Comparing Recurrent and Convolutional Neural Networks for Predicting Wave Propagation
Abstract
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.
Cite
Text
Fotiadis et al. "Comparing Recurrent and Convolutional Neural Networks for Predicting Wave Propagation." ICLR 2020 Workshops: DeepDiffEq, 2020.Markdown
[Fotiadis et al. "Comparing Recurrent and Convolutional Neural Networks for Predicting Wave Propagation." ICLR 2020 Workshops: DeepDiffEq, 2020.](https://mlanthology.org/iclrw/2020/fotiadis2020iclrw-comparing/)BibTeX
@inproceedings{fotiadis2020iclrw-comparing,
title = {{Comparing Recurrent and Convolutional Neural Networks for Predicting Wave Propagation}},
author = {Fotiadis, Stathi and Pignatelli, Eduardo and Valencia, Mario Lino and Cantwell, Chris and Storkey, Amos and Bharath, Anil A.},
booktitle = {ICLR 2020 Workshops: DeepDiffEq},
year = {2020},
url = {https://mlanthology.org/iclrw/2020/fotiadis2020iclrw-comparing/}
}