EUVIMEDEUVIMED entdecken
Crossref

Predicting ocean pressure field with a physics-informed neural network

Seunghyun Yoon, Yongsung Park iD, Peter Gerstoft iD, Woojae Seong iD

The Journal of the Acoustical Society of America · 01.03.2024 · 155 (3) · 2037-2049

DOI: 10.1121/10.0025235 ↗

Kurz gefasst

Fachartikel in der Zeitschrift The Journal of the Acoustical Society of America, online erschienen am 13.03.2024. Verfasst von Seunghyun Yoon und 3 weiteren Autor:innen. Beteiligte Einrichtung: Department of Naval Architecture and Ocean Engineering, Seoul National University, Seoul 08826, Republic of Korea. Die Arbeit wurde bisher 57-mal zitiert (Crossref) und nennt 60 Literaturangaben. Gefördert von: Korea Institute for Advancement of Technology, National Research Foundation of Korea, Office of Naval Research.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Ocean sound pressure field prediction, based on partially measured pressure magnitudes at different range-depths, is presented. Our proposed machine learning strategy employs a trained neural network with range-depth as input and outputs complex acoustic pressure at the location. We utilize a physics-informed neural network (PINN), fitting sampled data while considering the additional information provided by the partial differential equation (PDE) governing the ocean sound pressure field. In vast ocean environments with kilometer-scale ranges, pressure fields exhibit rapidly fluctuating phases, even at frequencies below 100 Hz, posing a challenge for neural networks to converge to accurate solutions. To address this, we utilize the envelope function from the parabolic-equation technique, fundamental in ocean sound propagation modeling. The envelope function shows slower variations across ranges, enabling PINNs to predict sound pressure in an ocean waveguide more effectively. Additional PDE information allows PINNs to capture PDE solutions even with a limited amount of training data, distinguishing them from purely data-driven machine learning approaches that require extensive datasets. Our approach is validated through simulations and using data from the SWellEx-96 experiment.

Autor:innen und Institutionen

  • Department of Naval Architecture and Ocean Engineering, Seoul National University, Seoul 08826, Republic of Korea.
  • Scripps Institution of Oceanography, University of California San Diego, La Jolla, California 92093-0238, USA.
  • Research Institute of Marine Systems Engineering, Seoul National University, Seoul 08826, Republic of Korea.

ORCID-Profile: Yongsung Park, Peter Gerstoft, Woojae Seong

Förderung

  • Korea Institute for Advancement of Technology
  • National Research Foundation of Korea
  • Office of Naval Research

Zitieren

APA

Yoon, S., Park, Y., Gerstoft, P., & Seong, W. (2024). Predicting ocean pressure field with a physics-informed neural network. The Journal of the Acoustical Society of America, 155(3), 2037-2049. https://doi.org/10.1121/10.0025235

Vancouver

Yoon S, Park Y, Gerstoft P, Seong W. Predicting ocean pressure field with a physics-informed neural network. The Journal of the Acoustical Society of America. 2024;155(3):2037-2049. doi:10.1121/10.0025235

BibTeX
@article{Yoon2024,
  author = {Yoon, Seunghyun and Park, Yongsung and Gerstoft, Peter and Seong, Woojae},
  title = {Predicting ocean pressure field with a physics-informed neural network},
  journal = {The Journal of the Acoustical Society of America},
  year = {2024},
  volume = {155},
  number = {3},
  pages = {2037--2049},
  doi = {10.1121/10.0025235}
}
Kostenlos starten →