Constraint-Aware Neural Networks for Riemann Problems

Abstract

Neural networks are increasingly used in complex (data-driven) simulations as surrogates or for accelerating the computation of classical surrogates. In many applications physical constraints, such as mass or energy conservation, must be satisfied to obtain reliable results. However, standard machine learning algorithms are generally not tailored to respect such constraints. We propose two different strategies to generate constraint-aware neural networks. We test their performance in the context of front-capturing schemes for strongly nonlinear wave motion in compressible fluid flow. Precisely, in this context so-called Riemann problems have to be solved as surrogates. Their solution describes the local dynamics of the captured wave front in numerical simulations. Three model problems are considered: a cubic flux model problem, an isothermal two-phase flow model, and the Euler equations. We demonstrate that a decrease in the constraint deviation correlates with low discretization errors for all model problems, in addition to the structural advantage of fulfilling the constraint.

References in corpus (2)

• On the difficulty of training Recurrent Neural Networks
• Searching for Activation Functions

Cited by in corpus (15)

• Deep Learning in Deterministic Computational Mechanics
• Weak baselines and reporting biases lead to overoptimism in machine learning for fluid-related partial differential equations
• Discontinuity Computing using Physics-Informed Neural Network
• Structure-preserving neural networks
• Solution of Physics-based Bayesian Inverse Problems with Deep Generative Priors
• A priori analysis on deep learning of subgrid-scale parameterizations for Kraichnan turbulence
• Physics-informed neural networks for inverse problems in supersonic flows
• A probabilistic generative model for semi-supervised training of coarse-grained surrogates and enforcing physical constraints through virtual observables
• Enforcing Deterministic Constraints on Generative Adversarial Networks for Emulating Physical Systems
• GoRINNs: Godunov-Riemann Informed Neural Networks for Learning Hyperbolic Conservation Laws
• Meta-MgNet: Meta Multigrid Networks for Solving Parameterized Partial Differential Equations
• Learning to Discretize: Solving 1D Scalar Conservation Laws via Deep Reinforcement Learning
• A Molecular-Continuum Multiscale Model for Inviscid Liquid-Vapor Flow with Sharp Interfaces
• A multi-stage deep learning based algorithm for multiscale modelreduction
• Neural network-based Godunov corrections for approximate Riemann solvers using bi-fidelity learning