Comparing recurrent and convolutional neural networks for predicting wave propagation

02/20/2020
by   Stathi Fotiadis, et al.
4

Dynamical systems can be modelled by partial differential equations and numerical computations are used everywhere in science and engineering. In this work, we investigate the performance of recurrent and convolutional deep neural network architectures to predict the surface waves. The system is governed by the Saint-Venant equations. We improve on the long-term prediction over previous methods while keeping the inference time at a fraction of numerical simulations. We also show that convolutional networks perform at least as well as recurrent networks in this task. Finally, we assess the generalisation capability of each network by extrapolating in longer time-frames and in different physical settings.

READ FULL TEXT

page 2

page 4

page 9

page 11

research
04/14/2020

PhICNet: Physics-Incorporated Convolutional Recurrent Neural Networks for Modeling Dynamical Systems

Dynamical systems involving partial differential equations (PDEs) and or...
research
12/04/2018

Approximating the solution to wave propagation using deep neural networks

Humans gain an implicit understanding of physical laws through observing...
research
12/01/2020

Simulating Surface Wave Dynamics with Convolutional Networks

We investigate the performance of fully convolutional networks to simula...
research
06/11/2018

State Space Representations of Deep Neural Networks

This paper deals with neural networks as dynamical systems governed by d...
research
09/04/2017

DR-RNN: A deep residual recurrent neural network for model reduction

We introduce a deep residual recurrent neural network (DR-RNN) as an eff...
research
03/24/2022

The Cost-Accuracy Trade-Off In Operator Learning With Neural Networks

The term `surrogate modeling' in computational science and engineering r...
research
02/24/2018

Convolutional Neural Networks combined with Runge-Kutta Methods

A convolutional neural network for image classification can be construct...

Please sign up or login with your details

Forgot password? Click here to reset