The performance of deep learning models largely depends on the scale and quality of training data. However, acquiring sufficient, high-quality samples for specific observation scenarios is often challenging due to high acquisition costs. Unlike optical imagery, synthetic aperture radar (SAR) target images exhibit strong nonlinear scattering variations with changing azimuth angles, making conventional data augmentation methods such as cropping or rotation ineffective. To tackle these challenges, this paper introduces an Azimuth-Continuously Controllable Generative Adversarial Network (ACC-GAN), which incorporates a continuous azimuth conditional variable to achieve precise azimuth-controllable target generation from dual-input SAR images. Our key contributions are threefold: (1) a continuous azimuth control mechanism that enables precise interpolation between arbitrary azimuth angles; (2) a dual-discriminator framework combining similarity and azimuth supervision to ensure both visual realism and angular accuracy; and (3) conditional batch normalization integrated with adaptive feature fusion to maintain scattering consistency. Experiments on the MSTAR dataset demonstrate that ACC-GAN effectively captures nonlinear azimuth-dependent transformations, generating high-quality images that improve downstream classification accuracy and validate its practical value for SAR data augmentation.

Many current satellite-derived bathymetry (SDB) methods usually rely on in-situ water depth, which limits their applications. In this study, an ICESat-2 assisted Dual-Band Model (IDBM) is proposed, which can be used to derive bathymetry independent of in-situ water depth. First, the Sentinel-2 blue and green band diffuse attenuation coefficient is derived using ICESat-2 lidar photon data from adjacent deep water according to the Jerlov K_d spectral curves and the sensor spectral response function. Then, these two coefficients are applied to the IDBM model to derive the water depth. Datasets for four study areas are used to validate the feasibility of the proposed IDBM model, in addition, the original QAA (quasi-analytical algorithm) assisted Dual-Band Model (QDBM) is also used to derive bathymetry for comparison purposes. Experiment results show that the proposed IDBM model is effective and can achieve higher or similar accuracy compared to the original QDBM model. The average MAE and RMSE of the IDBM model reach 1.23m and 1.67m, while those of the QDBM model are 1.44m and 1.91m, respectively. The performance of the IDBM model has improved to some extent. Especially for the SI case, the MAE and RMSE of the QDBM model are 1.46m and 2.00m, while those of the IDBM model are 0.99m and 1.55m, which are reduced by 0.47m and 0.45m. In conclusion, the proposed IDBM model is feasible and effective to derive bathymetry without in-situ water depth.

Machine learning (ML) technology has been successfully applied to Satellite Derived Bathymetry (SDB) using the water surface reflectance. Many studies have proved that it is not enough to derive water depth accurately using water surface reflectance only, and the integration of additional features into ML models will be helpful for water depth inversion. In this paper, a slope-assisted back propagation model (SBP) is proposed to obtain water bathymetry. The slope feature is used in this model by iterative optimization. Besides, data augmentation (DA) technology is also used to improve the training of BP models. We validated our model on datasets with different sample size from 4 research areas. Compared with the Log-ratio model, the mean absolute error (MAE) is reduced between 0.3m and 0.7m, the relative reduction rate of MAE can reach 67%, and the mean square error (MSE) is also relatively reduced by more than 38%. Compared with the conventional ML models, the relative reduction rate of MAE is 11%, and the MSE is relatively reduced by 24%. Experimental results show that the prediction accuracy of the proposed SBP model can be improved effectively; it provides an effective solution for bathymetric retrieval tasks.