Inversion in an uncertain ocean using Gaussian processes
Document Type
Article
Publication Date
3-1-2023
Abstract
Gaussian processes (GPs) can capture correlation of the acoustic field at different depths in the ocean. This feature is exploited in this work for pre-processing acoustic data before these are employed for source localization and environmental inversion using matched field inversion (MFI) in an underwater waveguide. Via the application of GPs, the data are denoised and interpolated, generating densely populated acoustic fields at virtual arrays, which are then used as data in MFI. Replicas are also computed at the virtual receivers at which field predictions are made. The correlations among field measurements at distinct spatial points are manifested through the selection of kernel functions. These rely on hyperparameters, that are estimated through a maximum likelihood process for optimal denoising and interpolation. The approach, employing Gaussian and Matérn kernels, is tested on synthetic and real data with both an exhaustive search and genetic algorithms and is found to be superior to conventional beamformer MFI. It is also shown that the Matérn kernel, providing more degrees of freedom because of an increased number of hyperparameters, is preferable over the frequently used Gaussian kernel.
Identifier
85149858710 (Scopus)
Publication Title
Journal of the Acoustical Society of America
External Full Text Location
https://doi.org/10.1121/10.0017437
e-ISSN
15208524
ISSN
00014966
PubMed ID
37002109
First Page
1600
Last Page
1611
Issue
3
Volume
153
Grant
N00014-18-1-2118
Fund Ref
Office of Naval Research
Recommended Citation
Michalopoulou, Zoi Heleni and Gerstoft, Peter, "Inversion in an uncertain ocean using Gaussian processes" (2023). Faculty Publications. 1856.
https://digitalcommons.njit.edu/fac_pubs/1856