Enhancing water depth inversion accuracy in the Yangtze River's Nantong Channel using random forest and coordinate attention mechanisms

Accurate bathymetry information is crucial for safe navigation and efficient management of the Yangtze River Channel, a vital shipping corridor in China. Traditional bathymetric surveying methods are time-consuming and labor-intensive, limiting their application in large-scale and real-time monitoring. This study proposes a novel approach for bathymetry inversion in the Yangtze River Nantong Channel by integrating geolocational features obtained from the ZY-1E satellite with high-resolution multibeam data using the random forest algorithm. Our approach incorporates geographical coordinates enhancing the predictive capabilities of conventional models. The random forest with longitude/latitude (RF-Lon./Lat.) model, which incorporates geographical information, outperformed conventional methods, achieving an R 2 of 0.57, MAE of 1.99 m, and RMSE of 2.96 m. The successful application of the RF-Lon./Lat. model highlights the effectiveness of integrating geolocational features with machine learning algorithms for accurate bathymetry inversion in the complex and turbid waters of the Yangtze River Channel. This innovative approach offers a promising solution for precise and efficient water depth estimation, which is essential for various applications in the Yangtze River Basin, including channel management, waterway maintenance, and hydrological studies. The insights gained from this study contribute to the growing body of knowledge on the application of machine learning and remote sensing techniques for bathymetric mapping in complex river environments, particularly in the context of the Yangtze River Channel.