Advances and applications of machine learning in underwater acoustics

Abstract

Recent advancements in machine learning (ML) techniques applied to underwater acoustics have significantly impacted various aspects of this field, such as source localization, target recognition, communication, and geoacoustic inversion. This review provides a comprehensive summary and evaluation of these developments. As a data-driven approach, ML played a pivotal role in discerning intricate relationships between input features and desired labels based on the provided training dataset. They are achieving success in ocean acoustic applications through ML hinges on several critical factors, including well-designed input feature preprocessing, appropriate labels, choice of ML models, effective training strategy, and availability of ample training and validation datasets. This review highlights noteworthy results from published studies to illustrate the effectiveness of ML methods in diverse application scenarios. In addition, it delves into the essential techniques employed within these applications. To understand the utility of ML in underwater acoustics, one must analyze its advantages and limitations. This assessment will aid in identifying scenarios where ML excels and those where it may face challenges. In addition, it provides insights into promising avenues for future research, shedding light on potential research directions that warrant exploration.

Keywords

Machine learning / Underwater acoustics / Source localization / Target recognition / Communication / Geoacoustic inversion

References

[1] Benson J, Chapman NR, Antoniou A. Geoacoustic model inversion using artificial neural networks. Inverse Prob. 2000, 16(6): 1627-1639

[2] Bianco MJ, Gerstoft P, Traer J, Ozanich E, Roch MA, Gannot S, Deledalle CA. Machine learning in acoustics: Theory and applications. J Acoust Soc Am. 2019, 146(5): 3590-3628

[3] Boashash B, O’shea P. A methodology for detection and classification of some underwater acoustic signals using time-frequency analysis techniques. IEEE Trans Acoust Speech Signal Proc. 1990, 38(11): 1829-1841

[4] Caiti A, Jesus S. Acoustic estimation of seafloor parameters: A radial basis functions approach. J Acoust Soc Am. 1996, 100(3): 1473-1481

[5] Caiti A, Parisini T. Mapping ocean sediments by RBF networks. IEEE J Ocean Eng. 1994, 19(4): 577-582

[6] Cao X, Togneri R, Zhang X, Yu Y. Convolutional neural network with second-order pooling for underwater target classification. IEEE Sens J. 2018, 19(8): 3058-3066

[7] Chen R, Schmidt H. Model-based convolutional neural network approach to underwater source-range estimation. J Acoust Soc Am. 2021, 149(1): 405-420

[8] Chen Y, Xu XN (2017) The research of underwater target recognition method based on deep learning. 2017 IEEE International Conference on Signal Processing, Communications and Computing (ICSPCC), Xiamen, China, 22-25 October 2017, pp 1–5

[9] Chen Y, Yu W, Sun X, Wan L, Tao Y, Xu X. Environment-aware communication channel quality prediction for underwater acoustic transmissions: A machine learning method. Appl Acoust. 2021, 181

[10] Chen Y, Zhu J, Wan L, Fang X, Tong F, Xu X. Routing failure prediction and repairing for AUV-assisted underwater acoustic sensor networks in uncertain ocean environments. Appl Acoust. 2022, 186

[11] Chen Z, He Z, Niu K, Rong Y. Neural network-based symbol detection in high-speed OFDM underwater acoustic communication. 2018, Hangzhou, In 2018 10th International Conference on Wireless Com-munications and Signal Processing (WCSP): 15

[12] Chi J, Li XL, Wang HZ, Gao DZ, Gerstoft P. Sound source ranging using a feed-forward neural network trained with fitting-based early stopping. J Acoust Soc Am. 2019, 146(3): EL258-EL264

[13] Chu H, Li C, Wang H, Wang J, Tai Y, Zhang Y, Yang F, Benezeth Y. A deep-learning based high-gain method for underwater acoustic signal detection in intensity fluctuation environments. Appl Acoust. 2023, 211

[14] Collins MD, Kuperman WA. Focalization: Environmental focusing and source localization. J Acoust Soc Am. 1991, 90(6): 1410-1422

[15] Collins MD, Kuperman WA, Schmidt H. Nonlinear inversion for ocean-bottom properties. J Acoust Soc Am. 1992, 92(5): 2770-2783

