Timezone: »

 
Physics Informed RNN-DCT Networks for Time-Dependent Partial Differential Equations
Benjamin Wu · Oliver Hennigh · Jan Kautz · Sanjay Choudhry · Wonmin Byeon

@
in Machine Learning and the Physical Sciences »

Physics-informed neural networks allow models to be trained by physical laws described by general nonlinear partial differential equations. However, traditional architectures struggle to solve more challenging time-dependent problems. In this work, we present a novel physics-informed framework for solving time-dependent partial differential equations. Our proposed model utilizes discrete cosine transforms to encode spatial frequencies and recurrent neural networks to process the time evolution, achieving state-of-the-art performance on the Taylor-Green vortex relative to other physics-informed baseline models.

Author Information

Benjamin Wu (National Astronomical Observatory of Japan)
Oliver Hennigh (Nvidia)
Jan Kautz (NVIDIA)
Sanjay Choudhry (NVIDIA)
Wonmin Byeon (NVIDIA Research)

More from the Same Authors