Sensitivity analysis is a powerful tool for analyzing multi-parameter models. For example, the Fisher information matrix (FIM) and the Cramér–Rao bound (CRB) involve derivatives of a forward model with respect to parameters. However, these derivatives are difficult to estimate in ocean acoustic models. This work presents a frequency-agnostic methodology for accurately estimating numerical derivatives using physics-based parameter preconditioning and Richardson extrapolation. The methodology is validated on a case study of transmission loss in the 50–400[Formula: see text]Hz band from a range-independent normal mode model for parameters of the sediment. Results demonstrate the utility of this methodology for obtaining Cramér–Rao bound (CRB) related to both model sensitivities and parameter uncertainties, which reveal parameter correlation in the model. This methodology is a general tool that can inform model selection and experimental design for inverse problems in different applications.
Sound power is often measured using the intensity-based engineering standard ANSI S12.12-1992. Traditional methods for intensity-based sound power estimation are limited in bandwidth at low frequencies by phase mismatch between microphones and at high frequencies by microphone spacing—with errors occurring well below the spatial Nyquist frequency. The PAGE (Phase and Amplitude Gradient Estimation) method has been used to extend the bandwidth of intensity calculations [Gee et al., J. Acoust. Soc. Am. 141(4), EL357–EL362 (2017)]. This paper examines the efficacy of the PAGE method to overcome bandwidth limitations in estimating sound power. Specifically, the sound fields from three sources—a blender, a vacuum cleaner, and a dodecahedron speaker—were measured according to ANSI S12.12-1992. The sound power was computed for each source using both the traditional and PAGE methods. The resulting intensity-based sound power estimates are compared against sound power measurements obtained according to the scientific-grade ISO 3741:1999 standard. The PAGE method increases the bandwidth over which reliable estimates are achievable for intensity-based sound power estimates, even exceeding the spatial Nyquist frequency when phase unwrapping is successful. Thus, using existing equipment, industry professionals can extend the bandwidth of sound power estimates with the PAGE method. [Work supported by NSF.]
Deep learning can assist in characterizing seabeds using sources of opportunity such as shipping noise. While previous work focused on seabed classification, this study uses a residual convolutional neural network to find individual seabed properties. The training data were labeled with sound speed, density, attenuation, and thickness of the layer values of the top sediment layer. A comparison was made between predictive capabilities of ResNet-18 networks when trained to learn a single parameter and those trained to simultaneously learn multiple parameters. For stiff parameters—those with high information content in the data—learning an individual parameter performed better. These single parameter predictions are fundamentally different from a geoacoustic inversion for one parameter. In geoacoustic inversion, all other parameters are held at a fixed value. In deep learning, variability in all other parameters is contained in the training data, but the network focuses on features in the data related to a single property. The trained networks are applied to ship noise measured during the 2017 Seabed Characterization Experiment. [Work supported by the Office of Naval Research and the National Science Foundation’s REU program.]
The impact of individual seabed properties on sound propagation in the ocean depends on many factors including source-receiver range and frequency band of interest. In this talk, estimates of the sound speed ratio across the water-sediment interface are obtained using a maximum entropy approach and ResNet18, a supervised machine learning model. The input data are spectrograms of surface ship noise from shipping lanes. Synthetic spectrograms are modeled using a ship noise source spectrum and a range-independent normal mode model, ORCA, with a wide range of environments and ship parameters. Experimental data from the New England Mud Patch are used with both inverse methods. The maximum entropy approach uses data-model mismatch to obtain a posterior probability distribution for the parameters of interest. The ResNet18 is trained on the synthetic spectrograms, augmented with additive noise, and then applied to the experimental data. A comparison of the results from these two methods for a variety of ships using different frequency bands will be presented, along with a discussion of the advantages and limitations of each method.
Because the seabed impacts sound propagation in the ocean, machine learning is being used for both seabed classification and to obtain estimates of individual seabed properties. This paper proposes a method to simultaneously estimate these properties and an associated uncertainty label. A residual neural network is trained and validated using synthetic ship noise spectrograms generated with a range-independent normal mode sound propagation model and a ship noise source spectrum. The data set includes 140 seabeds: In each, the top sediment layer has a random thickness and properties randomly chosen from five sets of bounds, which roughly correspond to clay, mud, sand, silt, and gravel. For each of the 140 sediments, a random selection of 405 combinations of ship speed, closest-point-of-approach range, and source depth are used resulting in 22k data samples. Each data sample is labeled with the true values of the sediment parameters as well as a label for the uncertainty level of each. The uncertainty levels are obtained from the Fisher information and qualify of the information content in the ship spectrogram about each parameter. Examples of how the residual neural network learns to perform regression for the parameter value and the uncertainty level will be presented.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.