[16] Dong Y, Shen X, Jiang Z, Wang H. Recognition of imbalanced underwater acoustic datasets with exponentially weighted cross-entropy loss. Appl Acoust. 2021, 174

[17] Dong Y, Shen X, Wang H. Bidirectional denoising autoencoders-based robust representation learning for underwater acoustic target signal denoising. IEEE Trans Instrum Meas. 2022, 71: 1-8

[18] Dosso SE, Wilmut MJ. Uncertainty estimation in simultaneous Bayesian tracking and environmental inversion. J Acoust Soc Am. 2008, 124(1): 82-97

[19] Dosso SE, Wilmut MJ. Comparison of focalization and marginalization for Bayesian tracking in an uncertain ocean environment. J Acoust Soc Am. 2009, 125(1): 717-722

[20] Feng S, Zhu X. A Transformer-Based Deep Learning Network for Underwater Acoustic Target Recognition. IEEE Geosci Remote Sens Lett. 2022, 19: 1-5

[21] Ferguson EL. Multitask convolutional neural network for acoustic localization of a transiting broadband source using a hydrophone array. J Acoust Soc Am. 2021, 150(1): 248-256

[22] Ferguson EL, Williams SB, Jin CT. Convolutional neural network for single-sensor acoustic localization of a transiting broadband source in very shallow water. J Acoust Soc Am. 2019, 146(6): 4687-4698

[23] Finette S, Mignerey PC. Stochastic matched-field localization of an acoustic source based on principles of Riemannian geometry. J Acoust Soc Am. 2018, 143(6): 3628-3638

[24] Frederick C, Villar S, Michalopoulou ZH. Seabed classification using physics-based modeling and machine learning. J Acoust Soc Am. 2020, 148(2): 859-872

[25] Fu Q, Song A. Adaptive modulation for underwater acoustic communications based on reinforcement learning. 2018, Charleston, SC, USA, Proceedings of OCEANS 2018 MTS/IEEE Charleston: 18

[26] Ge FX, Bai YY, Li MJ, Zhu GP, Yin JW. Label distribution-guided transfer learning for underwater source localization. J Acoust Soc Am. 2022, 151(6): 4140-4149

[27] Geng X, Zheng YR (2022) Exploiting propagation delay in underwater acoustic communication networks via deep reinforcement learning. IEEE Trans Neural Netw Learn Syst 1–12. https://doi.org/10.1109/TNNLS.2022.3170050

[28] Gerstoft P. Inversion of seismoacoustic data using genetic algorithms and a posteriori probability distributions. J Acoust Soc Am. 1994, 95(2): 770-782

[29] Gingras DF, Gerstoft P. Inversion for geometric and geoacoustic parameters in shallow water: Experimental results. J Acoust Soc Am. 1995, 97(6): 3589-3598

[30] Goldwater M, Zitterbart DP, Wright D, Bonnel J. Machine-learning-based simultaneous detection and ranging of impulsive baleen whale vocalizations using a single hydrophone. J Acoust Soc Am. 2023, 153(2): 1094-1107

[31] He Y, Han G, Jiang J, Wang H, Martinez-Garcia M. A trust update mechanism based on reinforcement learning in underwater acoustic sensor networks. IEEE Trans Mob Comput. 2020, 21(3): 811-821

[32] Hemminger TL, Pao YH. Detection and classification of underwater acoustic transients using neural networks. IEEE Trans Neural Networks. 1994, 5(5): 712-718

[33] Huang ZQ, Xu J, Gong ZX, Wang HB, Yan YH. Source localization using deep neural networks in a shallow water environment. J Acoust Soc Am. 2018, 143(5): 2922-2932

[34] Irfan M, Jiangbin Z, Ali S, Iqbal M, Masood Z, Hamid U. DeepShip: An underwater acoustic benchmark dataset and a separable convolution based autoencoder for classification. Expert Syst Appl. 2021, 183

[35] Jiang J, Shi T, Huang M, Xiao Z. Multi-scale spectral feature extraction for underwater acoustic target recognition. Measurement. 2020, 166

[36] Jiang J, Wu Z, Lu J, Huang M, Xiao Z. Interpretable features for underwater acoustic target recognition. Measurement. 2021, 173

