Underwater noise transmission in the ocean environment is a complex physical phenomenon involving not only widely varying physical parameters and dynamical scales but also uncertainties in the ocean parameters. It is challenging to construct generalized physical models that can predict transmission loss in a broad range of situations. In this regard, we propose a convolutional recurrent autoencoder network (CRAN) architecture, which is a data-driven deep learning model for learning far-field acoustic propagation. Being data-driven, the CRAN model relies only on the quality of the data and is agnostic to how the data are obtained. The CRAN model can learn a reduced-dimensional representation of physical data and can predict the far-field acoustic signal transmission loss distribution in the ocean environment. We demonstrate the ability of the CRAN model to learn far-field transmission loss distribution in a two-dimensional ocean domain with depth-dependent sources. Results show that the CRAN can learn the essential physical elements of acoustic signal transmission loss generated due to geometric spreading, refraction, and reflection from the ocean surface and bottom. Such ability of the CRAN to learn complex ocean acoustics transmission has the potential for real-time far-field underwater noise prediction for marine vessel decision-making and online control.
References
1.
Abadi
, M.
(2015
). “TensorFlow: Large-scale machine learning on heterogeneous systems
” https://www.tensorflow.org/ (Last viewed April 30, 2022).2.
Borrel-Jensen
, N.
, Engsig-Karup
, A. P.
, and Jeong
, C.-H.
(2021
). “Physics-informed neural networks for one-dimensional sound field predictions with parameterized sources and impedance boundaries
,” JASA Express Lett.
1
(12
), 122402
.3.
Bronstein
, M. M.
, Bruna
, J.
, LeCun
, Y.
, Szlam
, A.
, and Vandergheynst
, P.
(2017
). “Geometric deep learning: Going beyond Euclidean data
,” IEEE Signal Process. Mag.
34
(4
), 18
–42
.4.
Bukka
, S. R.
, Gupta
, R.
, Magee
, A. R.
, and Jaiman
, R. K.
(2021
). “Assessment of unsteady flow predictions using hybrid deep learning based reduced-order models
,” Phys. Fluids
33
(1
), 013601
.5.
Chi
, J.
, Li
, X.
, Wang
, H.
, Gao
, D.
, and Gerstoft
, P.
(2019
). “Sound source ranging using a feed-forward neural network trained with fitting-based early stopping
,” J. Acoust. Soc. Am.
146
(3
), EL258
–EL264
.6.
Deo
, I. K.
, and Jaiman
, R. K.
(2022
). “Predicting waves in fluids with deep neural network
,” Phys. Fluids
34
, 067108
.7.
Duarte
, C. M.
, Chapuis
, L.
, Collin
, S. P.
, Costa
, D. P.
, Devassy
, R. P.
, Eguiluz
, V. M.
, Erbe
, C.
, Gordon
, T. A.
, Halpern
, B. S.
, Harding
, H. R.
, Havlik
, M. N.
, Meekan
, M.
, Merchant
, N. D.
, Miksis-Olds
, J. L.
, Parsons
, M.
, Predragovic
, M.
, Radford
, A. N.
, Radford
, C. A.
, Simpson
, S. D.
, Slabbekoorn
, H.
, Staaterman
, E.
, Van Opzeeland
, I. C.
, Winderen
, J.
, Zhang
, X.
, and Juanes
, F.
(2021
). “The soundscape of the Anthropocene ocean
,” Science
371
(6529
), eaba4658
.8.
Erbe
, C.
, Marley
, S. A.
, Schoeman
, R. P.
, Smith
, J. N.
, Trigg
, L. E.
, and Embling
, C. B.
(2019
). “The effects of ship noise on marine mammals—A review
,” Front. Mar. Sci.
6
, 606
.9.
Ferguson
, E. L.
(2021
). “Multitask convolutional neural network for acoustic localization of a transiting broadband source using a hydrophone array
,” J. Acoust. Soc. Am.
150
(1
), 248
–256
.10.
Fotiadis
, S.
, Pignatelli
, E.
, Valencia
, M. L.
, Cantwell
, C.
, Storkey
, A.
, and Bharath
, A. A.
(2020
). “Comparing recurrent and convolutional neural networks for predicting wave propagation
,” arXiv:2002.08981.11.
Hornik
, K.
(1991
). “Approximation capabilities of multilayer feedforward networks
,” Neural Netw.
4
(2
), 251
–257
.12.
Hsieh
, W. W.
(2009
). Machine Learning Methods in the Environmental Sciences: Neural Networks and Kernels
(Cambridge University
, Cambridge, UK
).13.
