Finite-element modeling in ocean acoustics: Where are we heading?

Jensen, Finn B.; Zampolli, Mario; Simmen, Jeffrey; Livingston, Ellen S.; Zhou, Ji‐Xun; Li, Fenghua

doi:10.1063/1.3493052

Cited by 3 publications

(1 citation statement)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In the case of rough, layered sediments, numerical methods such as the finite element method (FEM) provide an attractive option. The FEM discretization of the governing acoustic wave equations in underwater domains enables accurate modeling of the seafloor environment [51,52,53,54,55,56,57,58]. Not limited by constraints on the degree of surface roughness or range dependence, FEM offers flexibility and can incorporate physics generated from realistic scenarios.…”

Section: Backscattermentioning

confidence: 99%

Seabed classification using physics-based modeling and machine learning

Frederick¹,

Villar²,

Michalopoulou³

2020

Preprint

View full text Add to dashboard Cite

In this work model-based methods are employed along with machine learning techniques to classify sediments in oceanic environments based on the geoacoustic properties of a twolayer seabed. Two different scenarios are investigated. First, a simple low-frequency case is set up, where the acoustic field is modeled with normal modes. Four different hypotheses are made for seafloor sediment possibilities and these are explored using both various machine learning techniques and a simple matched-field approach. For most noise levels, the latter has an inferior performance to the machine learning methods. Second, the high-frequency model of the scattering from a rough, two-layer seafloor is considered. Again, four different sediment possibilities are classified with machine learning. For higher accuracy, 1D Convolutional Neural Networks (CNNs) are employed. In both cases we see that the machine learning methods, both in simple and more complex formulations, lead to effective sediment characterization. Our results assess the robustness to noise and model misspecification of different classifiers.

show abstract

Section: Backscattermentioning

confidence: 99%

Seabed classification using physics-based modeling and machine learning

Frederick¹,

Villar²,

Michalopoulou³

2020

Preprint

View full text Add to dashboard Cite

show abstract

Weakly-Supervised Physics-Informed Neural Networks with Hard Constraints for Sound Propagation Problems in Complex Environments *

Xu,

Pan

2024

OCEANS 2024 - Singapore

View full text Add to dashboard Cite

Seabed classification using physics-based modeling and machine learning

Frederick

Villar

Michalopoulou

2020

The Journal of the Acoustical Society of America

View full text Add to dashboard Cite

In this work, model-based methods are employed, along with machine learning techniques, to classify sediments in oceanic environments based on the geoacoustic properties of a two-layer seabed. Two different scenarios are investigated. First, a simple low-frequency case is set up, in which the acoustic field is modeled with normal modes. Four different hypotheses are made for seafloor sediment possibilities, and these are explored using both various machine learning techniques and a simple matched-field approach. For most noise levels, the latter has an inferior performance to the machine learning methods. Second, the high-frequency model of the scattering from a rough, two-layer seafloor is considered. Again, four different sediment possibilities are classified with machine learning. For higher accuracy, one-dimensional convolutional neural networks are employed. In both cases, the machine learning methods, both in simple and more complex formulations, lead to effective sediment characterization. The results assess the robustness to noise and model misspecification of different classifiers.

show abstract

Finite-element modeling in ocean acoustics: Where are we heading?

Cited by 3 publications

References 15 publications

Seabed classification using physics-based modeling and machine learning

Seabed classification using physics-based modeling and machine learning

Weakly-Supervised Physics-Informed Neural Networks with Hard Constraints for Sound Propagation Problems in Complex Environments *

Seabed classification using physics-based modeling and machine learning

Contact Info

Product

Resources

About