Hidden Fluid Mechanics: A Navier-Stokes Informed Deep Learning Framework for Assimilating Flow Visualization Data

Abstract

We present hidden fluid mechanics (HFM), a physics informed deep learning framework capable of encoding an important class of physical laws governing fluid motions, namely the Navier-Stokes equations. In particular, we seek to leverage the underlying conservation laws (i.e., for mass, momentum, and energy) to infer hidden quantities of interest such as velocity and pressure fields merely from spatio-temporal visualizations of a passive scaler (e.g., dye or smoke), transported in arbitrarily complex domains (e.g., in human arteries or brain aneurysms). Our approach towards solving the aforementioned data assimilation problem is unique as we design an algorithm that is agnostic to the geometry or the initial and boundary conditions. This makes HFM highly flexible in choosing the spatio-temporal domain of interest for data acquisition as well as subsequent training and predictions. Consequently, the predictions made by HFM are among those cases where a pure machine learning strategy or a mere scientific computing approach simply cannot reproduce. The proposed algorithm achieves accurate predictions of the pressure and velocity fields in both two and three dimensional flows for several benchmark problems motivated by real-world applications. Our results demonstrate that this relatively simple methodology can be used in physical and biomedical problems to extract valuable quantitative information (e.g., lift and drag forces or wall shear stresses in arteries) for which direct measurements may not be possible.

References in corpus (9)

• Adam: A Method for Stochastic Optimization
• TensorFlow: Large-Scale Machine Learning on Heterogeneous Distributed Systems
• Hidden Physics Models: Machine Learning of Nonlinear Partial Differential Equations
• Physics Informed Deep Learning (Part I): Data-driven Solutions of Nonlinear Partial Differential Equations
• Neural Ordinary Differential Equations
• Multistep Neural Networks for Data-driven Discovery of Nonlinear Dynamical Systems
• On the Expressive Power of Deep Neural Networks
• Active learning of constitutive relation from mesoscopic dynamics for macroscopic modeling of non-Newtonian flows
• Deep Multi-fidelity Gaussian Processes

Cited by in corpus (34)

• fPINNs: Fractional Physics-Informed Neural Networks
• Surrogate Modeling for Fluid Flows Based on Physics-Constrained Deep Learning Without Simulation Data
• A composite neural network that learns from multi-fidelity data: Application to function approximation and inverse PDE problems
• Integrating Machine Learning and Multiscale Modeling: Perspectives, Challenges, and Opportunities in the Biological, Biomedical, and Behavioral Sciences
• Deep Learning Methods for Reynolds-Averaged Navier-Stokes Simulations of Airfoil Flows
• SciANN: A Keras/Tensorflow wrapper for scientific computations and physics-informed deep learning using artificial neural networks
• Efficient training of physics-informed neural networks via importance sampling
• Variational Physics-Informed Neural Networks For Solving Partial Differential Equations
• Understanding and mitigating gradient pathologies in physics-informed neural networks
• Enforcing Statistical Constraints in Generative Adversarial Networks for Modeling Chaotic Dynamical Systems
• Deep learning observables in computational fluid dynamics
• Physics Informed Neural Networks for Simulating Radiative Transfer
• Solver-in-the-Loop: Learning from Differentiable Physics to Interact with Iterative PDE-Solvers
• Iterative Surrogate Model Optimization (ISMO): An active learning algorithm for PDE constrained optimization with deep neural networks
• Active Training of Physics-Informed Neural Networks to Aggregate and Interpolate Parametric Solutions to the Navier-Stokes Equations
• A Derivative-Free Method for Solving Elliptic Partial Differential Equations with Deep Neural Networks
• Teaching the Incompressible Navier-Stokes Equations to Fast Neural Surrogate Models in 3D
• A solver for subsonic flow around airfoils based on physics-informed neural networks and mesh transformation
• A neural network multigrid solver for the Navier-Stokes equations
• Learning to Control PDEs with Differentiable Physics
• Physics-Guided Machine Learning for Scientific Discovery: An Application in Simulating Lake Temperature Profiles
• Estimates on the generalization error of Physics Informed Neural Networks (PINNs) for approximating PDEs
• Semi Conditional Variational Auto-Encoder for Flow Reconstruction and Uncertainty Quantification from Limited Observations
• Physics-Constrained Bayesian Neural Network for Fluid Flow Reconstruction with Sparse and Noisy Data
• IDRLnet: A Physics-Informed Neural Network Library
• HyperPINN: Learning parameterized differential equations with physics-informed hypernetworks
• Bridging the Gap: Machine Learning to Resolve Improperly Modeled Dynamics
• Learning Incompressible Fluid Dynamics from Scratch -- Towards Fast, Differentiable Fluid Models that Generalize
• Solving Elliptic Equations with Brownian Motion: Bias Reduction and Temporal Difference Learning
• Learning Green's Functions of Linear Reaction-Diffusion Equations with Application to Fast Numerical Solver
• Deep reinforcement learning for the control of conjugate heat transfer with application to workpiece cooling
• Parameter identification for a damage model using a physics informed neural network
• Physics Informed Neural Networks (PINNs)for approximating nonlinear dispersive PDEs
• Estimates on the generalization error of Physics Informed Neural Networks (PINNs) for approximating a class of inverse problems for PDEs