1. Learning rays via deep neural network in a ray-based IPDG method for high-frequency Helmholtz equations in inhomogeneous media.
- Author
-
Yeung, Tak Shing Au, Cheung, Ka Chun, Chung, Eric T., Fu, Shubin, and Qian, Jianliang
- Subjects
- *
ARTIFICIAL neural networks , *INHOMOGENEOUS materials , *HELMHOLTZ equation , *WAVE functions , *DEEP learning , *PLANE wavefronts - Abstract
We develop a deep learning approach to extract ray directions at discrete locations by analyzing highly oscillatory wave fields. A deep neural network is trained on a set of local plane-wave fields to predict ray directions at discrete locations. The resulting deep neural network is then applied to a reduced-frequency Helmholtz solution to extract ray directions, which are further incorporated into a ray-based interior-penalty discontinuous Galerkin (IPDG) method to solve the corresponding Helmholtz equations at higher frequencies. In this way, we observe no apparent pollution effects in the resulting Helmholtz solutions in inhomogeneous media. Our 2D and 3D numerical results show that the proposed scheme is very efficient and yields highly accurate solutions. • A novel IPDG method is developed for solving high-frequency Helmholtz equation. • Plane wave functions are used for basis functions. • Neural network is used to find dominant wave directions with low frequency wavefield. • Extension examples in 2D and 3D are provided. [ABSTRACT FROM AUTHOR]
- Published
- 2022
- Full Text
- View/download PDF