Passive ocean acoustic thermometry with machine learning

Abstract Passive ocean acoustic thermometry (POAT) needs long accumulation time to achieve high accuracy. This article provides a machine learning-based method, Random Forest, to obtain the averaged sound speed (AVSS). With supervised learning, the AVSS can be estimated from half an hour accumulated noise cross-correlation functions (NCFs). Based on the feature importance analysis, an empirical equation is proposed to briefly describe the relationships between the features. The results of estimations are compared among different methods to demonstrate the advantage of the machine learning-based approach.

[1]  Paul Hursky,et al.  Adaptive passive fathometer processing. , 2010, The Journal of the Acoustical Society of America.

[2]  W. Kuperman,et al.  Measuring the effect of ambient noise directionality and split-beam processing on the convergence of the cross-correlation function. , 2013, The Journal of the Acoustical Society of America.

[3]  W.A. Kuperman,et al.  Using ocean ambient noise for array self-localization and self-synchronization , 2005, IEEE Journal of Oceanic Engineering.

[4]  Leo Breiman,et al.  Bagging Predictors , 1996, Machine Learning.

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

[6]  Sharon Gannot,et al.  Machine learning in acoustics: Theory and applications. , 2019, The Journal of the Acoustical Society of America.

[7]  E. C. Shang,et al.  Ocean acoustic tomography based on adiabatic mode theory , 1989 .

[8]  M. Brown,et al.  Tomographic inversion of measured cross-correlation functions of ocean noise in shallow water using ray theory , 2016 .

[9]  M. Brown,et al.  Waveform modeling and inversion of ambient noise cross-correlation functions in a coastal ocean environment. , 2015, The Journal of the Acoustical Society of America.

[10]  Andy Liaw,et al.  Classification and Regression by randomForest , 2007 .

[11]  W. Kuperman,et al.  Extracting coherent wave fronts from acoustic ambient noise in the ocean , 2004 .

[12]  Leo Breiman,et al.  Random Forests , 2001, Machine Learning.

[13]  Gaël Varoquaux,et al.  Scikit-learn: Machine Learning in Python , 2011, J. Mach. Learn. Res..

[14]  T. Birdsall,et al.  A demonstration of ocean acoustic tomography , 1982, Nature.

[15]  Michael B. Porter,et al.  Computational Ocean Acoustics , 1994 .

[16]  C. Wapenaar,et al.  Deep ocean sound speed characteristics passively derived from the ambient acoustic noise field , 2017 .

[17]  Oleg A Godin.  Recovering the acoustic Green's function from ambient noise cross correlation in an inhomogeneous moving medium. , 2006, Physical review letters.

[18]  W. Kuperman,et al.  Emergence rate of the time-domain Green's function from the ambient noise cross-correlation function , 2005 .

[19]  O. Godin,et al.  Ocean tomography with acoustic daylight , 2010 .

[20]  G. M. Wenz.  Acoustic Ambient Noise in the Ocean: Spectra and Sources , 1962 .

[21]  Gérard Biau,et al.  Analysis of a Random Forests Model , 2010, J. Mach. Learn. Res..

[22]  Carl Wunsch,et al.  Ocean acoustic tomography: a scheme for large scale monitoring , 1979 .

[23]  B. Cornuelle,et al.  Ocean acoustic tomography , 1988, Signal Recovery and Synthesis.

[24]  Philippe Roux,et al.  Enhancing the emergence rate of coherent wavefronts from ocean ambient noise correlations using spatio-temporal filters. , 2012, The Journal of the Acoustical Society of America.

[25]  Karim G. Sabra,et al.  Monitoring deep‐ocean temperatures using acoustic ambient noise , 2015 .

[26]  Philippe Roux,et al.  Coherent processing of shipping noise for ocean monitoring. , 2013, The Journal of the Acoustical Society of America.

[27]  M. Porter,et al.  A passive fathometer technique for imaging seabed layering using ambient noise , 2006 .

[28]  Philippe Roux,et al.  Arrival-time structure of the time-averaged ambient noise cross-correlation function in an oceanic waveguide. , 2005, The Journal of the Acoustical Society of America.