A deep reinforcement learning framework for dynamic optimization of numerical schemes for compressible flow simulations

Basic methods in fluid mechanics (76Mxx) Numerical methods for partial differential equations, initial value and time-dependent initial-boundary value problems (65Mxx) Hyperbolic equations and hyperbolic systems (35Lxx)

Cites Work

Unnamed Item
Unnamed Item
An adaptive central-upwind weighted essentially non-oscillatory scheme
Scale separation for implicit large eddy simulation
On the spectral properties of shock-capturing schemes
The numerical simulation of two-dimensional fluid flow with strong shocks
Efficient implementation of essentially nonoscillatory shock-capturing schemes
Approximate Riemann solvers, parameter vectors, and difference schemes
Large-eddy simulation of the shock/turbulence interaction
Performance of under-resolved two-dimensional incompressible flow simulations. II
Assessing the numerical dissipation rate and viscosity in numerical simulations of fluid flows
On the proper setup of the double Mach reflection as a test case for the resolution of gas dynamics codes
Targeted ENO schemes with tailored resolution property for hyperbolic conservation laws
A second-order projection method for the incompressible Navier-Stokes equations
Implicit subgrid-scale modeling by adaptive deconvolution
Performance of under-resolved two-dimensional incompressible flow simulations
Efficient implementation of weighted ENO schemes
Numerical symmetry-preserving techniques for low-dissipation shock-capturing schemes
Direct shape optimization through deep reinforcement learning
An alternative formulation of targeted ENO scheme for hyperbolic conservation laws
WENO3-NN: a maximum-order three-point data-driven weighted essentially non-oscillatory scheme
Consistent and symmetry preserving data-driven interface reconstruction for the level-set method
Deep reinforcement learning of viscous incompressible flow
A multi-objective Bayesian optimization environment for systematic design of numerical schemes for compressible flow
Simple smoothness indicator WENO-Z scheme for hyperbolic conservation laws
A review on deep reinforcement learning for fluid mechanics
A family of high-order targeted ENO schemes for compressible-fluid simulations
A two-dimensional HLLC Riemann solver for conservation laws: application to Euler and magnetohydrodynamic flows
An adaptive local deconvolution method for implicit LES
Novel weighted essentially non-oscillatory schemes with adaptive weights
A parallel modular computing environment for three-dimensional multiresolution simulations of compressible flows
Numerical Solution of the Riemann Problem for Two-Dimensional Gas Dynamics
Total variation diminishing Runge-Kutta schemes
Comparison of Several Difference Schemes on 1D and 2D Test Problems for the Euler Equations
Artificial neural networks trained through deep reinforcement learning discover control strategies for active flow control
Solution of two-dimensional Riemann problems for gas dynamics without Riemann problem solvers
Data-Driven Science and Engineering
A Targeted ENO Scheme as Implicit Model for Turbulent and Genuine Subgrid Scales
A Hybrid Method with TENO Based Discontinuity Indicator for Hyperbolic Conservation Laws
JAX-fluids: a fully-differentiable high-order computational fluid dynamics solver for compressible two-phase flows
High-order finite-volume TENO schemes with dual ENO-like stencil selection for unstructured meshes
A new smoothed particle hydrodynamics method based on high-order moving-least-square targeted essentially non-oscillatory scheme for compressible flows
ALPACA -- a level-set based sharp-interface multiresolution solver for conservation laws

This page was built for publication: A deep reinforcement learning framework for dynamic optimization of numerical schemes for compressible flow simulations