Dynamic multi-task neural network for end-to-end prediction of deep-sea acoustic transmission loss
The Journal of the Acoustical Society of America · 01.02.2026 · 159 (2) · 1555-1569
DOI: 10.1121/10.0042428 ↗Kurz gefasst
Fachartikel in der Zeitschrift The Journal of the Acoustical Society of America, online erschienen am 17.02.2026. Verfasst von Yongxian Wang und 2 weiteren Autor:innen. Beteiligte Einrichtung: College of Meteorology and Oceanography, National University of Defense Technology, Changsha 410073, China. Die Arbeit wurde bisher 7-mal zitiert (Crossref) und nennt 43 Literaturangaben. Gefördert von: Natural Science Foundation of Hu'nan Province, Innovation Research Foundation of National University of Defense Technology, National Natural Science Foundation of China.
Abstract (Originalsprache)
Accurate and efficient prediction of deep-sea acoustic transmission loss is essential for underwater applications, such as sonar design and underwater communication. In practical acoustic field computation tasks, it is often necessary to analyze the spatial distribution characteristics of the acoustic field in different regions. However, traditional numerical models require large-scale simulations on dense grids to predict acoustic fields over multiple spatial ranges, resulting in high computational cost. To address these limitations, this study proposes a dynamic multi-task U-Net (DMT-UNet) neural network model. Built on a multi-task learning framework, the model can dynamically adjust its network structure for end-to-end joint modeling of acoustic transmission loss at different computation ranges. Incorporating source information and deep-sea sound speed profiles as inputs enhances adaptability to model complex environments. DMT-UNet achieves an average root mean square error of approximately 1.6 dB on simulated deep-sea acoustic field datasets, with computational efficiency improved by more than 98.8% compared to traditional numerical models. Gradient-based visualization reveals how the model reconstructs acoustic field distributions during decoding, demonstrating interpretability. Experimental results show that DMT-UNet yields high prediction accuracy and computational efficiency, while maintaining consistency with physical laws and generalization capability. Thus, DMT-UNet enables real-time, multi-task acoustic modeling in complex deep-sea environments.
Autor:innen und Institutionen
- College of Meteorology and Oceanography, National University of Defense Technology, Changsha 410073, China.
ORCID-Profile: Yongxian Wang, Houwang Tu
Förderung
- Natural Science Foundation of Hu'nan Province
- Innovation Research Foundation of National University of Defense Technology
- National Natural Science Foundation of China
- Youth Independent Innovation Fund Project of the National University of Defense Technology
- Shaanxi Province Postdoctoral Science Foundation
Zitieren
APA
Wang, Y., Sun, Z., & Tu, H. (2026). Dynamic multi-task neural network for end-to-end prediction of deep-sea acoustic transmission loss. The Journal of the Acoustical Society of America, 159(2), 1555-1569. https://doi.org/10.1121/10.0042428
Vancouver
Wang Y, Sun Z, Tu H. Dynamic multi-task neural network for end-to-end prediction of deep-sea acoustic transmission loss. The Journal of the Acoustical Society of America. 2026;159(2):1555-1569. doi:10.1121/10.0042428
BibTeX
@article{Wang2026,
author = {Wang, Yongxian and Sun, Zhao and Tu, Houwang},
title = {Dynamic multi-task neural network for end-to-end prediction of deep-sea acoustic transmission loss},
journal = {The Journal of the Acoustical Society of America},
year = {2026},
volume = {159},
number = {2},
pages = {1555--1569},
doi = {10.1121/10.0042428}
}
EUVIMED