EUVIMEDEUVIMED entdecken
Crossref

Estimation of the spatial variability of the New England Mud Patch geoacoustic properties using a distributed array of hydrophones and deep learning

Ariel Vardi iD, Peter H Dahl iD, David Dall'Osto, David Knobles, Preston Wilson iD, John Leonard, Julien Bonnel iD

The Journal of the Acoustical Society of America · 01.12.2024 · 156 (6) · 4229-4241

DOI: 10.1121/10.0034707 ↗

Kurz gefasst

Fachartikel in der Zeitschrift The Journal of the Acoustical Society of America, online erschienen am 24.12.2024. Verfasst von Ariel Vardi und 6 weiteren Autor:innen. Beteiligte Einrichtung: Department of Applied Ocean Physics and Engineering, Woods Hole Oceanographic Institution, Woods Hole, Massachusetts 02543, USA. Die Arbeit wurde bisher 7-mal zitiert (Crossref) und nennt 47 Literaturangaben. Gefördert von: U.S. Naval Research Laboratory.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

This article presents a spatial environmental inversion scheme using broadband impulse signals with deep learning (DL) to model a single spatially-varying sediment layer over a fixed basement. The method is applied to data from the Seabed Characterization Experiment 2022 (SBCEX22) in the New England Mud-Patch (NEMP). Signal Underwater Sound (SUS) explosive charges generated impulsive signals recorded by a distributed array of bottom-moored hydrophones. The inversion scheme is first validated on a range-dependent synthetic test set simulating SBCEX22 conditions, then applied to experimental data to predict the lateral spatial structure of sediment sound speed and its ratio with the interfacial water sound speed. Traditional geoacoustic inversion requires significant computational resources. Here, a neural network enables rapid single-signal inversion, allowing the processing of 1836 signals along 722 tracks. The method is applied to both synthetic and experimental data. Results from experimental data suggest an increase in both absolute compressional sound speed and sound speed ratio from southwest to northeast in the NEMP, consistent with published coring surveys and geoacoustic inversion results. This approach demonstrates the potential of DL for efficient spatial geoacoustic inversion in shallow water environments.

Autor:innen und Institutionen

  • Department of Applied Ocean Physics and Engineering, Woods Hole Oceanographic Institution, Woods Hole, Massachusetts 02543, USA.
  • Department of Mechanical Engineering, Massachusetts Institute of Technology, Cambridge, Massachusetts 02139, USA.
  • Applied Physics Laboratory, University of Washington, Seattle, Washington 98105, USA.
  • The Platt Institute, Austin, Texas 78755, USA.
  • Walker Department of Mechanical Engineering and Applied Research Laboratories, University of Texas at Austin, Austin, Texas 78712, USA.

ORCID-Profile: Ariel Vardi, Peter H Dahl, Preston Wilson, Julien Bonnel

Förderung

  • U.S. Naval Research Laboratory

Zitieren

APA

Vardi, A., Dahl, P. H., Dall'Osto, D., Knobles, D., Wilson, P., Leonard, J., & Bonnel, J. (2024). Estimation of the spatial variability of the New England Mud Patch geoacoustic properties using a distributed array of hydrophones and deep learning. The Journal of the Acoustical Society of America, 156(6), 4229-4241. https://doi.org/10.1121/10.0034707

Vancouver

Vardi A, Dahl PH, Dall'Osto D, Knobles D, Wilson P, Leonard J, et al. Estimation of the spatial variability of the New England Mud Patch geoacoustic properties using a distributed array of hydrophones and deep learning. The Journal of the Acoustical Society of America. 2024;156(6):4229-4241. doi:10.1121/10.0034707

BibTeX
@article{Vardi2024,
  author = {Vardi, Ariel and Dahl, Peter H and Dall'Osto, David and Knobles, David and Wilson, Preston and Leonard, John and Bonnel, Julien},
  title = {Estimation of the spatial variability of the New England Mud Patch geoacoustic properties using a distributed array of hydrophones and deep learning},
  journal = {The Journal of the Acoustical Society of America},
  year = {2024},
  volume = {156},
  number = {6},
  pages = {4229--4241},
  doi = {10.1121/10.0034707}
}
Kostenlos starten →