A Neural Network Method for Retrieving Sea Surface Wind Speed for C-Band SAR

Yu, Peng; Xu, Wenxiang; Zhong, Xiaojing; Johannessen, Johnny A.; Yan, Xiao‐Hai; Geng, Xupu; He, Yuanrong; Lu, Wenfang

doi:10.3390/rs14092269

Cited by 9 publications

(2 citation statements)

References 62 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, the physical relationship between the wind vector and its radar backscatter is a complex nonlinear function that, in addition to (1), also includes the polarization and relative azimuth between the radar viewing angle and the wind direction. To increase the efficiency of solving the inverse GMF problems, reconstruct the entire TC structure, and enhance the low-quality data, neural network technologies and machine learning methods are used [13,14].…”

Section: Introductionmentioning

confidence: 99%

Estimating the Intensity of Tropical Cyclones from Spiral Signatures Acquired by Spaceborne SAR

Yurchak

2024

Remote Sensing

View full text Add to dashboard Cite

Accurate estimates of tropical cyclone (TC) intensity are important for improving forecasts as well as studying ocean dynamics during such extreme events. Since most cyclone life occurs over the open ocean, remote sensing techniques play an important role in obtaining the necessary data. The possibility of using the configuration of spiral signatures of mature tropical cyclones (TCs) observed in synthetic aperture radar (SAR) images to estimate the maximum wind speed of a TC is considered. This study assessed the intensity of 14 TCs in the Atlantic and Pacific Oceans using radar images obtained by the Radarsat Hurricane Application Project. TC intensity was estimated using the hyperbolic-logarithmic approximation of TC spiral signatures (HLS approximation). Additionally, the edges of the spiral signatures were partially fitted using a logarithmic spiral to improve the reliability of the HLS approximation. For the first time, a physical model of changing the crossing angle of the logarithmic portion of the edges was proposed and tested on SAR images of the TC. HLS maximum wind speed estimates were compared with Best Track estimates. The results showed the closeness of both estimates with a correlation of 0.95 and a standard deviation of 2.9 m s−1. The results indicate the possibility of using the HLS approximation to estimate the intensity of mature TCs from SAR data.

show abstract

Section: Introductionmentioning

confidence: 99%

Estimating the Intensity of Tropical Cyclones from Spiral Signatures Acquired by Spaceborne SAR

Yurchak

2024

Remote Sensing

View full text Add to dashboard Cite

show abstract

“…A DL method based on topological patterns was used with the high-resolution data of Sentinel-1 to improve the accuracy of TC intensity detection [20]. Progress has been made in exploring SAR wind speeds using DL, including deploying neural networks to invert sea surface wind speed from SAR and designing CNNs to extract SAR features to estimate TC intensity [21][22][23][24]. Using DL to construct forecast models based on Sentinel-1 and Sentinel-2 images has also shown good capability for offshore wind speed estimation [25].…”

Section: Introductionmentioning

confidence: 99%

Dual-Level Contextual Attention Generative Adversarial Network for Reconstructing SAR Wind Speeds in Tropical Cyclones

Han

Yang

et al. 2023

Remote Sensing

View full text Add to dashboard Cite

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.

show abstract

On the ambiguity removal of wind direction derived from space-borne SAR imagery using deep learning

Yang,

Fang,

Wang

et al. 2024

Remote Sensing of Environment

View full text Add to dashboard Cite

A Neural Network Method for Retrieving Sea Surface Wind Speed for C-Band SAR

Cited by 9 publications

References 62 publications

Estimating the Intensity of Tropical Cyclones from Spiral Signatures Acquired by Spaceborne SAR

Estimating the Intensity of Tropical Cyclones from Spiral Signatures Acquired by Spaceborne SAR

Dual-Level Contextual Attention Generative Adversarial Network for Reconstructing SAR Wind Speeds in Tropical Cyclones

On the ambiguity removal of wind direction derived from space-borne SAR imagery using deep learning

Contact Info

Product

Resources

About