Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
144 tokens/sec
GPT-4o
7 tokens/sec
Gemini 2.5 Pro Pro
45 tokens/sec
o3 Pro
4 tokens/sec
GPT-4.1 Pro
38 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

Discovering Artificial Viscosity Models for Discontinuous Galerkin Approximation of Conservation Laws using Physics-Informed Machine Learning (2402.16517v2)

Published 26 Feb 2024 in math.NA, cs.LG, and cs.NA

Abstract: Finite element-based high-order solvers of conservation laws offer large accuracy but face challenges near discontinuities due to the Gibbs phenomenon. Artificial viscosity is a popular and effective solution to this problem based on physical insight. In this work, we present a physics-informed machine learning algorithm to automate the discovery of artificial viscosity models in a non-supervised paradigm. The algorithm is inspired by reinforcement learning and trains a neural network acting cell-by-cell (the viscosity model) by minimizing a loss defined as the difference with respect to a reference solution thanks to automatic differentiation. This enables a dataset-free training procedure. We prove that the algorithm is effective by integrating it into a state-of-the-art Runge-Kutta discontinuous Galerkin solver. We showcase several numerical tests on scalar and vectorial problems, such as Burgers' and Euler's equations in one and two dimensions. Results demonstrate that the proposed approach trains a model that is able to outperform classical viscosity models. Moreover, we show that the learnt artificial viscosity model is able to generalize across different problems and parameters.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (64)
  1. Shock capturing with entropy-based artificial viscosity for staggered grid discontinuous spectral element method. Computers & Fluids, 98:152–163, 2014.
  2. Review of discontinuous Galerkin finite element methods for partial differential equations on complicated domains. Building bridges: connections and challenges in modern approaches to numerical partial differential equations, pages 281–310, 2016.
  3. Unified analysis of discontinuous Galerkin methods for elliptic problems. SIAM Journal on Numerical Analysis, 39(5):1749–1779, 2002.
  4. B. Ayuso and L. D. Marini. Discontinuous Galerkin methods for advection-diffusion-reaction problems. SIAM Journal on Numerical Analysis, 47(2):1391–1420, 2009.
  5. First order quasilinear equations with boundary conditions. Communications in Partial Differential Equations, 4(9):1017–1034, 1979.
  6. Shock capturing with PDE-based artificial viscosity for DGFEM: Part I. formulation. Journal of Computational Physics, 229(5):1810–1827, 2010.
  7. High-order discontinuous Galerkin discretization of transonic turbulent flows. In 47th AIAA Aerospace Sciences Meeting including The New Horizons Forum and Aerospace Exposition, page 180, 2009.
  8. Discontinuous Galerkin methods for first-order hyperbolic problems. Mathematical Models and Methods in Applied Sciences, 14(12):1893–1903, 2004.
  9. A problem-independent limiter for high-order Runge–Kutta discontinuous Galerkin methods. Journal of Computational Physics, 169(1):111–150, 2001.
  10. A deep learning algorithm to accelerate algebraic multigrid methods in finite element solvers of 3D elliptic PDEs. arXiv preprint arXiv:2304.10832, 2023.
  11. Discontinuous Galerkin methods: theory, computation and applications, volume 11. Springer Science & Business Media, 2012.
  12. TVB Runge-Kutta local projection discontinuous Galerkin finite element method for conservation laws III: One-dimensional systems. Journal of Computational Physics, 84(1):90–113, 1989.
  13. B. Cockburn and C.-W. Shu. The Runge–Kutta discontinuous Galerkin method for conservation laws v: multidimensional systems. Journal of Computational Physics, 141(2):199–224, 1998.
