A convolutional neural network for source range and ocean seabed classification using pressure time-series

Neural networks learn features that are useful for classification directly from a source, such as a recorded signal, which removes the need for feature extraction or domain transformations necessary in other machine learning algorithms. To take advantage of these benefits and have a finer temporal resolution, a one-dimensional convolutional neural network is applied to pressure time-series to find source range and ocean environment class from a received signal. The neural network was trained on simulated signals generated in different environments (sandy, muddy, or mixed-layer sediment layers) for several ranges (0.5 to 15 km). We found significant potential in a neural network of this type, given a large amount of varied training samples for the network, to learn important features suitable for range and environment predictions. This type of network provides an alternative for frequency-domain learning and is potentially useful for impulsive sources. Success in the time domain also reduces the computational requirements of conversion to frequency domain and increases the temporal resolution, which might be beneficial for real-time applications.

[1]  Angélique Drémeau,et al.  Direct regressions for underwater acoustic source localization in fluctuating oceans , 2017 .

[2]  L. A. Thompson,et al.  Broadband sound propagation in shallow water and geoacoustic inversion. , 2000, The Journal of the Acoustical Society of America.

[3]  J. Goff,et al.  Maximum Entropy Derived Statistics of Sound-Speed Structure in a Fine-Grained Sediment Inferred From Sparse Broadband Acoustic Measurements on the New England Continental Shelf , 2020, IEEE Journal of Oceanic Engineering.

[4]  Jimmy Ba,et al.  Adam: A Method for Stochastic Optimization , 2014, ICLR.

[5]  Peter Gerstoft,et al.  Ship localization in Santa Barbara Channel using machine learning classifiers. , 2017, The Journal of the Acoustical Society of America.

[6]  Thomas Brox,et al.  U-Net: Convolutional Networks for Biomedical Image Segmentation , 2015, MICCAI.

[7]  Climent Nadeu,et al.  A novel approach to real-time range estimation of underwater acoustic sources using supervised machine learning , 2017, OCEANS 2017 - Aberdeen.

[8]  Henrik Schmidt,et al.  Classification of underwater targets from autonomous underwater vehicle sampled bistatic acoustic scattered fields. , 2015, The Journal of the Acoustical Society of America.

[9]  Peter Gerstoft,et al.  Source localization in an ocean waveguide using supervised machine learning , 2017, The Journal of the Acoustical Society of America.

[10]  Zoi-Heleni Michalopoulou,et al.  Geoacoustic inversion with generalized additive models. , 2019, The Journal of the Acoustical Society of America.

[11]  Sergey Ioffe,et al.  Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift , 2015, ICML.

[12]  Tracianne B. Neilsen,et al.  A feedforward neural network for source range and ocean seabed classification using time-domain features , 2019 .

[13]  Geoffrey E. Hinton,et al.  Rectified Linear Units Improve Restricted Boltzmann Machines , 2010, ICML.

[14]  Yonghong Yan,et al.  Source localization using deep neural networks in a shallow water environment. , 2018, The Journal of the Acoustical Society of America.

[15]  James H. Miller,et al.  Inversion for sediment geoacoustic properties at the New England Bight. , 2003, The Journal of the Acoustical Society of America.

[16]  Mark J. Beran,et al.  A neural network approach to source localization , 1991 .

[17]  Xue-Zhen Zhang,et al.  Low-frequency geoacoustic model for the effective properties of sandy seabottoms. , 2009, The Journal of the Acoustical Society of America.

[18]  N. R. Chapman,et al.  Source levels of shallow explosive charges , 1988 .

[19]  Evan K. Westwood,et al.  A normal mode model for acousto‐elastic ocean environments , 1996 .

[20]  Terence D. Sanger,et al.  Optimal unsupervised learning in a single-layer linear feedforward neural network , 1989, Neural Networks.

[21]  Jürgen Schmidhuber,et al.  Long Short-Term Memory , 1997, Neural Computation.

[22]  Luca Antiga,et al.  Automatic differentiation in PyTorch , 2017 .

[23]  Hua Peng,et al.  Underwater acoustic source localization using generalized regression neural network. , 2018, The Journal of the Acoustical Society of America.