Physics-informed neural networks for high-speed flows
Physics-informed neural networks for high-speed flows
Zhiping Mao,Ameya Dilip Jagtap,G. Karniadakis
2020 · DOI: 10.1016/j.cma.2019.112789
Computer Methods in Applied Mechanics and Engineering · 1,027회 인용
TLDR
In the current form, where the conservation laws are imposed at random points, PINNs are not as accurate as traditional numerical methods for forward problems but they are superior for inverse problems that cannot even be solved with standard techniques.