Huang
, Z.
, Xu
, J.
, Gong
, Z.
, Wang
, H.
, and Yan
, Y.
(2018
). “Source localization using deep neural networks in a shallow water environment
,” J. Acoust. Soc. Am.
143
(5
), 2922
–2932
.14.
James
, K. R.
, and Dowling
, D. R.
(2005
). “A probability density function method for acoustic field uncertainty analysis
,” J. Acoust. Soc. Am.
118
(5
), 2802
–2810
.15.
James
, K. R.
, and Dowling
, D. R.
(2011
). “Pekeris waveguide comparisons of methods for predicting acoustic field amplitude uncertainty caused by a spatially uniform environmental uncertainty (L)
,” J. Acoust. Soc. Am.
129
(2
), 589
–592
.16.
Jensen
, F. B.
, Kuperman
, W. A.
, Porter
, M. B.
, Schmidt
, H.
, and Tolstoy
, A.
(2011
). Computational Ocean Acoustics
(Springer
, New York
).17.
18.
Lee
, K.
, and Carlberg
, K. T.
(2020
). “Model reduction of dynamical systems on nonlinear manifolds using deep convolutional autoencoders
,” J. Comput. Phys.
404
, 108973
.19.
Leshno
, M.
, Lin
, V. Y.
, Pinkus
, A.
, and Schocken
, S.
(1993
). “Multilayer feedforward networks with a nonpolynomial activation function can approximate any function
,” Neural Netw.
6
(6
), 861
–867
.20.
Mallik
, W.
, Jaiman
, R. K.
, and Jelovica
, J.
(2021
). “Kinematically consistent recurrent neural networks for learning inverse problems in wave propagation
,” arXiv:2110.03903.21.
Mallik
, W.
, Jaiman
, R. K.
, and Jelovica
, J.
(2022
). “Convolutional recurrent autoencoder network for learning underwater ocean acoustics
,” arXiv:2204.05573.22.
Mansour
, T.
(2019
). “Deep neural networks are lazy: On the inductive bias of deep learning
,” Master's thesis, MIT
, Cambridge, MA
.23.
McDougall
, T. J.
, Jackett
, D. R.
, Wright
, D. G.
, and Feistel
, R.
(2003
). “Accurate and computationally efficient algorithms for potential temperature and density of seawater
,” J. Atmos. Ocean. Technol.
20
(5
), 730
–741
.24.
Moseley
, B.
, Nissen-Meyer
, T.
, and Markham
, A.
(2020
). “Deep learning for fast simulation of seismic waves in complex media
,” Solid Earth
11
(4
), 1527
–1549
.25.
Niu
, H.
, Ozanich
, E.
, and Gerstoft
, P.
(2017
). “Ship localization in Santa Barbara Channel using machine learning classifiers
,” J. Acoust. Soc. Am.
142
(5
), EL455
–EL460
.26.
Porter
, M. B.
(2010
). “Bellhop: A beam/ray trace code
,” https://oalib-acoustics.org/website_resources/AcousticsToolbox/Bellhop-2010-1.pdf (Last viewed June 20, 2022).27.
Porter
, M. B.
, and Bucker
, H. P.
(1987
). “Gaussian beam tracing for computing ocean acoustic fields
,” J. Acoust. Soc. Am.
82
(4
), 1349
–1359
.28.
Porter
, M. B.
, and Liu
, Y.-C.
(1994
). “Finite-element ray tracing
,” Theor. Comput. Acoust.
2
, 947
–956
.29.
Smith
, J. D.
, Azizzadenesheli
, K.
, and Ross
, Z. E.
(2021
). “Eikonet: Solving the eikonal equation with deep neural networks
,” IEEE Trans. Geosci. Remote Sens.
59
(12
), 10685
–10696
.30.
Sorteberg
, W. E.
, Garasto
, S.
, Cantwell
, C. C.
, and Bharath
, A. A.
(2019
). “Approximating the solution of surface wave propagation using deep neural networks
,” in INNS Big Data and Deep Learning Conference
(Springer
, New York
), pp. 246
–256
.31.
Wang
, Z.
, Bovik
, A. C.
, Sheikh
, H. R.
, and Simoncelli
, E. P.
(2004
). “Image quality assessment: From error visibility to structural similarity
,” IEEE Trans. Image Process.
13
(4
), 600
–612
.© 2022 Acoustical Society of America.
2022
Acoustical Society of America
You do not currently have access to this content.