Uniformly Accurate Machine Learning Based Hydrodynamic Models for Kinetic Equations

Abstract

A new framework is introduced for constructing interpretable and truly reliable reduced models for multiscale problems in situations without scale separation. Hydrodynamic approximation to the kinetic equation is used as an example to illustrate the main steps and issues involved. To this end, a set of generalized moments are constructed first to optimally represent the underlying velocity distribution. The well-known closure problem is then solved with the aim of best capturing the associated dynamics of the kinetic equation. The issue of physical constraints such as Galilean invariance is addressed and an active learning procedure is introduced to help ensure that the dataset used is representative enough. The reduced system takes the form of a conventional moment system and works regardless of the numerical discretization used. Numerical results are presented for the BGK (Bhatnagar--Gross--Krook) model and binary collision of Maxwell molecules. We demonstrate that the reduced model achieves a uniform accuracy in a wide range of Knudsen numbers spanning from the hydrodynamic limit to free molecular flow.

arXiv commentProceedings of the National Academy of Sciences (2019)

References in corpus (19)

• Adam: A Method for Stochastic Optimization
• Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
• Deep Potential Molecular Dynamics: a scalable model with the accuracy of quantum mechanics
• Turbulence Modeling in the Age of Data
• Deep learning for universal linear embeddings of nonlinear dynamics
• Hidden Physics Models: Machine Learning of Nonlinear Partial Differential Equations
• Data-driven discovery of coordinates and governing equations
• A Physics Informed Machine Learning Approach for Reconstructing Reynolds Stress Modeling Discrepancies Based on DNS Data
• PDE-Net 2.0: Learning PDEs from Data with A Numeric-Symbolic Hybrid Deep Network
• Active Learning of Uniformly Accurate Inter-atomic Potentials for Materials Simulation
• Extended dynamic mode decomposition with dictionary learning: a data-driven adaptive spectral decomposition of the Koopman operator
• A class of asymptotic preserving schemes for kinetic equations and related problems with stiff sources
• Data-Driven Forecasting of High-Dimensional Chaotic Systems with Long Short-Term Memory Networks
• Deep Potential: a general representation of a many-body potential energy surface
• PDE-Net: Learning PDEs from Data
• Discovery of Nonlinear Multiscale Systems: Sampling Strategies and Embeddings
• End-to-end Symmetry Preserving Inter-atomic Potential Energy Model for Finite and Extended Systems
• Solid Harmonic Wavelet Scattering for Predictions of Molecule Properties
• Learning Koopman Invariant Subspaces for Dynamic Mode Decomposition

Cited by in corpus (32)

• Frequency Principle: Fourier Analysis Sheds Light on Deep Neural Networks
• DLGA-PDE: Discovery of PDEs with incomplete candidate library via combination of deep learning and genetic algorithm
• 2022 Review of Data-Driven Plasma Science
• Supervised learning from noisy observations: Combining machine-learning techniques with data assimilation
• Combining machine learning and data assimilation to forecast dynamical systems from noisy partial observations
• Learning nonlocal constitutive models with neural networks
• OnsagerNet: Learning Stable and Interpretable Dynamics using a Generalized Onsager Principle
• Machine learning moment closure models for the radiative transfer equation I: directly learning a gradient based closure
• Extracting Interpretable Physical Parameters from Spatiotemporal Systems using Unsupervised Learning
• Deep Fictitious Play for Finding Markovian Nash Equilibrium in Multi-Agent Games
• Machine learning based non-Newtonian fluid model with molecular fidelity
• Integrating Machine Learning with Physics-Based Modeling
• Asymptotic-Preserving Neural Networks for multiscale hyperbolic models of epidemic spread
• Image Inversion and Uncertainty Quantification for Constitutive Laws of Pattern Formation
• Data-driven, multi-moment fluid modeling of Landau damping
• Physics-informed neural networks for solving forward and inverse flow problems via the Boltzmann-BGK formulation
• Learning orbital dynamics of binary black hole systems from gravitational wave measurements
• Learning Thermodynamically Stable and Galilean Invariant Partial Differential Equations for Non-equilibrium Flows
• An equivariant neural operator for developing nonlocal tensorial constitutive models
• Separable Physics-informed Neural Networks for Solving the BGK Model of the Boltzmann Equation
• Learning of viscosity functions in rarefied gas flows with physics-informed neural networks
• DeePN${}^2$: A deep learning-based non-Newtonian hydrodynamic model
• Hyperbolic Machine Learning Moment Closures for the BGK Equations
• Data-Driven Constitutive Relation Reveals Scaling Law for Hydrodynamic Transport Coefficients
• Frame-independent vector-cloud neural network for nonlocal constitutive modeling on arbitrary grids
• Learning of discrete models of variational PDEs from data
• Machine learning moment closure models for the radiative transfer equation III: enforcing hyperbolicity and physical characteristic speeds
• Solving continuum and rarefied flows using differentiable programming
• The model reduction of the Vlasov-Poisson-Fokker-Planck system to the Poisson-Nernst-Planck system via the Deep Neural Network Approach
• Machine learning and serving of discrete field theories -- when artificial intelligence meets the discrete universe
• Learning invariance preserving moment closure model for Boltzmann-BGK equation
• A Positive and Stable L2-minimization Based Moment Method for the Boltzmann Equation of Gas dynamics