Neural network-based Godunov corrections for approximate Riemann solvers using bi-fidelity learning
This addresses a domain-specific problem in computational fluid dynamics by improving solver efficiency, though it is incremental as it builds on existing approximate methods.
The paper tackled the computational cost of exact Riemann solvers for hyperbolic PDEs by proposing neural network-based surrogate models to correct approximate solvers, achieving robust and accurate results in 1D and 2D applications.
The Riemann problem is fundamental in the computational modeling of hyperbolic partial differential equations, enabling the development of stable and accurate upwind schemes. While exact solvers provide robust upwinding fluxes, their high computational cost necessitates approximate solvers. Although approximate solvers achieve accuracy in many scenarios, they produce inaccurate solutions in certain cases. To overcome this limitation, we propose constructing neural network-based surrogate models, trained using supervised learning, designed to map interior and exterior conservative state variables to the corresponding exact flux. Specifically, we propose two distinct approaches: one utilizing a vanilla neural network and the other employing a bi-fidelity neural network. The performance of the proposed approaches is demonstrated through applications to one-dimensional and two-dimensional partial differential equations, showcasing their robustness and accuracy.