A Fourier-basis physics-informed neural network reports better accuracy than conventional neural network baselines on the shock-prone Burgers equation and the periodic Helmholtz equation, with low sensitivity to activation function choice.
Zhang , author H
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
physics.flu-dyn 1years
2025 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Physics-informed Fourier Basis Neural Network for Fluid Mechanics
A Fourier-basis physics-informed neural network reports better accuracy than conventional neural network baselines on the shock-prone Burgers equation and the periodic Helmholtz equation, with low sensitivity to activation function choice.