A novel spatial graph attention networks for satellite-derived bathymetry in coastal and island waters

Obtaining accurate bathymetric maps is crucial for various applications like marine monitoring and planning. However, bathymetric inversion is influenced by water quality conditions and bottom reflections exhibiting spatial similarity. This study explores the spatial perspective in designing bathymetric inversion networks, proposing a Multi-Scale Graph Attention Network (MSGAN) model. MSGAN utilizes spectral bands and field data to extract bathymetric features by establishing graph adjacency matrices. Experimental data are collected from Nanshan Port, Visakhapatnam Beach, and Qilianyu Island to evaluate MSGAN's performance. Results demonstrate MSGAN outperforms existing methods like Stumpf, log-linear regression and random forest, achieving enhanced depth estimation accuracy even in turbid water bodies. Notably, MSGAN provides more detailed bathymetric maps for deep-water areas compared to traditional algorithms. This study introduces an efficient approach for satellite-derived bathymetry inversion, enhancing shallow water mapping capabilities. Overall, MSGAN offers a promising technique for bathymetric mapping from remote sensing data, with wide applications in hydrological and environmental monitoring.