Spectral-Geospatial XGBoost Regression for Bathymetric Mapping in Yellow River RSG-XGBoost for Yellow River Bathymetry Mapping

This is the authors' abstract. We don't add key points for this paper.

This study proposes a Spectral-Geospatial XGBoost Regression (RSG-XGBoost) model for bathymetric mapping in complex river confluences, demonstrated at the Yellow River–Yiluohe River junction. The method fuses multispectral GF-1 WFV1 imagery with geospatial variables to estimate water depth from limited in-situ observations. Using depth measurements collected by an RDI 600 kHz ADCP River Ray, we benchmark RSG-XGBoost against the Stumpf model, a log-linear model, and a standard Random Forest across multiple depth intervals and heterogeneous channel morphologies.RSG-XGBoost delivers the best performance, achieving an overall RMSE of 0.45 m and maintaining higher accuracy in challenging depth ranges where traditional empirical models degrade. The resulting bathymetric maps capture fine-scale underwater topography and subtle geomorphic features that competing approaches fail to resolve. The gradient boosting framework effectively models non-linear relationships between spectral responses, spatial context, and depth, improving robustness in optically and morphologically complex reaches. We also discuss uncertainties and limitations, including sensitivity to environmental conditions and the transferability of trained models to other river systems. These results support more reliable river bathymetry for management, navigation, and ecological applications.