Abstract
Accurate bathymetric mapping in turbid river environments remains a considerable challenge for traditional remote sensing methods, particularly in dynamic systems like the Yellow River, where high sediment loads disrupt optical signals. This study proposes an Extra Trees model integrated with geographical parameters to improve depth estimation at the confluence of the Yellow River and Yiluo River. Using GaoFen-1 wide field of view 1(GF-1WFV1) satellite imagery (acquired June 15, 2024) and 2000 in-situ depth measurements from an Acoustic Doppler Current Profiler (ADCP) River Ray system, we evaluated the model against conventional approaches, including the Stumpf model, Log-Linear model, and Random Forest model. The Extra Trees model achieved superior accuracy with a coefficient of determination (R²) of 0.91, mean absolute error (MAE) of 0.26 m, and root mean square error (RMSE) of 0.46 m, outperforming the Stumpf (R² = 0.01, RMSE = 1.51 m), Log-Linear (R² = 0.00, RMSE = 1.51 m), and Random Forest (R² = 0.75, RMSE = 0.76 m) models. Feature importance analysis revealed that geographical parameters (longitude and latitude) were more influential than spectral features in depth prediction, highlighting the critical role of spatial context in capturing complex bathymetric patterns. The model demonstrated consistent performance across depth ranges (0–10 m) and excelled in resolving subtle morphological features, such as channels and shoals, that traditional methods missed. Comparative analysis with XGBoost further showed that the Extra Trees model maintained spatial continuity in depth predictions, avoiding artificial boundaries. These results suggest that integrating geographical parameters with ensemble learning enhances bathymetric mapping accuracy in turbid rivers, offering valuable tools for monitoring river morphology and supporting water resource management.