Physics-informed neural networks for the shallow-water equations on the sphere

DOI10.1016/J.JCP.2022.111024arXiv2104.00615WikidataQ114163357 ScholiaQ114163357MaRDI QIDQ6364358FDOQ6364358

Publication date: 1 April 2021

Abstract: We propose the use of physics-informed neural networks for solving the shallow-water equations on the sphere in the meteorological context. Physics-informed neural networks are trained to satisfy the differential equations along with the prescribed initial and boundary data, and thus can be seen as an alternative approach to solving differential equations compared to traditional numerical approaches such as finite difference, finite volume or spectral methods. We discuss the training difficulties of physics-informed neural networks for the shallow-water equations on the sphere and propose a simple multi-model approach to tackle test cases of comparatively long time intervals. Here we train a sequence of neural networks instead of a single neural network for the entire integration interval. We also avoid the use of a boundary value loss by encoding the boundary conditions in a custom neural network layer. We illustrate the abilities of the method by solving the most prominent test cases proposed by Williamson et al. [J. Comput. Phys. 102 (1992), 211-224].

Mathematics Subject Classification ID

Artificial intelligence (68Txx) Numerical methods for partial differential equations, initial value and time-dependent initial-boundary value problems (65Mxx) Basic methods in fluid mechanics (76Mxx)

This page was built for publication: Physics-informed neural networks for the shallow-water equations on the sphere

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6364358)