Study of acoustic propagation across an oceanic front at the edge of the New England shelf.

Propagation of low-frequency sound across a warm core ring-enhanced oceanic front at lower horizontal grazing angles is presented. The data were collected from an experimental source tow conducted during the New England Shelf Break Acoustics (NESBA) experiments in spring 2021. The 3 h tow track provides spatiotemporal measurements of acoustic propagation through the front across varying geometries. Coincident oceanographic measurements are used to estimate the strong temperature gradient of the water column and three-dimensional (3D) sound speed field. Two-dimensional (2D) adiabatic mode and full-field sound propagation models are utilized to investigate the acoustic sensitivity to the frontal structure. Then, the joint effects of acoustic ducting and bathymetric slope refraction are examined using 3D sound propagation models. Key components of the measured acoustic impulse response are captured in the 3D numerical model, and the sensitivity of low-frequency propagation to the front geometry is demonstrated.

Real-time joint ocean acoustics and circulation modeling in the 2021 New England Shelf Break Acoustics experiment (L).

During the spring of 2021, a coordinated multi-vessel effort was organized to study physical oceanography, marine geology and biology, and acoustics on the northeast United States continental shelf, as part of the New England Shelf Break Acoustics (NESBA) experiment. One scientific goal was to establish a real-time numerical model aboard the research vessel with high spatial and temporal resolution to predict the oceanography and sound propagation within the NESBA study area. The real-time forecast model performance and challenges are reported in this letter without adjustment or re-simulation after the cruise. Future research directions for post-experiment studies are also suggested.

Deep embedded clustering of coral reef bioacoustics.

Deep clustering was applied to unlabeled, automatically detected signals in a coral reef soundscape to distinguish fish pulse calls from segments of whale song. Deep embedded clustering (DEC) learned latent features and formed classification clusters using fixed-length power spectrograms of the signals. Handpicked spectral and temporal features were also extracted and clustered with Gaussian mixture models (GMM) and conventional clustering. DEC, GMM, and conventional clustering were tested on simulated datasets of fish pulse calls (fish) and whale song units (whale) with randomized bandwidth, duration, and SNR. Both GMM and DEC achieved high accuracy and identified clusters with fish, whale, and overlapping fish and whale signals. Conventional clustering methods had low accuracy in scenarios with unequal-sized clusters or overlapping signals. Fish and whale signals recorded near Hawaii in February-March 2020 were clustered with DEC, GMM, and conventional clustering. DEC features demonstrated the highest accuracy of 77.5% on a small, manually labeled dataset for classifying signals into fish and whale clusters.

Automated two-dimensional localization of underwater acoustic transient impulses using vector sensor image processing (vector sensor localization).

Detecting acoustic transients by signal-to-noise ratio (SNR) becomes problematic in nonstationary ambient noise environments characteristic of coral reefs. An alternate approach presented here uses signal directionality to automatically detect and localize transient impulsive sounds collected on underwater vector sensors spaced tens of meters apart. The procedure, which does not require precise time synchronization, first constructs time-frequency representations of both the squared acoustic pressure (spectrogram) and dominant directionality of the active intensity (azigram) on each sensor. Within each azigram, sets of time-frequency cells associated with transient energy arriving from a consistent azimuthal sector are identified. Binary image processing techniques then link sets that share similar duration and bandwidth between different sensors, after which the algorithm triangulates the source location. Unlike most passive acoustic detectors, the threshold criterion for this algorithm is bandwidth instead of pressure magnitude. Data collected from shallow coral reef environments demonstrate the algorithm's ability to detect SCUBA bubble plumes and consistent spatial distributions of somniferous fish activity. Analytical estimates and direct evaluations both yield false transient localization rates from 3% to 6% in a coral reef environment. The SNR distribution of localized pulses off Hawaii has a median of 7.7 dB and interquartile range of 7.1 dB.

Block sparse Bayesian learning for broadband mode extraction in shallow water from a vertical array.

The horizontal wavenumbers and modal depth functions are estimated by block sparse Bayesian learning (BSBL) for broadband signals received by a vertical line array in shallow-water waveguides. The dictionary matrix consists of multi-frequency modal depth functions derived from shooting methods given a large set of hypothetical horizontal wavenumbers. The dispersion relation for multi-frequency horizontal wavenumbers is also taken into account to generate the dictionary. In this dictionary, only a few of the entries are used to describe the pressure field. These entries represent the modal depth functions and associated wavenumbers. With the constraint of block sparsity, the BSBL approach is shown to retrieve the horizontal wavenumbers and corresponding modal depth functions with high precision, while a priori knowledge of sea bottom, moving source, and source locations is not needed. The performance is demonstrated by simulations and experimental data.

