A Reinforcement Learning Based Slope Limiter for Two-Dimensional Finite Volume Schemes

DOI10.1007/978-3-031-40860-1_22MaRDI QIDQ6151396zbMATH OpenFDO

Authors Jens Keim, Anna Schwarz, Simone Chiocchetti, Ch. Rohde, Andrea Beck

Publication date 12 February 2024

Published in Springer Proceedings in Mathematics & Statistics (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1007/978-3-031-40860-1_22

zbMATH Keywords

finite volumeMUSCLreinforcement learning

Mathematics Subject Classification ID

Combinatorial aspects of tessellation and tiling problems (05B45) Euler equations (35Q31) Finite difference methods for initial value and initial-boundary value problems involving PDEs (65M06) Finite volume methods for initial value and initial-boundary value problems involving PDEs (65M08) Finite volume methods for boundary value problems involving PDEs (65N08) Mesh generation, refinement, and adaptive methods for boundary value problems involving PDEs (65N50) Learning and adaptive systems in artificial intelligence (68T05) Gas dynamics (general theory) (76N15)

Recommendations

• Two-dimensional slope limiters for finite volume schemes on non-coordinate-aligned meshes
• Learning to Discretize: Solving 1D Scalar Conservation Laws via Deep Reinforcement Learning
• DynAMO: multi-agent reinforcement learning for dynamic anticipatory mesh optimization with applications to hyperbolic conservation laws
• Deep reinforcement learning for adaptive mesh refinement
• A deep reinforcement learning framework for dynamic optimization of numerical schemes for compressible flow simulations

Cites work

• A data-driven shock capturing approach for discontinuous Galerkin methods
• A general reinforcement learning algorithm that masters chess, shogi, and Go through self-play
• A high-order finite volume method for systems of conservation laws-multi-dimensional optimal order detection (MOOD)
• A neural network based shock detection and localization approach for discontinuous Galerkin methods
• Algebraic Flux Correction II. Compressible Euler Equations
• Compact finite difference schemes with spectral-like resolution
• Detecting troubled-cells on two-dimensional unstructured grids using a neural network
• Efficient parallelization of a shock capturing for discontinuous Galerkin methods using finite volume sub-cells
• Filtering in Legendre spectral methods
• Finite Volume Methods for Hyperbolic Problems
• High resolution schemes for hyperbolic conservation laws
• Hyperbolic Conservation Laws in Continuum Physics
• On Upstream Differencing and Godunov-Type Schemes for Hyperbolic Conservation Laws
• Riemann Solvers and Numerical Methods for Fluid Dynamics
• Towards the ultimate conservative difference scheme. V. A second-order sequel to Godunov's method
• Uniformly High-Order Accurate Nonoscillatory Schemes. I

Cited in

(1)

• DynAMO: multi-agent reinforcement learning for dynamic anticipatory mesh optimization with applications to hyperbolic conservation laws

This page was built for publication: A Reinforcement Learning Based Slope Limiter for Two-Dimensional Finite Volume Schemes

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6151396)