  14. Hyperbolic conservation laws in continuum physics, volume 3. Springer, 2005.
  15. D. A. Di Pietro and A. Ern. Mathematical aspects of discontinuous Galerkin methods, volume 69. Springer Science & Business Media, 2011.
  16. Controlling oscillations in high-order discontinuous Galerkin schemes using artificial viscosity tuned by neural networks. Journal of Computational Physics, 409:109304, 2020.
  17. M. Dumbser and M. Käser. An arbitrary high-order discontinuous Galerkin method for elastic waves on unstructured meshes—II. The three-dimensional isotropic case. Geophysical Journal International, 167(1):319–336, 2006.
  18. A posteriori subcell limiting of the discontinuous Galerkin finite element method for hyperbolic conservation laws. Journal of Computational Physics, 278:47–75, 2014.
  19. D. R. Durran. Numerical methods for fluid dynamics: With applications to geophysics, volume 32. Springer Science & Business Media, 2010.
  20. Stationary flow predictions using convolutional neural networks. In Numerical Mathematics and Advanced Applications ENUMATH 2019: European Conference, Egmond aan Zee, The Netherlands, September 30-October 4, pages 541–549. Springer, 2020.
  21. A comprehensive deep learning-based approach to reduced order modeling of nonlinear time-dependent parametrized PDEs. Journal of Scientific Computing, 87:1–36, 2021.
  22. Deep Learning. MIT press, 2016.
  23. D. Gottlieb and C.-W. Shu. On the Gibbs phenomenon and its resolution. SIAM Review, 39(4):644–668, 1997.
  24. Entropy viscosity method for nonlinear conservation laws. Journal of Computational Physics, 230(11):4248–4267, 2011.
  25. Dream to control: Learning behaviors by latent imagination. arXiv preprint arXiv:1912.01603, 2019.
  26. Physics-informed machine learning: A survey on problems, methods and applications. arXiv preprint arXiv:2211.08064, 2022.
  27. R. Hartmann. Adaptive discontinuous Galerkin methods with shock-capturing for the compressible Navier–Stokes equations. International Journal for Numerical Methods in Fluids, 51(9-10):1131–1156, 2006.
  28. Combining machine learning and domain decomposition methods for the solution of partial differential equations—a review. GAMM-Mitteilungen, 44(1):e202100001, 2021.
  29. D. Hendrycks and K. Gimpel. Gaussian error linear units (GELUs). arXiv preprint arXiv:1606.08415, 2016.
  30. J. S. Hesthaven. Numerical methods for conservation laws: From analysis to algorithms. SIAM, 2017.
  31. J. S. Hesthaven and T. Warburton. Nodal discontinuous Galerkin methods: algorithms, analysis, and applications. Springer Science & Business Media, 2007.
  32. Physics-informed machine learning. Nature Reviews Physics, 3(6):422–440, 2021.
  33. Nodal discontinuous Galerkin methods on graphics processors. Journal of Computational Physics, 228(21):7863–7882, 2009.
  34. Viscous shock capturing in a time-explicit discontinuous Galerkin method. Mathematical Modelling of Natural Phenomena, 6(3):57–83, 2011.
  35. Adaptive semidiscrete central-upwind schemes for nonconvex hyperbolic conservation laws. SIAM Journal on Scientific Computing, 29(6):2381–2401, 2007.
  36. A. Kurganov and E. Tadmor. Solution of two-dimensional Riemann problems for gas dynamics without Riemann problem solvers. Numerical Methods for Partial Differential Equations: An International Journal, 18(5):584–608, 2002.
  37. D. Kuzmin. A vertex-based hierarchical slope limiter for p-adaptive discontinuous Galerkin methods. Journal of Computational and Applied Mathematics, 233(12):3077–3085, 2010.
  38. A parallel, high-order discontinuous Galerkin code for laminar and turbulent flows. Computers & Fluids, 37(4):427–438, 2008.
  39. Continuous control with deep reinforcement learning. arXiv preprint arXiv:1509.02971, 2015.
