Probabilistic neural networks for fluid flow surrogate modeling and data recovery

Abstract

We consider the use of probabilistic neural networks for fluid flow {surrogate modeling} and data recovery. This framework is constructed by assuming that the target variables are sampled from a Gaussian distribution conditioned on the inputs. Consequently, the overall formulation sets up a procedure to predict the hyperparameters of this distribution which are then used to compute an objective function given training data. We demonstrate that this framework has the ability to provide for prediction confidence intervals based on the assumption of a probabilistic posterior, given an appropriate model architecture and adequate training data. The applicability of the present framework to cases with noisy measurements and limited observations is also assessed. To demonstrate the capabilities of this framework, we consider canonical regression problems of fluid dynamics from the viewpoint of reduced-order modeling and spatial data recovery for four canonical data sets. The examples considered in this study arise from (1) the shallow water equations, (2) a two-dimensional cylinder flow, (3) the wake of NACA0012 airfoil with a Gurney flap, and (4) the NOAA sea surface temperature data set. The present results indicate that the probabilistic neural network not only produces a machine-learning-based fluid flow {surrogate} model but also systematically quantifies the uncertainty therein to assist with model interpretability.

References in corpus (48)

• Adam: A Method for Stochastic Optimization
• A Comprehensive Survey on Graph Neural Networks
• Machine Learning for Fluid Mechanics
• A Tutorial on Bayesian Optimization of Expensive Cost Functions, with Application to Active User Modeling and Hierarchical Reinforcement Learning
• Turbulence Modeling in the Age of Data
• Deep learning for universal linear embeddings of nonlinear dynamics
• Weight Uncertainty in Neural Networks
• Physics Informed Deep Learning (Part I): Data-driven Solutions of Nonlinear Partial Differential Equations
• Super-resolution reconstruction of turbulent flows with machine learning
• A Comprehensive Physics-Informed Machine Learning Framework for Predictive Turbulence Modeling
• Physics-Informed Machine Learning Approach for Augmenting Turbulence Models: A Comprehensive Framework
• Nonlinear mode decomposition with convolutional neural networks for fluid dynamics
• Data-Driven Forecasting of High-Dimensional Chaotic Systems with Long Short-Term Memory Networks
• Physics Informed Deep Learning (Part II): Data-driven Discovery of Nonlinear Partial Differential Equations
• Reduced-order modeling of advection-dominated systems with recurrent neural networks and convolutional autoencoders
• Deep Gaussian Processes
• Shallow Neural Networks for Fluid Flow Reconstruction with Limited Sensors
• Searching for turbulence models by artificial neural network
• Assessment of supervised machine learning methods for fluid flows
• Convolutional neural network based hierarchical autoencoder for nonlinear mode decomposition of fluid field data
• Bayesian Neural Networks: An Introduction and Survey
• Overcoming Limitations of Mixture Density Networks: A Sampling and Fitting Framework for Multimodal Future Prediction
• Machine-learning-based reduced order modeling for unsteady flows around bluff bodies of various shapes
• A neural network approach for the blind deconvolution of turbulent flows
• Robust flow field reconstruction from limited measurements via sparse representation
• Multi-level Convolutional Autoencoder Networks for Parametric Prediction of Spatio-temporal Dynamics
• Photometric redshift estimation via deep learning
• Synthetic turbulent inflow generator using machine learning
• Quantifying model form uncertainty in Reynolds-averaged turbulence models with Bayesian deep neural networks
• A Deep Learning based Approach to Reduced Order Modeling for Turbulent Flow Control using LSTM Neural Networks
• Time-series learning of latent-space dynamics for reduced-order model closure
• Extreme learning machine for reduced order modeling of turbulent geophysical flows
• Experimental velocity data estimation for imperfect particle images using machine learning
• Sub-grid scale model classification and blending through deep learning
• Deep convolutional recurrent autoencoders for learning low-dimensional feature dynamics of fluid systems
• Operator-theoretic framework for forecasting nonlinear time series with kernel analog techniques
• A long short-term memory embedding for hybrid uplifted reduced order models
• Compressed Convolutional LSTM: An Efficient Deep Learning framework to Model High Fidelity 3D Turbulence
• Dropout as a Bayesian Approximation: Appendix
• An advanced hybrid deep adversarial autoencoder for parameterized nonlinear fluid flow modelling
• Super-Resolution Simulation for Real-Time Prediction of Urban Micrometeorology
• Dimensionality Reduction and Reduced Order Modeling for Traveling Wave Physics
• Airfoil wake modification with Gurney flap at Low-Reynolds number
• How Good is the Bayes Posterior in Deep Neural Networks Really?
• Multi-Resolution Dynamic Mode Decomposition
• Accelerating PDE-constrained Inverse Solutions with Deep Learning and Reduced Order Models
• From the Inner to Outer Milky Way: A Photometric Sample of 2.6 Million Red Clump Stars
• RoboJam: A Musical Mixture Density Network for Collaborative Touchscreen Interaction