[37] Jiang R, Wang X, Cao S, Zhao J, Li X. Deep neural networks for channel estimation in underwater acoustic OFDM systems. IEEE Access. 2019, 7: 23579-23594

[38] Jin G, Liu F, Wu H, Song Q. Deep learning-based framework for expansion, recognition and classification of underwater acoustic signal. J Exp Theor Artif Intell. 2020, 32(2): 205-218

[39] Jin SY, Su Y, Guo CJ, Fan YX, Tao ZY. Offshore ship recognition based on center frequency projection of improved EMD and KNN algorithm. Mech Syst Signal Process. 2023, 189

[40] Ke X, Yuan F, Cheng E. Integrated optimization of underwater acoustic ship-radiated noise recognition based on twodimensional feature fusion. Appl Acoust. 2020, 159

[41] Khishe M. Drw-ae: A deep recurrent-wavelet autoencoder for underwater target recognition. IEEE J Oceanic Eng. 2022, 47(4): 1083-1098

[42] Kim KI, Pak MI, Chon BP, Ri CH. A method for underwater acoustic signal classification using convolutional neural network combined with discrete wavelet transform. Int J Wavelets Multiresolut Inf Proc. 2021, 19(04): 2050092

[43] LeCun Y, Bengio Y, Hinton G. Deep learning. Nature. 2015, 521(7553): 436-444

[44] Lefort R, Real G, Dremeau A. Direct regression for underwater acoustic source localization in fluctuating oceans. Appl Acoust. 2017, 116: 303-310

[45] Li B, Zhou S, Stojanovic M, Freitag L, Willett P. Multicarrier communication over underwater acoustic channels with nonuniform Doppler shifts. IEEE J Oceanic Eng. 2008, 33(2): 198-209

[46] Li D, Liu F, Shen T, Chen L, Zhao D. Data augmentation method for underwater acoustic target recognition based on underwater acoustic channel modeling and transfer learning. Appl Acoust. 2023, 208

[47] Li L, Song S, Feng X. Combined LOFAR and DEMON spectrums for simultaneous underwater acoustic object counting and F0 estimation. Journal of Marine Science and Engineering. 2022, 10(10): 1565

[48] Li P, Wu J, Wang Y, Lan Q, Xiao W. STM: Spectrogram transformer model for underwater acoustic target recognition. Journal of Marine Science and Engineering. 2022, 10(10): 1428

[49] Li T, Sahu AK, Talwalkar A, Smith V. Federated learning: Challenges, methods, and future directions. IEEE Signal Proc Mag. 2020, 37(3): 50-60

[50] Li XL, Song WH, Gao DZ, Gao W, Wang HZ (2020b) Training a U-Net based on a random mode-coupling matrix model to recover acoustic interference striations. J Acoust Soc Am 147(4): EL363–EL369. https://doi.org/10.1121/10.0001125

[51] Li XL, Wang PY, Song WH, Gao W. Modal wavenumber estimation by combining physical informed neural network. J Acoust Soc Am. 2023, 153(5): 2637-2648

[52] Liu F, Shen T, Luo Z, Zhao D, Guo S. Underwater target recognition using convolutional recurrent neural networks with 3-D Mel-spectrogram and data augmentation. Appl Acoust. 2021, 178

[53] Liu L, Cai L, Ma L, Qiao G. Channel state information prediction for adaptive underwater acoustic downlink OFDMA system: deep neural networks based approach. IEEE Trans Veh Technol. 2021, 70(9): 9063-9076

[54] Liu MD, Niu HQ, Li ZL, Liu YN, Zhang QQ. Deep-learning geoacoustic inversion using multi-range vertical array data in shallow water. J Acoust Soc Am. 2022, 151(3): 2101-2116

[55] Liu W, Yang Y, Xu M, Lv L, Shi Y. Source localization in the deep ocean using a convolutional neural network. J Acoust Soc Am. 2020, 147(4): EL314-EL319

[56] Liu YN, Niu HQ, Li ZL. A multi-task learning convolutional neural network for source localization in deep ocean. J Acoust Soc Am. 2020, 148(2): 873-883

