.png){kind=icon}
.png){kind=icon}
Return
Sea Surface Wind Speed Retrieval with a Dual-Branch Feature-Fusion Network Using GaoFen-3 Series SAR Data
.png){kind=icon}
OA
AI
X
R
W
C
DOI：10.3390/rs18070971.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
Highlights What are the main findings? The proposed attention-guided dual-branch feature-fusion network, which integrates spatial and nonlinear features from the GaoFen-3 (GF-3) series SAR satellite data, leads to an effective improvement in sea surface wind speed retrieval accuracy while maintaining the key spatial characteristics of the wind field. The refinement of radiometric calibration constants for specific GF-3B SAR satellite beam codes, achieved through a Geophysical Model Function (GMF)-based method, has successfully enhanced the accuracy of sea surface wind speed retrieval to meet international benchmarks. What are the implications of the main findings? The development of an attention mechanism-guided, dual-branch feature-fusion model provides a new dimension for SAR wind speed retrieval by fusing nonlinear relationships and local spatial features through a parallel structure, capturing the inherent spatial characteristics of marine dynamics. A correction to the radiometric calibration constants for specific beam codes of the GF-3B SAR satellite was applied, using a GMF and scatterometer wind field data. This refinement addresses the insufficient radiometric accuracy that hindered sea surface wind speed retrieval.Highlights What are the main findings? The proposed attention-guided dual-branch feature-fusion network, which integrates spatial and nonlinear features from the GaoFen-3 (GF-3) series SAR satellite data, leads to an effective improvement in sea surface wind speed retrieval accuracy while maintaining the key spatial characteristics of the wind field. The refinement of radiometric calibration constants for specific GF-3B SAR satellite beam codes, achieved through a Geophysical Model Function (GMF)-based method, has successfully enhanced the accuracy of sea surface wind speed retrieval to meet international benchmarks. What are the implications of the main findings? The development of an attention mechanism-guided, dual-branch feature-fusion model provides a new dimension for SAR wind speed retrieval by fusing nonlinear relationships and local spatial features through a parallel structure, capturing the inherent spatial characteristics of marine dynamics. A correction to the radiometric calibration constants for specific beam codes of the GF-3B SAR satellite was applied, using a GMF and scatterometer wind field data. This refinement addresses the insufficient radiometric accuracy that hindered sea surface wind speed retrieval.Abstract To address the suboptimal radiometric calibration accuracy observed in specific beam codes of the GaoFen-3 (GF-3) series satellite for sea surface wind speed (SSWS) retrieval, this study introduces a calibration constant correction method based on the geophysical model function (GMF). This approach enables high-precision SSWS retrieval from GF-3B data. Conventional SAR-based SSWS retrieval models typically rely on pointwise mapping relationships, which overlook the spatial characteristics inherent in dynamic sea surface wind fields. To overcome this limitation, this study proposes an attention-guided dual-branch feature-fusion network (ADBFF-NET). The first branch, implemented as a backpropagation neural network (BPNN), learns nonlinear mappings between the normalized radar cross-section (NRCS, sigma 0), incidence angle, azimuth look direction, and wind vectors (speed and direction). The second branch, designed as a residual convolutional neural network, extracts spatial features of wind fields. An attention mechanism fuses the outputs of both branches, thereby enhancing retrieval accuracy. Experiments conducted with GF-3 series satellite data were validated against the European Centre for Medium-Range Weather Forecasts (ECMWF) Reanalysis V5 (ERA5), Advanced Scatterometer (ASCAT) wind fields, and altimeter-derived wind speeds. The results indicate that the SSWS retrieved from GF-3B SAR data using the corrected calibration constants achieve a root mean square error (RMSE) of 1 m/s against ERA5 wind speeds, representing an approximately 40% reduction compared with the RMSE obtained using the original calibration constant. Furthermore, compared to ERA5 and ASCAT data, the RMSE of the wind speeds retrieved by the ADBFF-NET model reaches 1.17 m/s and 1.03 m/s, respectively.
Keywords:
sea surface wind speed (SSWS)
GaoFen-3
neural network
radiation calibration
Journal
IF:
4.1
Papers:
6.8K
Citations:
15.1W