A multi-task neural network for source localization in shallow-water environment with depth classification
JASA Express Letters · 01.07.2026 · 6 (7)
DOI: 10.1121/10.0044372 ↗Kurz gefasst
Fachartikel in der Zeitschrift JASA Express Letters, online erschienen am 15.07.2026. Verfasst von Jing Guo und 1 weiteren Autor:innen. Beteiligte Einrichtung: Key Laboratory of Underwater Acoustic Environment, Institute of Acoustics, Chinese Academy of Sciences, Beijing 100190, China. Die Arbeit nennt 24 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC 4.0).
Abstract (Originalsprache)
Limited high-quality training data can cause overfitting and weak generalization in deep-learning-based source localization, leading to degraded performance in realistic environments. In this study, a multi-task neural network with a depth-classification branch is developed, motivated by the depth resolution of a vertical line array and the depth-dependent structure of the localization ambiguity surface. The depth-classification branch regularizes depth estimation and reduces model complexity, thereby mitigating overfitting in the range-regression branch. Transfer learning from simulations to experiments further improves performance with limited measurements. The developed network yields improved localization performance, as demonstrated using both simulated and experimental data.
Autor:innen und Institutionen
- Key Laboratory of Underwater Acoustic Environment, Institute of Acoustics, Chinese Academy of Sciences, Beijing 100190, China.
- University of Chinese Academy of Sciences, Beijing 100049, China.
ORCID-Profile: Jing Guo
Zitieren
APA
Guo, J., & Zeng, J. (2026). A multi-task neural network for source localization in shallow-water environment with depth classification. JASA Express Letters, 6(7). https://doi.org/10.1121/10.0044372
Vancouver
Guo J, Zeng J. A multi-task neural network for source localization in shallow-water environment with depth classification. JASA Express Letters. 2026;6(7). doi:10.1121/10.0044372
BibTeX
@article{Guo2026,
author = {Guo, Jing and Zeng, Juan},
title = {A multi-task neural network for source localization in shallow-water environment with depth classification},
journal = {JASA Express Letters},
year = {2026},
volume = {6},
number = {7},
doi = {10.1121/10.0044372}
}
EUVIMED