Internal waves are crucial for understanding oceanographic parameters such as spatiotemporal distribution and energy transfer. They significantly impact ocean circulation, marine ecosystems, and offshore operations. However, studying internal waves is challenging due to their dynamic nature and the need for effective observation methods. This study investigated nonlinear internal solitary waves (ISWs) in the South China Sea using SSHa data from the SWOT satellite mission (Cycles 2 to 20). The distribution patterns and seasonal variations in ISWs were analyzed, revealing that ISWs are more frequently observed in summer while being rarely detected in winter. By combining SSHa observations with a Mode-1 vertical structure model, the isopycnal displacement, velocity fields, and energy characteristics of ISWs were reconstructed. The results show a maximum isopycnal displacement of 160 m at 400 m depth and peak kinetic energy near the surface (~2000 J/m³) and potential energy at a depth of around 300 m (~9000 J/m³). These findings highlight the vertical variability of ISWs and demonstrate the capability of SWOT data in capturing their fine-scale evolution, providing new opportunities for oceanic research and enhancing our understanding of internal waves’ impact on marine environments and ocean circulation.

The operational robustness of geomagnetic matching navigation for underwater vehicles is increasingly challenged by environmental disturbances in complex seas. In particular, electromagnetic induction associated with internal solitary waves can significantly alter the ambient magnetic field, thereby degrading matching performance. However, the magnitude and depth dependence of this interference remain poorly quantified due to the lack of high‐resolution three‐dimensional ocean observations. To explore these dynamic perturbations and their navigational impacts, this paper proposes a Marine‐Dynamics Magnetic Volumetric Reconstruction (MD‐MVR), which integrates SWOT satellite altimetry with a physics‐guided learning architecture to retrieve subsurface wave kinematics and reconstruct a spatiotemporally continuous volumetric induced magnetic field. Quantitative assessment reveals a critical relationship between surface signatures and underwater threats, where the magnetic interference intensity at 800 m depth is more than twofold that at the surface, with a peak magnitude reaching 20.921 nT under strong velocity shear and coherent current closure. Simulation results reveal that navigation accuracy is strongly affected by ISW‐induced magnetic disturbances across seasons and operating depths. Under the representative 5 nT composite‐error condition, mean positioning errors increase to approximately 1.15–1.76 n miles, with the exceedance probability above 1.0 n mile reaching over 90% in adverse shallow‐depth cases. Under the lower 3 nT condition, errors are reduced but remain non‐negligible, particularly for oblique tracks and spatial‐domain algorithms during energetic seasonal conditions. These findings provide a quantitative baseline for evaluating depth‐ and season‐dependent environmental risks and demonstrate the potential of physics‐guided volumetric reconstruction in supporting high‐fidelity environmental perception for next‐generation underwater navigation systems.

The geomagnetic reference map is an important component of underwater geomagnetic matching navigation, and it directly affects navigation and positioning accuracy. However, representative global geomagnetic models still cannot fully meet the requirements of high-precision matching navigation. To address this, this study proposes a local marine geomagnetic anomaly model reconstruction method via multi-source data fusion based on a fully connected neural network. The proposed MAG-DFN method uses the EMAG2 model as the background field and learns model residuals from shipborne measurements to reconstruct the geomagnetic model. Two sub-areas in the South China Sea and the western Pacific were selected for this experiment, each containing two withheld 1° × 1° validation blocks, and four baseline methods were introduced for comparison. The results show that MAG-DFN reduces MAE by 14.71%, 23.35%, 22.09%, and 8.96%, and RMSE by 12.41%, 18.87%, 16.73%, and 6.65%, in the four validation blocks, respectively. In addition, MAG-DFN outperforms all baseline methods. These results indicate that the MAG-DFN method, by integrating high-precision shipborne data, can effectively reduce the local deviations of the EMAG2 and better support matching navigation.