In this paper, we presented a method for retrieving sea surface wind speed (SSWS) from Sentinel-1 synthetic aperture radar (SAR) horizontal-horizontal (HH) polarization data in extra-wide (EW) swath mode, which have been extensively acquired over the Arctic for polar monitoring. In contrast to the conventional algorithm, i.e., using a geophysical model function (GMF) to retrieve SSWS by spaceborne SAR, we introduced an alternative retrieval method based on a GMF-guided neural network. The SAR normalized radar cross section, incidence angle, and wind direction are used as the inputs of a back propagation (BP) neural network, and the output is the SSWS. The network is developed based on 11,431 HH-polarized EW images acquired in the marginal ice zone (MIZ) of the Arctic from 2015 to 2018 and their collocated scatterometer wind measurements. Verification of the neural network based on the testing dataset yields a bias of 0.23 m/s and a root mean square error (RMSE) of 1.25 m/s compared to the scatterometer wind data for wind speeds less than approximately 30 m/s. Further comparison of the SAR retrieved SSWS with independent buoy measurements shows a bias and RMSE of 0.12 m/s and 1.42 m/s, respectively. We also analyzed the uncertainty of the retrieval when reanalysis model wind direction data are used as inputs to the neural network. By combining the detected sea ice cover information based on SAR data, sea ice and marine-meteorological parameters can be derived simultaneously by spaceborne SAR at a high spatial resolution in the Arctic.

The acquisition of significant wave height (SWH) in coastal seas is significantly important to human activities. The Gaofen-3 (GF-3) satellites, comprising GF-3, GF-3B and GF-3C, are independently developed operational SAR of China, capable of providing high-precision, high-resolution, multi-polarization coastal ocean wave observations. In order to obtain SWH in coastal seas, the retrieval of SWH using Quad-Polarization Stripmap (QPS) mode data from GF-3 satellites based on the deep learning method is implemented in this study. Furthermore, to obtain more SWH data, the polarization ratio model was applied to the Fine Stripmap (FS) mode data and Ultra Fine Stripmap (UFS) mode data to extend the model application. Comparisons with ECMWF Reanalysis v5 (ERA5) wave heights show that the QPS mode SWH retrieval achieves a root mean square error (RMSE) of 0.33 m. For the FS mode, the RMSE is 0.44 m (vs. ERA5) and 0.52 m (vs. altimeter). For the UFS mode, the RMSE is 0.39 m (vs. ERA5). Evaluation results indicate the feasibility of the proposed method for coastal SWH retrieval.

The twin Sentinel-1 (S1) satellites have been extensively acquiring synthetic aperture radar (SAR) data in the Arctic, providing the unique opportunity to obtain ocean dynamic parameters with both high spatial resolution and wide swath coverage in the marginal ice zone (MIZ). In this paper, we proposed a method for retrieving the ocean significant wave height (SWH) from S1 SAR data in horizontal-horizontal (HH) polarization based on a backpropagation neural network (BPNN). A total of 4,273 scenes from S1 extra wide swath mode data acquired in the Arctic were collocated with data from four radar altimeters (RA), yielding 126,128 collocated data pairs. These data were separated into training and testing datasets to develop a BPNN model for retrieving SWH. Comparing the S1 retrieved SWH using the testing dataset with the RA SWH yielded a bias of 0.17 m, a root-mean-square error of 0.71 m and a scatter index of 23.05% for SWH less than 10 m. The S1 retrieved SWH were further compared with CFOSAT/SWIM data acquired in the Arctic between August 2019 and May 2020 to validate the SWIM performance on wave measurements at different beams.

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, σ⁰), 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.

Onboard processing for remote sensing satellites has long been of interest in ocean monitoring because it can provide timely information on rapidly changing ocean environments. Recently, the integration of artificial intelligence (AI) into onboard processing has emerged as an active research topic. However, application scenarios and on-orbit demonstrations of AI-based onboard processing remain limited. In this study, we achieved the first on-orbit detection of ocean eddies using AI on the Haishao-1 (HS-1) spaceborne synthetic aperture radar (SAR) satellite, marking the first attempt to monitor an ocean dynamic process directly onboard. Specifically, an onboard application module was developed for HS-1, integrating image preprocessing and deep learning-based detection based on our previously developed Eddy Detection based on YOLO (EOLO) model. On-orbit experiments verified stable execution of the application module. Ground reproduction of the tasks using hardware identical to the onboard computing units yielded an average processing time of 3.4-6.1 s per image. Evaluation against expert annotations of 288 HS-1 scenes showed that EOLO, originally developed using Sentinel-1 imagery, achieved an F1 score of 78% after threshold adjustment. The application module has also been deployed on the Haishao-2 platform for Arctic sea ice extraction, further demonstrating its extensibility. This study presents the implementation and on-orbit validation of the onboard application module, providing a practical reference for future applications.