Predicting Equilibrium Bed Morphology of Large-Scale Meandering Rivers Using a Novel LES-Trained Machine Learning Approach
Published in Journal of Advances in Modeling Earth Systems (JAMES), 2025
Flood-induced deformation of the bed topography of fluvial meandering rivers could lead to riverbank displacement, infrastructure failure, and the propagation of scour and deposition features. The ability to predict sediment transport in large-scale meanders is, therefore, a critical requirement for tackling a host of environmental issues. High-fidelity simulations of large-scale rivers coupling large-eddy simulation (LES) of the flow with morphodynamic processes can provide accurate predictions of such phenomena, but this approach is computationally very expensive owing to the costly two-way coupling between turbulence and bed morphodynamics across disparate time scales. This study presents a novel machine learning approach trained on data from high-fidelity simulations. We develop and demonstrate the performance of a convolutional neural network autoencoder (CNNAE) algorithm to generate high-fidelity bed shear stress and equilibrium morphology of large-scale meandering rivers. The CNNAE algorithm utilizes as input instantaneous shear stress distribution and change of bed elevation obtained from high-fidelity simulation results, along with geometric parameters of meanders to predict mean bed shear stress distribution and equilibrium bed elevation of rivers. The proposed machine learning approach predicts bed shear stress and equilibrium bed morphology of large-scale meanders under bankfull flow conditions at a fraction of the cost of brute-force coupled LES-morphodynamics.
Recommended citation: Zhang, Z., Gholami Anjiraki, M., Seyedzadeh, H., Sotiropoulos, F., Yang, X., & Khosronejad, A. (2025). Predicting equilibrium bed morphology of large‐scale meandering rivers using a novel LES‐trained machine learning approach. Journal of Advances in Modeling Earth Systems, 17(10), e2024MS004710.
Download Paper | Download Bibtex