[57] Liu YN, Niu HQ, Li ZL, Wang MY (2021c) Deep-learning source localization using autocorrelation functions from a single hydrophone in deep ocean. JASA Express Lett 1(1):036002. https://doi.org/10.1121/10.0003647

[58] Liu YN, Niu HQ, Yang SS, Li ZL. Multiple source localization using learning-based sparse estimation in deep ocean. J Acoust Soc Am. 2021, 150(5): 3773-3786

[59] Lucas E, Wang ZH (2020) Supervised learning for performance prediction in underwater acoustic communications. Global Oceans 2020: Singapore–U.S. Gulf Coast, Biloxi, MS, USA, 05-30 October 2020, pp 1–6

[60] Luo X, Feng Y, Zhang M. An underwater acoustic target recognition method based on combined feature with automatic coding and reconstruction. IEEE Access. 2021, 9: 63841-63854

[61] Mary DR, Ko E, Kim SG, Yum SH, Shin SY, Park SH. A systematic review on recent trends, challenges, privacy and security issues of underwater internet of things. Sensors. 2021, 21(24): 8262

[62] McMahan B, Moore E, Ramage D, Hampson S, Arcas BA. Communication-efficient learning of deep networks from decentralized data. 2017, Ft. Lauderdale, FL, USA, In Artificial intelligence and statistics: 1273-1282

[63] Michalopoulou ZH, Alexandrou D, Moustier C. Application of neural and statistical classifiers to the problem of seafloor characterization. IEEE J Ocean Eng. 1995, 20(3): 190-197

[64] Mnih V, Kavukcuoglu K, Silver D, Rusu AA, Veness J, Bellemare MG, Graves A, Riedmiller M, Fidjeland AK, Ostrovski G, Petersen S. Human-level control through deep reinforcement learning. Nature. 2015, 518(7540): 529-533

[65] Neilsen TB, Escobar-Amado CD, Acree MC, Hodgkiss WS, Castro-Correa J. Learning location and seabed type from a moving midfrequency source. J Acoust Soc Am. 2021, 149(1): 692-705

[66] Niu HQ, Gerstoft P, Ozanich E, Li ZL, Zhang RH, Gong ZX, Wang HB. Block sparse Bayesian learning for broadband mode extraction in shallow water from a vertical array. J Acoust Soc Am. 2020, 147(6): 3729-3739

[67] Niu HQ, Gong ZX, Ozanich E, Gerstoft P, Wang HB, Li ZL. Deep-learning source localization using multi-frequency magnitude-only data. J Acoust Soc Am. 2019, 146(1): 211-222

[68] Niu HQ, Li ZL, Wang HB, Gong ZX (2019b) Overview of machine learning methods in underwater source localization. J Signal Proc 35(9):1450–1459. https://doi.org/10.16798/j.issn.1003-0530.2019.09.002

[69] Niu HQ, Ozanich E, Gerstoft P (2017a) Ship localization in Santa Barbara Channel using machine learning classifiers. J Acoust Soc Am 142(5): EL455–EL460. https://doi.org/10.1121/1.5010064

[70] Niu HQ, Reeves E, Gerstoft P. Source localization in an ocean waveguide using supervised machine learning. J Acoust Soc Am. 2017, 142(3): 1176-1188

[71] Ozard JM, Zakarauskas P, Ko P. An artificial neural network for range and depth discrimination in matched field processing. J Acoust Soc Am. 1991, 90: 2658-2663

[72] Piccolo J, Haramuniz G, Michalopoulou ZH. Geoacoustic inversion with generalized additive models. J Acoust Soc Am.. 2019, 145(6): EL463-EL468

[73] Qarabaqi P, Stojanovic M. Statistical characterization and computationally efficient modeling of a class of underwater acoustic communication channels. IEEE J Oceanic Eng. 2013, 38(4): 701-717

[74] Ren J, Xie Y, Zhang X, Xu J. UALF: A learnable front-end for intelligent underwater acoustic classification system. Ocean Eng. 2022, 264

[75] Santos-Domínguez D, Torres-Guijarro S, Cardenal-Lopez A, Pena-Gimenez A. ShipsEar: An underwater vessel noise database. Appl Acoust. 2016, 113: 64-69