A feedforward neural network for direction-of-arrival estimation.

This paper examines the relationship between conventional beamforming and linear supervised learning, then develops a nonlinear deep feed-forward neural network (FNN) for direction-of-arrival (DOA) estimation. First, conventional beamforming is reformulated as a real-valued, linear inverse problem in the weight space, which is compared to a support vector machine and a linear FNN model. In the linear formulation, DOA is quickly and accurately estimated for a realistic array calibration example. Then, a nonlinear FNN is developed for two-source DOA and for K-source DOA, where K is unknown. Two training methodologies are used: exhaustive training for controlled accuracy and random training for flexibility. The number of FNN model hidden layers, hidden nodes, and activation functions are selected using a hyperparameter search. In plane wave simulations, the 2-source FNN resolved incoherent sources with 1° resolution using a single snapshot, similar to Sparse Bayesian Learning (SBL). With multiple snapshots, K-source FNN achieved resolution and accuracy similar to Multiple Signal Classification and SBL for an unknown number of sources. The practicality of the deep FNN model is demonstrated on Swellex96 experimental data for multiple source DOA on a horizontal acoustic array.

Machine learning in acoustics: Theory and applications.

Acoustic data provide scientific and engineering insights in fields ranging from biology and communications to ocean and Earth science. We survey the recent advances and transformative potential of machine learning (ML), including deep learning, in the field of acoustics. ML is a broad family of techniques, which are often based in statistics, for automatically detecting and utilizing patterns in data. Relative to conventional acoustics and signal processing, ML is data-driven. Given sufficient training data, ML can discover complex relationships between features and desired labels or actions, or between features themselves. With large volumes of training data, ML can discover models describing complex acoustic phenomena such as human speech and reverberation. ML in acoustics is rapidly developing with compelling results and significant future promise. We first introduce ML, then highlight ML developments in four acoustics research areas: source localization in speech processing, source localization in ocean acoustics, bioacoustics, and environmental sounds in everyday scenes.

Deep-learning source localization using multi-frequency magnitude-only data.

A deep learning approach based on big data is proposed to locate broadband acoustic sources using a single hydrophone in ocean waveguides with uncertain bottom parameters. Several 50-layer residual neural networks, trained on a huge number of sound field replicas generated by an acoustic propagation model, are used to handle the bottom uncertainty in source localization. A two-step training strategy is presented to improve the training of the deep models. First, the range is discretized in a coarse (5 km) grid. Subsequently, the source range within the selected interval and source depth are discretized on a finer (0.1 km and 2 m) grid. The deep learning methods were demonstrated for simulated magnitude-only multi-frequency data in uncertain environments. Experimental data from the China Yellow Sea also validated the approach.

Ship localization in Santa Barbara Channel using machine learning classifiers.

Machine learning classifiers are shown to outperform conventional matched field processing for a deep water (600 m depth) ocean acoustic-based ship range estimation problem in the Santa Barbara Channel Experiment when limited environmental information is known. Recordings of three different ships of opportunity on a vertical array were used as training and test data for the feed-forward neural network and support vector machine classifiers, demonstrating the feasibility of machine learning methods to locate unseen sources. The classifiers perform well up to 10 km range whereas the conventional matched field processing fails at about 4 km range without accurate environmental information.

Eastern Arctic ambient noise on a drifting vertical array.

Ambient noise in the eastern Arctic was studied from April to September 2013 using a 22 element vertical hydrophone array as it drifted from near the North Pole (89° 23'N, 62° 35'W) to north of Fram Strait (83° 45'N, 4° 28'W). The hydrophones recorded for 108 min/day on six days per week with a sampling rate of 1953.125 Hz. After removal of data corrupted by non-acoustic transients, 19 days throughout the transit period were analyzed. Noise contributors identified include broadband and tonal ice noises, bowhead whale calling, seismic airgun surveys, and earthquake T phases. The bowhead whale or whales detected are believed to belong to the endangered Spitsbergen population, and were recorded when the array was as far north as 86° 24'N. Median power spectral estimates and empirical probability density functions along the array transit show a change in the ambient noise levels corresponding to seismic survey airgun occurrence and received level at low frequencies and transient ice noises at high frequencies. Median power for the same periods across the array shows that this change is consistent in depth. The median ambient noise for May 2013 was among the lowest of the sparse reported observations in the eastern Arctic but comparable to the more numerous observations of western Arctic noise levels.