Assessments of epistemic uncertainty using Gaussian stochastic weight averaging for fluid-flow regression

Abstract

We use Gaussian stochastic weight averaging (SWAG) to assess the model-form uncertainty associated with neural-network-based function approximation relevant to fluid flows. SWAG approximates a posterior Gaussian distribution of each weight, given training data, and a constant learning rate. Having access to this distribution, it is able to create multiple models with various combinations of sampled weights, which can be used to obtain ensemble predictions. The average of such an ensemble can be regarded as the `mean estimation', whereas its standard deviation can be used to construct `confidence intervals', which enable us to perform uncertainty quantification (UQ) with regard to the training process of neural networks. We utilize representative neural-network-based function approximation tasks for the following cases: (i) a two-dimensional circular-cylinder wake; (ii) the DayMET dataset (maximum daily temperature in North America); (iii) a three-dimensional square-cylinder wake; and (iv) urban flow, to assess the generalizability of the present idea for a wide range of complex datasets. SWAG-based UQ can be applied regardless of the network architecture, and therefore, we demonstrate the applicability of the method for two types of neural networks: (i) global field reconstruction from sparse sensors by combining convolutional neural network (CNN) and multi-layer perceptron (MLP); and (ii) far-field state estimation from sectional data with two-dimensional CNN. We find that SWAG can obtain physically-interpretable confidence-interval estimates from the perspective of model-form uncertainty. This capability supports its use for a wide range of problems in science and engineering.

References in corpus (13)

• Prediction of Aerodynamic Flow Fields Using Convolutional Neural Networks
• 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
• A neural network approach for the blind deconvolution of turbulent flows
• Convolutional neural networks for fluid flow analysis: toward effective metamodeling and low-dimensionalization
• From coarse wall measurements to turbulent velocity fields through deep learning
• Sparse identification of nonlinear dynamics with low-dimensionalized flow representations
• Generalization techniques of neural networks for fluid flow estimation
• Memory embedded non-intrusive reduced order modeling of non-ergodic flows
• A priori analysis on deep learning of subgrid-scale parameterizations for Kraichnan turbulence
• Deep learning of the spanwise-averaged Navier-Stokes equations
• Identifying key differences between linear stochastic estimation and neural networks for fluid flow regressions

Cited by in corpus (8)

• Super-Resolution Analysis via Machine Learning: A Survey for Fluid Flows
• Machine learning building-block-flow wall model for large-eddy simulation
• Uncertainty-aware Surrogate Models for Airfoil Flow Simulations with Denoising Diffusion Probabilistic Models
• Identifying key differences between linear stochastic estimation and neural networks for fluid flow regressions
• Reconstructing three-dimensional bluff body wake from sectional flow fields with convolutional neural networks
• Convolutional Long Short-Term Memory (convLSTM) for Spatio-Temporal Forecastings of Saturations and Pressure in the SACROC Field
• Reducing Spatial Discretization Error on Coarse CFD Simulations Using an OpenFOAM-Embedded Deep Learning Framework
• Multi-resolution Physics-Aware Recurrent Convolutional Neural Network for Complex Flows