A multi-task learning (MTL) method with adaptively weighted losses applied to a convolutional neural network (CNN) is proposed to estimate the range and depth of an acoustic source in deep ocean. The network input is the normalized sample covariance matrices of the broadband data received by a vertical line array. To handle the environmental uncertainty, both the training and validation data are generated by an acoustic propagation model based on multiple possible sets of environmental parameters. The sensitivity analysis is investigated to examine the effect of mismatched environmental parameters on the localization performance in the South China Sea environment. Among the environmental parameters, the array tilt is found to be the most important factor on the localization. Simulation results demonstrate that, compared with the conventional matched field processing (MFP), the CNN with MTL performs better and is more robust to array tilt in the deep-ocean environment. Tests on real data from the South China Sea also validate the method. In the specific ranges where the MFP fails, the method reliably estimates the ranges and depths of the underwater acoustic source.
References
1.
M. J.
Bianco
, P.
Gerstoft
, J.
Traer
, E.
Ozanich
, M. A.
Roch
, S.
Gannot
, and C.-A.
Deledalle
, “Machine learning in acoustics: Theory and applications
,” J. Acoust. Soc. Am.
146
(5
), 3590
–3628
(2019
).2.
H.
Niu
, E.
Reeves
, and P.
Gerstoft
, “Source localization in an ocean waveguide using supervised machine learning
,” J. Acoust. Soc. Am.
142
(3
), 1176
–1188
(2017
).3.
H.
Niu
, E.
Reeves
, and P.
Gerstoft
, “Ship localization in Santa Barbara channel using machine learning classifiers
,” J. Acoust. Soc. Am.
142
(5
), EL455
–EL460
(2017
).4.
Y.
Wang
and H.
Peng
, “Underwater acoustic source localization using generalized regression neural network
,” J. Acoust. Soc. Am.
143
(4
), 2321
–2331
(2018
).5.
V.
Premus
, M.
Evans
, and P.
Abbot
“Machine learning-based classification of recreational fishing vessel kinematics from broadband striation patterns
,” J. Acoust. Soc. Am.
147
(2
), EL184
–EL188
(2020
).6.
E. L.
Ferguson
, S. B.
Williams
, and C. T.
Jin
, “Sound source localization in a multipath environment using convolutional neural networks
,” in Proceedings of the 2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)
, April 15–20, Calgary, Canada
, pp. 2386
–2390
.7.
E. L.
Ferguson
, S. B.
Williams
, and C. T.
Jin
, “Convolutional neural network for single-sensor acoustic localization of a transiting broadband source in very shallow water
,” J. Acoust. Soc. Am.
146
(6
), 4687
–4698
(2019
).8.
R.
Lefort
, G.
Real
, and A.
Drémeau
, “Direct regressions for underwater acoustic source localization in fluctuating oceans
,” Appl. Acoust.
116
, 303
–310
(2017
).9.
Z.
Huang
, J.
Xu
, Z.
Gong
, H.
Wang
, and Y.
Yan
, “Source localization using deep neural networks in a shallow water environment
,” J. Acoust. Soc. Am.
143
(5
), 2922
–2932
(2018
).10.
H.
Niu
, Z.
Gong
, E.
Ozanich
, P.
Gerstoft
, H.
Wang
, and Z.
Li
, “Deep-learning source localization using multi-frequency magnitude-only data
,” J. Acoust. Soc. Am.
146
(1
), 211
–222
(2019
).11.
Y.
Liu
, H.
Niu
, and Z.
Li
, “Source ranging using ensemble convolutional networks in the direct zone of deep water
,” Chin. Phys. Lett.
36
(04
), 044302
(2019
).12.
W.
Wang
, H.
Ni
, L.
Su
, T.
Hu
, Q.
Ren
, P.
Gerstoft
, and L.
Ma
, “Deep transfer learning for source ranging: Deep-sea experiment results
,” J. Acoust. Soc. Am.
146
(4
), EL317
–EL322
(2019
).13.
J.
Chi
, X.
Li
, H.
Wang
, D.
Gao
, and P.
Gerstoft
, “Sound source ranging using a feed-forward neural network trained with fitting-based early stopping
,” J. Acoust. Soc. Am.
146
(3
), EL258
–EL264
(2019
).14.
J.
Yangzhou
, Z.
Ma
, and X.
Huang
, “A deep neural network approach to acoustic source localization in a shallow water tank experiment
,” J. Acoust. Soc. Am.
146
(6
), 4802
–4811
(2019
).15.
E.
Ozanich
, P.
Gerstoft
, and H.
Niu
, “A feedforward neural network for direction-of-arrival estimation
,” J. Acoust. Soc. Am.
147
(3
), 2035
–2048
(2020
).16.
W.
Liu
, Y.
Yang
, M.
Xu
, L.
Lv
, and Y.
Shi
, “Source localization in the deep ocean using a convolutional neural network
,” J. Acoust. Soc. Am.
147
(4
), EL314
–EL319
(2020
).17.
Y.
LeCun
, Y.
Bengio
, and G.
Hinton
, “Deep learning
,” Nature
521
, 436
–444
(2015
).18.
A.
Kendall
and Y.
Gal
, “What uncertainties do we need in Bayesian deep learning for computer vision?
,” arxiv.org/abs/1703.04977 (2017
).19.
A.
Kendall
, Y.
Gal
, and R.
Cipolla
, “Multi-task learning using uncertainty to weigh losses for scene geometry and semantics
,” arxiv.org/abs/1705.07115 (2017
).20.
S.
Ruder
, “An overview of multi-task learning in deep neural networks
,” arxiv.org/abs/1706.05098 (2017
).21.
