A crucial indicator of hydrodynamic conditions, sediment transport systems, and geomorphic evolution is riverbed sediment. Hydraulic engineering, channel upkeep, and ecological management all depend on accurate sediment classification. Because of their intricate geomorphology and dynamic hydrodynamic forces, riverine systems show more spatial heterogeneity than comparatively stable marine habitats. It is challenging to adapt traditional mapping of the link between sediment types and acoustic signal characteristics based on a single resolution or uniform scale to the riverbed settings present in river basins. This study suggests a multi-resolution, multi-scale framework for riverbed sediment classification that incorporates both local detail and broad structural elements in order to overcome these limitations. The geomorphons landform identification approach is presented as a crucial instrument for describing the spatial distribution of riverbed silt due to the complexity of riverbed geomorphology. Bathymetric, backscatter, and geomorphic characteristics are combined across several resolutions and scales to create a hierarchical feature-extraction approach. To find stable and discriminative variables, an iterative tree-based feature selection technique is used. Three supervised classification models are assessed using multibeam and field sampling data from the Fuchun River Basin. The results show that the suggested method continuously enhances classification performance for all models. The overall accuracy of the Random Forest classifier increases by about 5%. The findings show that using multi-resolution and multi-scale information enhances riverbed classification’s resilience and accuracy.
Li et al. (Sun,) studied this question.