A learned conservative semi-Lagrangian finite volume scheme for transport simulations
arXiv:2302.10398 · doi:10.1016/j.jcp.2023.112329
Abstract
Semi-Lagrangian (SL) schemes are known as a major numerical tool for solving transport equations with many advantages and have been widely deployed in the fields of computational fluid dynamics, plasma physics modeling, numerical weather prediction, among others. In this work, we develop a novel machine learning-assisted approach to accelerate the conventional SL finite volume (FV) schemes. The proposed scheme avoids the expensive tracking of upstream cells but attempts to learn the SL discretization from the data by incorporating specific inductive biases in the neural network, significantly simplifying the algorithm implementation and leading to improved efficiency. In addition, the method delivers sharp shock transitions and a level of accuracy that would typically require a much finer grid with traditional transport solvers. Numerical tests demonstrate the effectiveness and efficiency of the proposed method.
arXiv comment24 pages
References in corpus (8)
- DeepONet: Learning nonlinear operators for identifying differential equations based on the universal approximation theorem of operators
- Gradient-enhanced physics-informed neural networks for forward and inverse PDE problems
- Learning data driven discretizations for partial differential equations
- Data Driven Governing Equations Approximation Using Deep Neural Networks
- A positivity-preserving high-order semi-Lagrangian discontinuous Galerkin scheme for the Vlasov-Poisson equations
- Data-Driven Deep Learning of Partial Differential Equations in Modal Space
- Learned discretizations for passive scalar advection in a 2-D turbulent flow
- Error-correcting neural networks for semi-Lagrangian advection in the level-set method