Generalization techniques of neural networks for fluid flow estimation

Abstract

We demonstrate several techniques to encourage practical uses of neural networks for fluid flow estimation. In the present paper, three perspectives which are remaining challenges for applications of machine learning to fluid dynamics are considered: 1. interpretability of machine-learned results, 2. bulking out of training data, and 3. generalizability of neural networks. For the interpretability, we first demonstrate two methods to observe the internal procedure of neural networks, i.e., visualization of hidden layers and application of gradient-weighted class activation mapping (Grad-CAM), applied to canonical fluid flow estimation problems -- $(1)$ drag coefficient estimation of a cylinder wake and $(2)$ velocity estimation from particle images. It is exemplified that both approaches can successfully tell us evidences of the great capability of machine learning-based estimations. We then utilize some techniques to bulk out training data for super-resolution analysis and temporal prediction for cylinder wake and NOAA sea surface temperature data to demonstrate that sufficient training of neural networks with limited amount of training data can be achieved for fluid flow problems. The generalizability of machine learning model is also discussed by accounting for the perspectives of inter/extrapolation of training data, considering super-resolution of wakes behind two parallel cylinders. We find that various flow patterns generated by complex interaction between two cylinders can be reconstructed well, even for the test configurations regarding the distance factor. The present paper can be a significant step toward practical uses of neural networks for both laminar and turbulent flow problems.

24 pages, 24 figures

References in corpus (12)

• Grad-CAM: Why did you say that?
• Perspectives on Machine Learning-augmented Reynolds-averaged and Large Eddy Simulation Models of Turbulence
• Global field reconstruction from sparse sensors with Voronoi tessellation-assisted deep learning
• Convolutional neural network and long short-term memory based reduced order surrogate for minimal turbulent channel flow
• Robust active flow control over a range of Reynolds numbers using an artificial neural network trained through deep reinforcement learning
• A neural network approach for the blind deconvolution of turbulent flows
• Construction of Reduced Order Models for Fluid Flows Using Deep Feedforward Neural Networks
• Convolutional neural networks for fluid flow analysis: toward effective metamodeling and low-dimensionalization
• Sparse identification of nonlinear dynamics with low-dimensionalized flow representations
• A priori analysis on deep learning of subgrid-scale parameterizations for Kraichnan turbulence
• Convolutional-network models to predict wall-bounded turbulence from wall quantities
• Inserting machine-learned virtual wall velocity for large-eddy simulation of turbulent channel flows

Cited by in corpus (10)

• Global field reconstruction from sparse sensors with Voronoi tessellation-assisted deep learning
• Convolutional neural network and long short-term memory based reduced order surrogate for minimal turbulent channel flow
• Super-Resolution Analysis via Machine Learning: A Survey for Fluid Flows
• Convolutional neural networks for fluid flow analysis: toward effective metamodeling and low-dimensionalization
• Sparse identification of nonlinear dynamics with low-dimensionalized flow representations
• Assessments of epistemic uncertainty using Gaussian stochastic weight averaging for fluid-flow regression
• Identifying key differences between linear stochastic estimation and neural networks for fluid flow regressions
• Joint Deep Reversible Regression Model and Physics-Informed Unsupervised Learning for Temperature Field Reconstruction
• Reconstructing three-dimensional bluff body wake from sectional flow fields with convolutional neural networks
• Model order reduction with neural networks: Application to laminar and turbulent flows