Cited by in corpus (39)

• Machine learning based spatio-temporal super resolution reconstruction of turbulent flows
• Convolutional neural network and long short-term memory based reduced order surrogate for minimal turbulent channel flow
• Convolutional neural network based hierarchical autoencoder for nonlinear mode decomposition of fluid field data
• Improving aircraft performance using machine learning: a review
• Super-resolution and denoising of fluid flow using physics-informed convolutional neural networks without high-resolution labels
• Super-Resolution Analysis via Machine Learning: A Survey for Fluid Flows
• Physics guided machine learning using simplified theories
• Convolutional neural networks for fluid flow analysis: toward effective metamodeling and low-dimensionalization
• Sparse identification of nonlinear dynamics with low-dimensionalized flow representations
• Stable a posteriori LES of 2D turbulence using convolutional neural networks: Backscattering analysis and generalization to higher Re via transfer learning
• Experimental velocity data estimation for imperfect particle images using machine learning
• Generalization techniques of neural networks for fluid flow estimation
• Machine learning building-block-flow wall model for large-eddy simulation
• Assessments of epistemic uncertainty using Gaussian stochastic weight averaging for fluid-flow regression
• Uncertainty-aware Surrogate Models for Airfoil Flow Simulations with Denoising Diffusion Probabilistic Models
• Flow Completion Network: Inferring the Fluid Dynamics from Incomplete Flow Information using Graph Neural Networks
• Identifying key differences between linear stochastic estimation and neural networks for fluid flow regressions
• Semi Conditional Variational Auto-Encoder for Flow Reconstruction and Uncertainty Quantification from Limited Observations
• Mechanisms of a Convolutional Neural Network for Learning Three-dimensional Unsteady Wake Flow
• Robust training approach of neural networks for fluid flow state estimations
• Tensor-based flow reconstruction from optimally located sensor measurements
• Inserting machine-learned virtual wall velocity for large-eddy simulation of turbulent channel flows
• Reconstructing three-dimensional bluff body wake from sectional flow fields with convolutional neural networks
• Reduced Order Modeling with Shallow Recurrent Decoder Networks
• Reconstructing unsteady flows from sparse, noisy measurements with a physics-constrained convolutional neural network
• Reduced-order Model for Fluid Flows via Neural Ordinary Differential Equations
• Generalization capabilities and robustness of hybrid models grounded in physics compared to purely deep learning models
• Inferring ocean transport statistics with probabilistic neural networks
• Reducing Spatial Discretization Error on Coarse CFD Simulations Using an OpenFOAM-Embedded Deep Learning Framework
• Convolutional Long Short-Term Memory (convLSTM) for Spatio-Temporal Forecastings of Saturations and Pressure in the SACROC Field
• Data-driven geophysical forecasting: Simple, low-cost, and accurate baselines with kernel methods
• Model order reduction with neural networks: Application to laminar and turbulent flows
• Probabilistic neural network-based reduced-order surrogate for fluid flows
• On Deep-Learning-Based Closures for Algebraic Surrogate Models of Turbulent Flows
• A turbulent eddy-viscosity surrogate modeling framework for Reynolds-Averaged Navier-Stokes simulations
• Network-based analysis of fluid flows: Progress and outlook
• Multi-resolution Physics-Aware Recurrent Convolutional Neural Network for Complex Flows
• High Throughput Training of Deep Surrogates from Large Ensemble Runs
• Probabilistic neural networks for predicting energy dissipation rates in geophysical turbulent flows