A Strictly Synchronous Benchmark of Empirical and Tree-Based Satellite-Derived Bathymetry in a Turbid River Confluence
Year: 2026
Type: article
Abstract: Satellite-derived bathymetry (SDB) in turbid rivers remains difficult because suspended sediment, optical mixing, and weak bottom visibility disrupt the monotonic spectral-depth relations assumed by classical empirical models. This letter presents a strictly synchronous benchmark at the Yellow River–Yiluo River confluence using GF-1 WFV1 imagery and in situ depth measurements acquired on June 15, 2024. Two empirical baselines, two spectral tree-ensemble models, and two coordinate-augmented tree-ensemble models are evaluated under a unified preprocessing and independent validation workflow. A total of 2000 samples are used for training, and 1816 nonoverlapping samples are reserved for independent validation, yielding a validation proportion of 47.6%. Results show a clear separation between model families: Stumpf and log-linear regression produce compressed depth estimates and low explanatory power, whereas the random forest model and LightGBM model preserve much stronger nonlinear depth sensitivity. Adding longitude and latitude further improves within-reach validation accuracy for both the random forest model and LightGBM model, with Geo_LightGBM model achieving the best accuracy ($R^{2}=0.938$, RMSE = 0.387 m, MAE = 0.249 m). This gain is interpreted as within-reach assistance. The benchmark, therefore, provides a controlled testbed for separating model behavior from temporal mismatch in optically complex inland waters.
Language: English
Topic: Coastal and Marine Dynamics
Subfield: Earth-Surface Processes
Field: Earth and Planetary Sciences
Domain: Physical Sciences
Open Access status: hybrid
Estimated APC paid: $2,645
Awards: G2777927201, G7578311628
OpenAlex ID: W7166507546
