Search Results

You are looking at 1 - 2 of 2 items for

  • Author or Editor: Weizeng Shao x
  • All content x
Clear All Modify Search
Weizeng Shao, Shuai Zhu, Xiaopeng Zhang, Shuiping Gou, Changzhe Jiao, Xinzhe Yuan, and Liangbo Zhao


This study proposes the use of the artificial neural network for wind retrieval with Chinese Gaofen-3 (GF-3) synthetic aperture radar (SAR) data. More than 10 000 images acquired in wave mode and quad-polarization strip map were collected over global seas throughout the 2-yr mission. The GF-3 operated in a quad-polarization channel—vertical–vertical (VV), vertical–horizontal (VH), horizontal–horizontal (HH), and horizontal–vertical (HV). These images were collocated with winds from the European Centre for Medium-Range Weather Forecasts at a 0.125° grid. The newly released wind retrieval algorithm for copolarization (VV and HH) SAR included CMOD7 and C-SARMOD2. We developed an algorithm based on an artificial neural network method using the SAR-measured normalized radar cross section at quad-polarization channels, herein named QPWIND_GF. Simulations using the QPWIND_GF showed that the correlation coefficient of wind speed was 0.94. We then validated the retrieval wind speeds against the measurements at a 0.25° grid from the Advanced Scatterometer. A comparison showed that the root-mean-square error (RMSE) of wind speed was 0.74 m s−1, which was better than the wind speed obtained using state-of-the-art methods—including, for example, CMOD7 (RMSE 0.88 m s−1) and C-SARMOD2 (RMSE 1.98 m s−1). The finding indicated that the accuracy of wind retrieval from GF-3 SAR images was significantly improved. Our work demonstrates the advanced feasibility of an artificial neural network method for SAR marine applications.

Full access
Weizeng Shao, Yuyi Hu, Ferdinando Nunziata, Valeria Corcione, Maurizio Migliaccio, and Xiaoming Li


In this study, a method for retrieving wind speed from synthetic aperture radar (SAR) imagery collected under extreme weather conditions is proposed. The rationale for this approach relies on the fact that, although copolarized channels exhibit saturation for wind speed >~20 m s−1, the wave growth can be successfully exploited to gather information on wind speed under extreme weather conditions. Hence, in this study, the intrinsic relationship among the wind-wave triplets [wind speed at 10 m above the sea surface, significant wave height (SWH), and peak wave period] is exploited in order to retrieve wind speeds under tropical cyclone conditions. Experiments, undertaken on actual X-band TerraSAR-X (TS-X) SAR images of tropical cyclones (Typhoon Megi, Hurricane Sandy, and Hurricane Miriam) and using collocated WAVEWATCH-III (WW3) simulations, revealed the robustness of the proposed approach, which resulted in a root-mean-square error (RMSE) of 2.54 m s−1 when comparing the retrieved wind speeds with the values from products delivered by the National Oceanic and Atmospheric Administration (NOAA) Hurricane Research Division (HRD). However, the applicability of the algorithm herein will be further confirmed at very strong storms.

Restricted access