Noise measured in the vicinity of an F-22A Raptor has been compared to similarity spectra found previously to represent mixing noise from large-scale and fine-scale turbulent structures in laboratory-scale jet plumes. Comparisons have been made for three engine conditions using ground-based sideline microphones, which covered a large angular aperture. Even though the nozzle geometry is complex and the jet is nonideally expanded, the similarity spectra do agree with large portions of the measured spectra. Toward the sideline, the fine-scale similarity spectrum is used, while the large-scale similarity spectrum provides a good fit to the area of maximum radiation. Combinations of the two similarity spectra are shown to match the data in between those regions. Surprisingly, a combination of the two is also shown to match the data at the farthest aft angle. However, at high frequencies the degree of congruity between the similarity and the measured spectra changes with engine condition and angle. At the higher engine conditions, there is a systematically shallower measured high-frequency slope, with the largest discrepancy occurring in the regions of maximum radiation.

In ocean acoustics, many types of optimizations have been employed to locate acoustic sources and estimate the properties of the seabed. How these tasks can take advantage of recent advances in deep learning remains as open questions, especially due to the lack of labeled field data. In this work, a Convolutional Neural Network (CNN) is used to find seabed type and source range simultaneously from 1 s pressure time series from impulsive sounds. Simulated data are used to train the CNN before application to signals from a single hydrophone signal during the 2017 Seabed Characterization Experiment. The training data includes four seabeds representing deep mud, mud over sand, sandy silt, and sand, and a wide range of source parameters. When applied to measured data, the trained CNN predicts expected seabed types and obtains ranges within 0.5 km when the source-receiver range is greater than 5 km, showing the potential for such algorithms to address these problems.

Due to the difficulty and expense of underwater field trials, a high-fidelity underwater simulator is a necessity for testing and developing algorithms. To fill this need, we present HoloOcean, an open-source underwater simulator, built upon Unreal Engine 4 (UE4). HoloOcean comes equipped with multiagent support, various sensor implementations of common underwater sensors, and simulated communications support. Due to being built upon UE4, new environments are straightforward to add, enabling easy extensions to be built. HoloOcean is controlled via a simple Python interface, allowing simple installation via pip, and requiring few lines of code to execute simulations. Each agent is equipped with various control schemes and dynamics that can be customized via the Python interface. Also included is a novel sonar sensor framework that leverages an octree representation of the environment for efficient and realistic sonar imagery generation. In addition, to improve the authenticity of the imaging sonar simulation, we use a novel cluster-based multipath ray-tracing algorithm, various probabilistic noise models, and properties of reflecting surfaces. We also leverage the sonar simulation framework to simulate sidescan, single-beam, and multibeam profiling sonars.

While source localization and seabed classification are often approached separately, the convolutional neural networks (CNNs) in this paper simultaneously predict seabed type, source depth and speed, and the closest point of approach. Different CNN architectures are applied to mid-frequency tonal levels from a moving source recorded on a 16-channel vertical line array (VLA). After training each CNN on synthetic data, a statistical representation of predictions on test cases is presented. The performance of a single regression-based CNN is compared to a multitask CNN in which regression is used for the source parameters and classification for the seabed type. The impact of water sound speed profile and seabed variations on the predictions is evaluated using simulated test cases. Environmental mismatch between the training and testing data has a negative impact on source depth estimates, while the remaining labels are estimated tolerably well but with a bias towards shorter ranges. Similar results are found for data measured on two VLAs during Seabed Characterization Experiment 2017. This work shows the superiority of multitask learning and the potential for using a CNN to localize an acoustic source and detect the surficial seabed properties from mid-frequency sounds.

Broadband spectrograms from surface ships are employed in convolutional neural networks (CNNs) to predict the seabed type, ship speed, and closest point of approach (CPA) range. Three CNN architectures of differing size and depth are trained on different representations of the spectrograms. Multitask learning is employed; the seabed type prediction comes from classification, and the ship speed and CPA range are estimated via regression. Due to the lack of labeled field data, the CNNs are trained on synthetic data generated using measured sound speed profiles, four seabed types, and a random distribution of source parameters. Additional synthetic datasets are used to evaluate the ability of the trained CNNs to interpolate and extrapolate source parameters. The trained models are then applied to a measured data sample from the 2017 Seabed Characterization Experiment (SBCEX 2017). While the largest network provides slightly more accurate predictions on tests with synthetic data, the smallest network generalized better to the measured data sample. With regard to the input data type, complex pressure spectral values gave the most accurate and consistent results for the ship speed and CPA predictions with the smallest network, whereas using absolute values of the pressure provided more accurate results compared to the expected seabed types.

Merchant ship-radiated noise, recorded on a single receiver in the 360–1100 Hz frequency band over 20 min, is employed for seabed classification using an ensemble of deep learning (DL) algorithms. Five different convolutional neural network architectures and one residual neural network are trained on synthetic data generated using 34 seabed types, which span from soft-muddy to hard-sandy environments. The accuracy of all of the networks using fivefold cross-validation was above 97%. Furthermore, the impact of the sound speed and water depth mismatch on the predictions is evaluated using five simulated test cases, where the deeper and more complex architectures proved to be more robust against this variability. In addition, to assess the generalizability performance of the ensemble DL, the networks were tested on data measured on three vertical line arrays in the Seabed Characterization Experiment in 2017, where 94% of the predictions indicated that mud over sand environments inferred in previous geoacoustic inversions for the same area were the most likely sediments. This work presents evidence that the ensemble of DL algorithms has learned how the signature of the sediments is encoded in the ship-radiated noise, providing a unified classification result when tested on data collected at-sea.