[76] Shen Y, Pan X, Zheng Z, Gerstoft P. Matched-field geoacoustic inversion based on radial basis function neural network. J Acoust Soc Am. 2020, 148(5): 3279-3290

[77] Sozer EM, Stojanovic M, Proakis JG. Underwater acoustic networks. IEEE J Oceanic Eng. 2000, 25(1): 72-83

[78] Steinberg BZ, Beran MJ, Chin SH, Howard JH. A neural network approach to source localization. J Acoust Soc Am. 1991, 90: 2081-2090

[79] Stephan Y, Demoulin X, Sarzeaud O. Neural direct approaches for geoacoustic inversion. J Comput Acoust. 1998, 6(1): 151-166

[80] Komen D, Neilsen TB, Howarth K, Knobles DP, Dahl PH. Seabed and range estimation of impulsive time series using a convolutional neural network. J Acoust Soc Am. 2020, 147(5): EL403-EL408

[81] van Walree PA, Socheleau FX, Otnes R, Jenserud T. The watermark benchmark for underwater acoustic modulation schemes. IEEE J Oceanic Eng. 2017, 42(4): 1007-1018

[82] Wang H, Wang B, Li Y. IAFNet: Few-shot learning for modulation recognition in underwater impulsive noise. IEEE Commun Lett. 2022, 26(5): 1047-1051

[83] Wang M, Zhu Z, Qian G. Modulation Signal Recognition of Underwater Acoustic Communication Based on Archimedes Optimization Algorithm and Random Forest. Sensors. 2023, 23(5): 2764

[84] Wang R, Yadav A, Makled EA, Dobre OA, Zhao R, Varshney PK. Optimal power allocation for full-duplex underwater relay networks with energy harvesting: a reinforcement learning approach. IEEE Wireless Communications Letters. 2020, 9(2): 223-227

[85] Wang S, Zeng X. Robust underwater noise targets classification using auditory inspired time–frequency analysis. Appl Acoust. 2014, 78: 68-76

[86] Wang WB, Li SC, Yang JS, Liu Z, Zhou WC (2016) Feature extraction of underwater target in auditory sensation area based on MFCC. IEEE/OES China Ocean Acoustics (COA), Harbin, China, 09-11 January 2016, pp 1–6

[87] Wang WB, Ni HY, Su L, Hu T, Ren QY, Gerstoft P et al (2019a) Deep transfer learning for source ranging: deep-sea experiment results. J Acoust Soc Am 146(4): EL317–EL322. https://doi.org/10.1121/1.5126923

[88] Wang W, Wang Z, Su L, Hu T, Ren Q, Gerstoft P, Ma L. Source depth estimation using spectral transformations and convolutional neural network in a deep-sea environment. J Acoust Soc Am. 2020, 148(6): 3633-3644

[89] Wang X, Liu A, Zhang Y, Xue F. Underwater acoustic target recognition: a combination of multi-dimensional fusion features and modified deep neural network. Remote Sensing. 2019, 11(16): 1888

[90] Wang X, Meng J, Liu Y, Zhan G, Tian Z. Selfsupervised acoustic representation learning via acoustic-embedding memory unit modified space autoencoder for underwater target recognition. J Acoust Soc Am. 2022, 152(5): 2905-2915

[91] Wang Y, Peng H. Underwater acoustic source localization using generalized regression neural network. J Acoust Soc Am. 2018, 143(4): 2321-2331

[92] Weiss K, Khoshgoftaar TM, Wang D. A survey of transfer learning. Journal of Big Data. 2016, 3(1): 1-40

[93] Xiao L, Jiang D, Chen Y, Su W, Tang Y. Reinforcement-learning-based relay mobility and power allocation for underwater sensor networks against jamming. IEEE J Oceanic Eng. 2019, 45(3): 1148-1156

[94] Xie Y, Ren J, Xu J. Underwater-art: Expanding information perspectives with text templates for underwater acoustic target recognition. J Acoust Soc Am. 2022, 152(5): 2641-2651

[95] Xie Y, Ren J, Xu J. Adaptive ship-radiated noise recognition with learnable fine-grained wavelet transform. Ocean Eng. 2022, 265

[96] Xu J, Xie Y, Wang W. Underwater acoustic target recognition based on smoothness-inducing regularization and spectrogram-based data augmentation. Ocean Eng. 2023, 281

