Sub-bottom profilers are utilized to extract features pertaining to the sub seafloor environment sediment stratification. Acquisition and analysis of sub-bottom profiles can provide insight into the sediment composition and acoustical properties. Typical analysis of profiles involves computationally expensive inversions such as model-based or Bayesian techniques which require large computational costs. Here, a neural network is developed to perform a geoacoustic inversion on simulated sub-bottom profiler data. The network is used to derive attenuation and acoustical impedance measurements corresponding to the layered media. Geoacoustic properties of the layered sediments are compared to values determined through a direct inversion of reflection coefficient, testing how well these techniques recover the ground truth values. The network, trained on simulated data, is applied to real sub bottom profiler data acquired over a well-studied area called the New England Mud Patch, roughly 80 km south of Nantucket. The simulated data-trained network is compared to a network trained on experimental data acquired by the R/V Tioga over the same region.
Skip Nav Destination
,
,
Article navigation
18 November 2024
187th Meeting of the Acoustical Society of America
18–22 November 2024
Virtual Meeting 2024
Acoustical Oceanography: Paper 1aAO1
March 28 2025
Neural network for geoacoustic inversion of sub-bottom profiler data Free
Justin Diamond;
Justin Diamond
1
Department of Mechanical Engineering, University of Washington Applied Physics Laboratory
, Seattle, WA, 98195, USA
; [email protected]
Search for other works by this author on:
David Dall'Osto;
David Dall'Osto
2
Department of Mechanical Engineering, University of Washington Applied Physics Laboratory
, Seattle, WA, 98195, USA
; [email protected]
Search for other works by this author on:
John Mower
John Mower
3
Department of Mechanical Engineering, University of Washington Applied Physics Laboratory
, Seattle, WA, 98195, USA
; [email protected]
Search for other works by this author on:
Justin Diamond
1
David Dall'Osto
2
John Mower
3
1
Department of Mechanical Engineering, University of Washington Applied Physics Laboratory
, Seattle, WA, 98195, USA
; [email protected]
2
Department of Mechanical Engineering, University of Washington Applied Physics Laboratory
, Seattle, WA, 98195, USA
; [email protected]
3
Department of Mechanical Engineering, University of Washington Applied Physics Laboratory
, Seattle, WA, 98195, USA
; [email protected]Proc. Mtgs. Acoust. 55, 005001 (2024)
Article history
Received:
December 20 2024
Accepted:
March 18 2025
Citation
Justin Diamond, David Dall'Osto, John Mower; Neural network for geoacoustic inversion of sub-bottom profiler data. Proc. Mtgs. Acoust. 18 November 2024; 55 (1): 005001. https://doi.org/10.1121/2.0002019
Download citation file:
111
Views
Citing articles via
Enhancing emotional well-being through active music listening: A study on mood improvement effects of music rhythm games
Hoi Ting Leung, Man Hei Law, et al.
Related Content
Arrays and signal processing during the “Nantucket Sound Experiment”: A review of work in honor of William M. Carey
J. Acoust. Soc. Am. (April 2014)
Perturbative inversion methods for obtaining bottom geoacoustic parameters in shallow water
J. Acoust. Soc. Am. (September 1987)
Autumn acoustic behavior of right whales in Southern New England waters
J. Acoust. Soc. Am. (April 2022)
Passive acoustic monitoring of biological and anthropogenic sounds at America’s first offshore wind farm
J. Acoust. Soc. Am. (November 2013)
Geoacoustic inversion on the New England Mud Patch using warping and dispersion curves of high-order modes
J. Acoust. Soc. Am. (May 2018)