Z. H.
Michalopoulou
and M. B.
Porter
, “Matched-field processing for broad-band source localization
,” IEEE J. Ocean. Eng.
21
(4
), 384
–392
(1996
).22.
A. B.
Baggeroer
, W. A.
Kuperman
, and P. N.
Mikhalevsky
, “An overview of matched field methods in ocean acoustics
,” IEEE J. Ocean. Eng.
18
, 401
–424
(1993
).23.
C.
Soares
and S. M.
Jesus
, “Broadband matched-field processing: Coherent and incoherent approaches
,” J. Acoust. Soc. Am.
113
(5
), 2587
–2598
(2003
).24.
K. L.
Gemba
, W. S.
Hodgkiss
, and P.
Gerstoft
, “Adaptive and compressive matched field processing
,” J. Acoust. Soc. Am.
141
(1
), 92
–103
(2017
).25.
K. L.
Gemba
, S.
Nannuru
, P.
Gerstoft
, and W. S.
Hodgkiss
, “Multi-frequency sparse Bayesian learning for robust matched field processing
,” J. Acoust. Soc. Am.
141
(5
), 3411
–3420
(2017
).26.
G.
Byun
, F.
Akins
, K. L.
Gemba
, H. C.
Song
, and W. A.
Kuperman
, “Multiple constraint matched field processing tolerant to array tilt mismatch
,” J. Acoust. Soc. Am.
147
(2
), 1231
–1238
(2020
).27.
I.
Goodfellow
, Y.
Bengio
, and A.
Courville
, Deep Learning
(MIT Press
, Cambridge, MA)
, 1st ed., Chap. 7, pp. 245
–246
(2016
).28.
M. B.
Porter
, “The Kraken normal mode program
,” http://oalib.hlsresearch.com/AcousticsToolbox/index.html (Last viewed May 27, 2018
).29.
F.
Chollet
, “Xception: Deep learning with depthwise separable convolutions
,” in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition
, Honolulu, HI
(July 21–26, 2017
).30.
S.
Ioffe
and C.
Szegedy
, “Batch normalization: Accelerating deep network training by reducing internal covariate shift
,” in Proceedings of The 32nd International Conference on Machine Learning
, Lille, France
(July 6–11, 2015
), pp. 448
–456
.31.
N.
Srivastava
, G.
Hinton
, and A.
Krizhevsky
, “Dropout: A simple way to prevent neural networks from overfitting
,” J. Mach. Learn. Res.
15
(1
), 1929
–1958
(2014
).32.
K.
He
, X.
Zhang
, S.
Ren
, and S.
Jian
, “Delving deep into rectifiers: Surpassing human-level performance on imagenet classification
,” in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition
, Boston, MA
(June 7–12, 2015
).33.
K.
He
, X.
Zhang
, S.
Ren
, and J.
Sun
, “Deep residual learning for image recognition
,” in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition
, Las Vegas, NV
(June 26–July 1, 2016
), pp. 770
–778
.34.
D.
Kingma
and J.
Ba
, “Adam: A method for stochastic optimization
,” arxiv.org/abs/1412.6980v9 (2017
).35.
I.
Loshchilov
and F.
Hutter
, “Decoupled weight decay regularization
,” arxiv.org/abs/1711.05101v3 (2019
).36.
F.
Chollet
, “Keras: Deep learning library for theano and tensorflow
,” https://keras.io (Last viewed May 1, 2019
).37.
M.
Abadi
, A.
Agarwal
, P.
Barham
, E.
Brevdo
, and X.
Zheng
, “Tensorflow: Large-scale machine learning on heterogeneous distributed systems
,” https://tensorflow.google.cn (Last viewed November 1, 2019
).38.
R.
Duan
, K.
Yang
, Y.
Ma
, Q.
Yang
, and H.
Li
, “Moving source localization with a single hydrophone using multipath time delays in the deep ocean
,” J. Acoust. Soc. Am.
136
(2
), EL159
–EL165
(2014
).39.
Z.
Lei
, K.
Yang
, and Y.
Ma
, “Passive localization in the deep ocean based on cross-correlation function matching
,” J. Acoust. Soc. Am.
139
(6
), EL196
–EL201
(2016
).40.
M.
Sun
, S.
Zhou
, and Z.
Li
, “Analysis of sound propagation in the direct-arrival zone in deep water with a vector sensor and its application
,” Acta Phys. Sin.
65
, 094302
(2016
).41.
R.
Mccargar
and L. M.
Zurk
, “Depth-based signal separation with vertical line arrays in the deep ocean
,” J. Acoust. Soc. Am.
133
(4
), EL320
–EL325
(2013
).42.
J.
Weng
and Y.
Yang
, “Experimental demonstration of shadow zone localization using deep water interference patterns measured by a single hydrophone
,” IEEE J. Ocean. Eng.
43
(4
), 1171
–1178
(2018
).43.
R.
Duan
, K.
Yang
, H.
Li
, and Y.
Ma
, “Acoustic-intensity striations below the critical depth: Interpretation and modeling
,” J. Acoust. Soc. Am.
142
(3
), EL245
–EL250
(2017
).44.
S.
Wu
, Z.
Li
, and J.
Qin
, “Geoacoustic inversion for bottom parameters in the deep-water area of the South China Sea
,” Chin. Phys. Lett.
32
(12
), 124301
(2015
).45.
E. C.
Shang
and Y. Y.
Wang
, “Environmental mismatching effects on source localization processing in mode space
,” J. Acoust. Soc. Am.
89
(5
), 2285
–2290
(1991
).© 2020 Acoustical Society of America.
2020
Acoustical Society of America
You do not currently have access to this content.