Answers are grounded in this paper and cite their sources.
• Random forest model enhances sediment predictions from Delft3D. • The correction model can predict spatially-resolved mud in the complex estuaries. • The new model is likely to be used to estimate the sediment accumulation/erosion. As a dynamic component of the coastal ecosystem, suspended cohesive sediment in fringing regions influences geomorphological features, controls light availability, and serves as a transport medium for pollutants. Therefore, monitoring suspended sediment concentration (SSC) at scale is essential for understanding the resilience of wetlands and thus safeguarding the surrounding coastal ecosystem. In this study, a novel model was developed to enable continuous estimation of SSC in present and future estuarine environments, by combining intermittent satellite observations with numerical process-based modelling (Delft3D-Flow). Specifically, the correction model consisted of two steps: (1) comparing the Delft3D-derived SSC with corrected satellite data and using K-means classification to categorise the differences into classes; (2) developing a random forest regression model for each class to predict the satellite-derived SSC using Delft3D-derived SSC and other physical parameters as inputs. The correction model demonstrated enhanced accuracy in predicting remotely-sensed SSC testing data (R² = 0.71, MAE ranging between 5.45 and 6.05 mg·L -1 ), and was an improvement on the SSC predictions derived solely from Delft3D simulations, assessed by comparing to a short-term deployment of in situ sensors, long-term monitoring data as well as satellite-based estimates. The newly developed correction model can enhance our ability to predict spatially-resolved SSC in complex intertidal estuaries where collecting adequate in situ validation data is challenging.
No takes yet. Share an insight, caveat, or question.
Shao et al. (2025) studied this question.
Synapse has enriched 10 related papers. Consider them for comparative context: