EUVIMEDEUVIMED entdecken
Crossref

Learning data distribution of three-dimensional ocean sound speed fields via diffusion models

Siyuan Li, Lei Cheng iD, Jun Li, Zichen Wang, Jianlong Li iD

The Journal of the Acoustical Society of America · 01.05.2024 · 155 (5) · 3410-3425

DOI: 10.1121/10.0026026 ↗

Kurz gefasst

Fachartikel in der Zeitschrift The Journal of the Acoustical Society of America, online erschienen am 23.05.2024. Verfasst von Siyuan Li und 4 weiteren Autor:innen. Beteiligte Einrichtung: College of Information Science and Electronic Engineering, Zhejiang University, Hangzhou 310027, China. Die Arbeit wurde bisher 18-mal zitiert (Crossref) und nennt 45 Literaturangaben.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

The probability distribution of three-dimensional sound speed fields (3D SSFs) in an ocean region encapsulates vital information about their variations, serving as valuable data-driven priors for SSF inversion tasks. However, learning such a distribution is challenging due to the high dimensionality and complexity of 3D SSFs. To tackle this challenge, we propose employing the diffusion model, a cutting-edge deep generative model that has showcased remarkable performance in diverse domains, including image and audio processing. Nonetheless, applying this approach to 3D ocean SSFs encounters two primary hurdles. First, the lack of publicly available well-crafted 3D SSF datasets impedes training and evaluation. Second, 3D SSF data consist of multiple 2D layers with varying variances, which can lead to uneven denoising during the reverse process. To surmount these obstacles, we introduce a novel 3D SSF dataset called 3DSSF, specifically designed for training and evaluating deep generative models. In addition, we devise a high-capacity neural architecture for the diffusion model to effectively handle variations in 3D sound speeds. Furthermore, we employ state-of-the-art continuous-time-based optimization method and predictor-corrector scheme for high-performance training and sampling. Notably, this paper presents the first evaluation of the diffusion model's effectiveness in generating 3D SSF data. Numerical experiments validate the proposed method's strong ability to learn the underlying data distribution of 3D SSFs, and highlight its effectiveness in assisting SSF inversion tasks and subsequently characterizing the transmission loss of underwater acoustics.

Autor:innen und Institutionen

  • College of Information Science and Electronic Engineering, Zhejiang University, Hangzhou 310027, China.
  • China State Shipbuilding Corporation Systems Engineering Research Institute, Beijing 100094, China.
  • Hainan Institute, Zhejiang University, 572025, Sanya, China.

ORCID-Profile: Lei Cheng, Jianlong Li

Zitieren

APA

Li, S., Cheng, L., Li, J., Wang, Z., & Li, J. (2024). Learning data distribution of three-dimensional ocean sound speed fields via diffusion models. The Journal of the Acoustical Society of America, 155(5), 3410-3425. https://doi.org/10.1121/10.0026026

Vancouver

Li S, Cheng L, Li J, Wang Z, Li J. Learning data distribution of three-dimensional ocean sound speed fields via diffusion models. The Journal of the Acoustical Society of America. 2024;155(5):3410-3425. doi:10.1121/10.0026026

BibTeX
@article{Li2024,
  author = {Li, Siyuan and Cheng, Lei and Li, Jun and Wang, Zichen and Li, Jianlong},
  title = {Learning data distribution of three-dimensional ocean sound speed fields via diffusion models},
  journal = {The Journal of the Acoustical Society of America},
  year = {2024},
  volume = {155},
  number = {5},
  pages = {3410--3425},
  doi = {10.1121/10.0026026}
}
Kostenlos starten →