[97] Yang H, Lee K, Choo Y, Kim K. Underwater acoustic research trends with machine learning: Passive SONAR applications. Journal of Ocean Engineering and Technology. 2020, 34(3): 227-236

[98] Yang Z, Huo L, Wang J, Zhou J. Denoising low SNR percussion acoustic signal in the marine environment based on the LMS algorithm. Measurement. 2022, 202

[99] Yangzhou J, Ma Z, Huang X. A deep neural network approach to acoustic source localization in a shallow water tank experiment. J Acoust Soc Am. 2019, 146(6): 4802-4811

[100] Yu Q, Zhu M, Zhang W, Shi J, Liu Y. Surface and underwater acoustic source recognition using multi-channel joint detection method based on machine learning. J Mar Sci Eng. 2023, 11(8): 1587

[101] Zeng X, Wang S (2014) Underwater sound classification based on Gammatone filter bank and Hilbert-Huang transform. International Conference on Signal Processing, Communications and Computing (ICSPCC), Guilin, China, 05-08 August 2014, pp 707–710

[102] Zhang W, Wu Y, Shi J, Leng H, Zhao Y, Guo J. Surface and underwater acoustic source discrimination based on machine learning using a single hydrophone. J Mar Sci Eng. 2022, 10(3): 321

[103] Zhang W, Yang X, Leng C, Wang J, Mao S. Modulation recognition of underwater acoustic signals using deep hybrid neural networks. IEEE Trans Wireless Commun. 2022, 21(8): 5977-5988

[104] Zhang Y, Wang H, Li C, Meriaudeau F (2022c) Complex-valued deep network aided channel tracking for underwater acoustic communications. OCEANS Conference, Chennai, India, 21-24 February 2022, pp 1–5

[105] Zhang Y, Li C, Wang H, Wang J, Yang F, Meriaudeau F. Deep learning aided OFDM receiver for underwater acoustic communications. Appl Acoust. 2022, 187

[106] Zhang Y, Wang H, Li C, Chen D, Meriaudeau F. Meta-learning-aided orthogonal frequency division multiplexing for underwater acoustic communications. J Acoust Soc Am. 2021, 149(6): 4596-4606

[107] Zhang Y, Wang H, Li C, Chen X, Meriaudeau F. On the performance of deep neural network aided channel estimation for underwater acoustic OFDM communications. Ocean Eng. 2022, 259

[108] Zhang Y, Wang H, Li C, Meriaudeau F. Data augmentation aided complex-valued network for channel estimation in underwater acoustic orthogonal frequency division multiplexing system. J Acoust Soc Am. 2022, 151(6): 4150-4164

[109] Zhang YL, Wang HB, Tai YP, Li C, Meriaudeau F (2021b) A machine learning label-free method for underwater acoustic OFDM channel estimations. 15th International Conference on Underwater Networks Systems, Shenzhen, China, 23-26 November 2021, pp 1–5

[110] Zhang Y, Li J, Zakharov Y, Li X, Li J. Deep learning based underwater acoustic OFDM communications. Appl Acoust. 2019, 154: 53-58

[111] Zhang YZ, Chang JZ, Liu Y, Xing LY, Shen XH (2023) Deep learning and expert knowledge based underwater acoustic OFDM receiver. Phys Commun 58:102041

[112] Zhang Y, Zhu J, Wang H, Shen X, Wang B, Dong Y. Deep reinforcement learning-based adaptive modulation for underwater acoustic communication with outdated channel state information. Remote Sensing. 2022, 14(16): 3947

[113] Zhao H, Ji F, Li Q, Guan Q, Wang S, Wen M. Federated meta-learning enhanced acoustic radio cooperative framework for ocean of things. IEEE Journal of Selected Topics in Signal Processing. 2022, 16(3): 474-486

[114] Zhou X, Yang K. A denoising representation framework for underwater acoustic signal recognition. J Acoust Soc Am. 2020, 147(4): EL377-EL383

Funding

National Natural Science Foundation of China(12174418)

Youth Innovation Promotion Association of the Chinese Academy of Sciences(2019021)

CAS Specific Research Assistant Funding Program