Deep learning has shown significant advantages over traditional spatial interpolation methods in single image super-resolution (SISR). Recently, many studies have applied super-resolution (SR) methods to generate high-resolution (HR) digital bathymetry models (DBMs), but substantial differences between DBM and natural images have been ignored, which leads to serious distortions and inaccuracies. Given the critical role of HR DBM in marine resource exploitation, economic development, and scientific innovation, we propose a frequency-aware texture matching transformer (FTT) for DBM SR, incorporating global terrain feature extraction (GTFE), high-frequency feature extraction (HFFE), and a terrain matching block (TMB). GTFE has the capability to perceive spatial heterogeneity and spatial locations, allowing it to accurately capture large-scale terrain features. HFFE can explicitly extract high-frequency priors beneficial for DBM SR and implicitly refine the representation of high-frequency information in the global terrain feature. TMB improves fidelity of generated HR DBM by generating position offsets to restore warped textures in deep features. Experimental results have demonstrated that the proposed FTT has superior performance in terms of elevation, slope, aspect, and fidelity of generated HR DBM. Notably, the root mean square error (RMSE) of elevation in steep terrain has been reduced by 4.89 m, which is a significant improvement in the accuracy and precision of the reconstruction. This research holds significant implications for improving the accuracy of DBM SR methods and the usefulness of HR bathymetry products for future marine research.

Satellite sea surface salinity (SSS) products suffer from coarse spatiotemporal resolution, limiting their utility for mesoscale ocean monitoring. To address this, we proposed the Transformer-based satellite SSS super-resolution (SR) model (TSR) coupled with a progressive transfer learning (PTL) strategy. TSR improved the resolution of the salinity satellite SMOS from 1/4° and 10 days to 1/12° and daily. Leveraging Transformer, TSR captured long-range dependencies critical for reconstructing fine-scale structures. PTL effectively balanced structural detail acquisition and local accuracy correction by combining the gridded reanalysis products with scattered in situ observations as training labels. Validated against independent in situ measurements, TSR outperformed existing L3 salinity satellite products, as well as convolutional neural network and generative adversarial network-based SR models, particularly reducing the root mean square error (RMSE) by 33% and the mean bias (MB) by 81% compared to the SMOS input. More importantly, TSR demonstrated an enhanced capability in resolving mesoscale eddies, which were previously obscured by noise in salinity satellite products. Compared to training with a single label type or switching label types non-progressively, PTL achieved a 3%–66% lower RMSE and a 73–92% lower MB. TSR enables higher-resolution satellite monitoring of SSS, contributing to the study of ocean dynamics and climate change.

Data voids significantly compromise the reliability of Digital Bathymetry Models (DBMs) for critical applications such as oceanographic research and resource exploration. Traditional interpolation methods struggle to accurately reconstruct complex submarine landforms, often resulting in blurred or distorted restorations. While deep learning methods offer promising solutions, the remarkable complexity and diversity of submarine landforms still pose significant challenges for DBM void-filling. To address this, we propose a novel two-stage deep learning framework leveraging topographic feature lines (TFL), named DTFL. In the first stage, DTFL focuses on predicting TFL within void regions. In the second stage, it employs the predicted TFL as geometric constraints to guide structurally rational and high fidelity restoration. Additionally, DTFL employs the proposed Enhanced-Transformer U-Net (ETU) architecture, which integrates the strengths of U-net and Transformers to capture long-range dependencies among multi-scale features. Crucially, a hierarchical integration strategy with a Feature Adaptive Alignment (FAA) module progressively injects the TFL information into the void-filling network at the feature level. This ensures that fine-grained spatial constraints with TFL features guide the reconstruction toward structurally rational reconstructions. Experiments demonstrate that our method outperforms existing approaches on both strip-shaped and random voids.