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.

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.

Multimodal remote sensing data provide important data support for large-scale, all-weather monitoring of offshore oil and gas platforms. However, differences in imaging modalities and acquisition conditions introduce significant domain shift, which limits the generalization capability of object detection models in unseen target domains. Furthermore, most existing multimodal detection methods typically rely on paired and strictly registered data, thereby restricting their applicability in practical scenarios. To overcome these challenges, an end-to-end method, termed OG-MLDD, is proposed for cross-modal offshore oil and gas platform detection. Without requiring multimodal image registration, the proposed method integrates meta-learning with domain discriminator (DD) to encourage the extraction of semantically discriminative representations that remain invariant across different domains. Specifically, a dual-gradient-descent-based meta-learning strategy is first introduced to jointly optimize the meta-train and meta-test objectives, encouraging the model to learn generalized and discriminative feature representations across different imaging modalities. Subsequently, a dynamic-weighted gradient reversal layer (DWGRL) is embedded into DD to guide adversarial feature learning between different domains, thereby promoting the acquisition of domain-robust representations and supplying global supervisory cues throughout the training process. Finally, a multi-scale feature aggregation (MFA) module is proposed to effectively integrate fine-grained local details with multiple receptive fields and high-level contextual information, thereby refining the fused feature representations and enhancing the representation capability of multi-scale offshore platform objects. Experimental results on a real-world dataset demonstrate that, even without using target domain data during training, the proposed method achieves superior detection performance and robust cross-domain generalization. Compared with existing methods, the full method improves detection accuracy by approximately 8 percentage points with a standard deviation of only 0.6, highlighting its superior detection performance and generalization ability.