In this paper, we present a deep learning technique for data-driven predictions of wave propagation in a fluid medium. The technique relies on an attention-based convolutional recurrent autoencoder network (AB-CRAN). To construct a low-dimensional representation of wave propagation data, we employ a denoising-based convolutional autoencoder. The AB-CRAN architecture with attention-based long short-term memory cells forms our deep neural network model for the time marching of the low-dimensional features. We assess the proposed AB-CRAN framework against the standard recurrent neural network for the low-dimensional learning of wave propagation. To demonstrate the effectiveness of the AB-CRAN model, we consider three benchmark problems, namely, one-dimensional linear convection, the nonlinear viscous Burgers equation, and the two-dimensional Saint-Venant shallow water system. Using the spatial-temporal datasets from the benchmark problems, our novel AB-CRAN architecture accurately captures the wave amplitude and preserves the wave characteristics of the solution for long time horizons. The attention-based sequence-to-sequence network increases the time-horizon of prediction compared to the standard recurrent neural network with long short-term memory cells. The denoising autoencoder further reduces the mean squared error of prediction and improves the generalization capability in the parameter space.
Skip Nav Destination
Article navigation
June 2022
Research Article|
June 07 2022
Predicting waves in fluids with deep neural network
Special Collection:
Artificial Intelligence in Fluid Mechanics
Indu Kant Deo
;
Indu Kant Deo
a)
Department of Mechanical Engineering, University of British Columbia
, Vancouver, British Columbia V6T 1Z4, Canada
Search for other works by this author on:
Rajeev Jaiman
Rajeev Jaiman
b)
Department of Mechanical Engineering, University of British Columbia
, Vancouver, British Columbia V6T 1Z4, Canada
b)Author to whom correspondence should be addressed: [email protected]
Search for other works by this author on:
a)
Electronic mail: [email protected]
b)Author to whom correspondence should be addressed: [email protected]
Note: This paper is part of the special topic, Artificial Intelligence in Fluid Mechanics.
Physics of Fluids 34, 067108 (2022)
Article history
Received:
January 30 2022
Accepted:
May 13 2022
Citation
Indu Kant Deo, Rajeev Jaiman; Predicting waves in fluids with deep neural network. Physics of Fluids 1 June 2022; 34 (6): 067108. https://doi.org/10.1063/5.0086926
Download citation file:
Pay-Per-View Access
$40.00
Sign In
You could not be signed in. Please check your credentials and make sure you have an active account and try again.
Citing articles via
On Oreology, the fracture and flow of “milk's favorite cookie®”
Crystal E. Owens, Max R. Fan (范瑞), et al.
Chinese Academy of Science Journal Ranking System (2015–2023)
Cruz Y. Li (李雨桐), 李雨桐, et al.
Physics-informed neural networks for solving Reynolds-averaged Navier–Stokes equations
Hamidreza Eivazi, Mojtaba Tahani, et al.
Related Content
Three-dimensional deep learning-based reduced order model for unsteady flow dynamics with variable Reynolds number
Physics of Fluids (March 2022)
Predicting transmission loss in underwater acoustics using convolutional recurrent autoencoder network
J. Acoust. Soc. Am. (September 2022)
Assessment of unsteady flow predictions using hybrid deep learning based reduced-order models
Physics of Fluids (January 2021)
Deep neural network for learning wave scattering and interference of underwater acoustics
Physics of Fluids (January 2024)
Combined space–time reduced-order model with three-dimensional deep convolution for extrapolating fluid dynamics
Physics of Fluids (April 2023)