Thermodynamically consistent physics-informed neural networks for hyperbolic systems
From MaRDI portal
Publication:6355686
DOI10.1016/J.JCP.2021.110754arXiv2012.05343WikidataQ115571336 ScholiaQ115571336MaRDI QIDQ6355686FDOQ6355686
Authors: Ravi G. Patel, Indu Manickam, Nathaniel Trask, Mitchell A. Wood, Myoungkyu Lee, Ignacio Tomas, Eric C. Cyr 
Publication date: 9 December 2020
Abstract: Physics-informed neural network architectures have emerged as a powerful tool for developing flexible PDE solvers which easily assimilate data, but face challenges related to the PDE discretization underpinning them. By instead adapting a least squares space-time control volume scheme, we circumvent issues particularly related to imposition of boundary conditions and conservation while reducing solution regularity requirements. Additionally, connections to classical finite volume methods allows application of biases toward entropy solutions and total variation diminishing properties. For inverse problems, we may impose further thermodynamic biases, allowing us to fit shock hydrodynamics models to molecular simulation of rarefied gases and metals. The resulting data-driven equations of state may be incorporated into traditional shock hydrodynamics codes.
Hyperbolic equations and hyperbolic systems (35Lxx) Artificial intelligence (68Txx) Numerical methods for partial differential equations, initial value and time-dependent initial-boundary value problems (65Mxx)
This page was built for publication: Thermodynamically consistent physics-informed neural networks for hyperbolic systems
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6355686)
