Enhancing Sediment Model by Incorporating Spatial-Temporal Variability in Particle Size and Settling Velocity Using Machine Learning Coupled with Numerical Models
Accurate prediction of sediment settling is critical for management of coastal ecosystems, but complex estuarine processes that influence sediment deposition and erosion present a major modelling challenge. This study explores a more efficient approach to simulating how particle size changes with dynamic sediment flocculation and thereby determines settling velocity. Environmental controls on in-situ particle size (median particle size D50) were investigated using regression model trained on coeval measurements of salinity, shear rate, and suspended sediment concentration (SSC). A machine learning (ML) model was developed and integrated into a fully coupled current-wave-sediment model to simulate flocculation-dimensional response in particle size due to variations in shear rate, salinity and SSC. The integrated model framework demonstrates its reliability and accuracy when evaluated against the in-situ measurements, SSC derived from satellite observations, and a parametric flocculation model that only relates settling velocity to SSC.