High-Fidelity Simulation of Turbulence in the Piscataqua River Using a Novel Neural Network Surrogate

Accurate three-dimensional characterization of turbulent flows in natural waterways is essential for the effective design of tidal farms and other critical infrastructure situated along or across rivers. High-fidelity predictions based on the large-eddy simulation (LES) method capture the necessary physics but incur computational costs that hinder rapid scenario testing. Statistically, a relatively long history of instantaneous flow fields is required to generate reliable turbulence statistics, e.g., mean velocity and Reynolds stresses, of river flow. Such a requirement often incurs high simulation runtime and data storage costs. This study seeks to develop a neural network surrogate model that learns from a limited number of instantaneous flow realizations and approximates the outputs of the corresponding time-averaged fields with LES-level accuracy. Such a surrogate would eliminate the need to accumulate extensive ensembles, enabling faster hydrodynamic assessment and making LES-informed analyses more accessible for practical engineering decisions.