  40. I. Loshchilov and F. Hutter. SGDR: Stochastic gradient descent with warm restarts. arXiv preprint arXiv:1608.03983, 2016.
  41. I. Loshchilov and F. Hutter. Decoupled weight decay regularization. arXiv preprint arXiv:1711.05101, 2017.
  42. Differentiable physics models for real-world offline model-based reinforcement learning. In 2021 IEEE International Conference on Robotics and Automation (ICRA), pages 4163–4170. IEEE, 2021.
  43. Suitability of artificial bulk viscosity for large-eddy simulation of turbulent flows with shocks. Journal of Computational Physics, 228(19):7368–7374, 2009.
  44. Automating turbulence modelling by multi-agent reinforcement learning. Nature Machine Intelligence, 3(1):87–96, 2021.
  45. G. Orlando. A filtering monotonization approach for DG discretizations of hyperbolic problems. Computers & Mathematics with Applications, 129:113–125, 2023.
  46. Automatic differentiation in Pytorch. NIPS 2017 Workshop on Autodiff, 2017.
  47. Pytorch: An imperative style, high-performance deep learning library. Advances in Neural Information Processing Systems, 32, 2019.
  48. P.-O. Persson and J. Peraire. Sub-cell shock capturing for discontinuous Galerkin methods. In 44th AIAA Aerospace Sciences Meeting and Exhibit, page 112, 2006.
  49. J. Qiu and C.-W. Shu. Hermite WENO schemes and their application as limiters for Runge–Kutta discontinuous Galerkin method: one-dimensional case. Journal of Computational Physics, 193(1):115–135, 2004.
  50. J. Qiu and C.-W. Shu. Runge–Kutta discontinuous Galerkin method using WENO limiters. SIAM Journal on Scientific Computing, 26(3):907–929, 2005.
  51. D. Ray and J. S. Hesthaven. Detecting troubled-cells on two-dimensional unstructured grids using a neural network. Journal of Computational Physics, 397:108845, 2019.
  52. V. V. Rusanov. The calculation of the interaction of non-stationary shock waves and obstacles. USSR Computational Mathematics and Mathematical Physics, 1(2):304–320, 1962.
  53. C. W. Schulz-Rinne. Classification of the Riemann problem for two-dimensional gas dynamics. SIAM Journal on Mathematical Analysis, 24(1):76–88, 1993.
  54. Controlling oscillations in spectral methods by local artificial viscosity governed by neural networks. Journal of Computational Physics, 431:110144, 2021.
  55. C.-W. Shu. High-order finite difference and finite volume WENO schemes and discontinuous Galerkin methods for CFD. International Journal of Computational Fluid Dynamics, 17(2):107–118, 2003.
  56. C.-W. Shu and S. Osher. Efficient implementation of essentially non-oscillatory shock-capturing schemes. Journal of Computational Physics, 77(2):439–471, 1988.
  57. G. A. Sod. A survey of several finite difference methods for systems of nonlinear hyperbolic conservation laws. Journal of Computational Physics, 27(1):1–31, 1978.
  58. Reinforcement learning: An introduction. MIT press, 2018.
  59. A machine learning approach to enhance the SUPG stabilization method for advection-dominated differential problems. Mathematics in Engineering, 5(2):1–26, 2023.
  60. P. Wesseling. Principles of computational fluid dynamics, volume 29. Springer Science & Business Media, 2009.
  61. Physics-informed machine learning approach for augmenting turbulence models: A comprehensive framework. Physical Review Fluids, 3(7):074602, 2018.
  62. J. Yu and J. S. Hesthaven. A study of several artificial viscosity models within the discontinuous Galerkin framework. Communications in Computational Physics, 27(5):1309–1343, 2020.
  63. Dive into Deep Learning. Cambridge University Press, 2023.
  64. Implementation of the entropy viscosity method with the discontinuous Galerkin method. Computer Methods in Applied Mechanics and Engineering, 253:479–490, 2013.

Summary

We haven't generated a summary for this paper yet.

Ai Sparkles Streamline Icon: https://streamlinehq.com Summarize Now