, Second Institute of Oceanography, MNR
Subject
General Earth and Planetary Sciences
Reference59 articles.
1. Gray, W.M. (1975). Tropical Cyclone Genesis. [Ph.D. Thesis, Colorado State University].
2. Tropical cyclones;Emanuel;Annu. Rev. Earth Planet. Sci.,2003
3. Global trends in tropical cyclone risk;Peduzzi;Nat. Clim. Change,2012
4. Wind fields from SAR: Could they improve our understanding of storm dynamics?;Katsaros;Johns Hopkins APL Tech. Digest,2000
5. Tiampo, K.F., Huang, L., Simmons, C., Woods, C., and Glasscoe, M.T. (2022). Detection of Flood Extent Using Sentinel-1A/B Synthetic Aperture Radar: An Application for Hurricane Harvey, Houston, TX. Remote Sens., 14.
Cited by
1 articles.
订阅此论文施引文献
订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献