Reconstruction of three-dimensional turbulent flow structures using surface measurements for free-surface flows based on a convolutional neural network

Abstract

A model based on a convolutional neural network (CNN) is designed to reconstruct the three-dimensional turbulent flows beneath a free surface using surface measurements, including the surface elevation and surface velocity. Trained on datasets obtained from the direct numerical simulation (DNS) of turbulent open-channel flows with a deformable free surface, the proposed model can accurately reconstruct the near-surface flow field and capture the characteristic large-scale flow structures away from the surface. The reconstruction performance of the model, measured by metrics such as the normalised mean squared reconstruction errors and scale-specific errors, is considerably better than that of the traditional linear stochastic estimation (LSE) method. We further analyse the saliency maps of the CNN model and the kernels of the LSE model and obtain insights into how the two models utilise surface features to reconstruct subsurface flows. The importance of different surface variables is analysed based on the saliency map of the CNN, which reveals knowledge about the surface-subsurface relations. The CNN is also shown to have a good generalization capability with respect to the Froude number if a model trained for a flow with a high Froude number is applied to predict flows with lower Froude numbers. The results presented in this work indicate that the CNN is effective regarding the detection of subsurface flow structures and by interpreting the surface-subsurface relations underlying the reconstruction model, the CNN can be a promising tool for assisting with the physical understanding of free-surface turbulence.

References in corpus (18)

• Machine Learning for Fluid Mechanics
• Turbulence Modeling in the Age of Data
• Super-resolution reconstruction of turbulent flows with machine learning
• A Physics Informed Machine Learning Approach for Reconstructing Reynolds Stress Modeling Discrepancies Based on DNS Data
• Nonlinear mode decomposition with convolutional neural networks for fluid dynamics
• Data-driven prediction of unsteady flow fields over a circular cylinder using deep learning
• Machine learning based spatio-temporal super resolution reconstruction of turbulent flows
• Unsupervised deep learning for super-resolution reconstruction of turbulence
• Shallow Neural Networks for Fluid Flow Reconstruction with Limited Sensors
• Convolutional neural network based hierarchical autoencoder for nonlinear mode decomposition of fluid field data
• From coarse wall measurements to turbulent velocity fields through deep learning
• A Multi-Pass GAN for Fluid Flow Super-Resolution
• State estimation in turbulent channel flow from limited observations
• Logarithmic-layer turbulence: a view from the wall
• Revealing the state space of turbulence using machine learning
• Machine-aided turbulence theory
• From wall observations to turbulence: The difficulty of flow reconstruction
• Direct numerical simulation of turbulent mass transfer at the surface of an open channel flow

Cited by in corpus (7)

• Three-dimensional generative adversarial networks for turbulent flow estimation from wall measurements
• Physics-agnostic and Physics-infused machine learning for thin films flows: modeling, and predictions from small data
• Vortex structures under dimples and scars in turbulent free-surface flows
• Some effects of limited wall-sensor availability on flow estimation with 3D-GANs
• Experimental investigation relating free-surface features to sub-surface turbulence
• Reconstruction of three-dimensional turbulent flows from sparse and noisy planar measurements: A weight-sharing neural network approach
• Mapping surface height dynamics to subsurface flow physics in free-surface turbulent flow using a shallow recurrent decoder