High-SNR phase unwrap method based on RMN-LSTM for distributed hydro-acoustic detection
Applied Optics · 01.06.2026 · 65 (16) · 5351
DOI: 10.1364/ao.592687 ↗Kurz gefasst
Fachartikel in der Zeitschrift Applied Optics, online erschienen am 22.05.2026. Verfasst von Yage Zhan und 7 weiteren Autor:innen. Die Arbeit nennt 15 Literaturangaben. Gefördert von: Chinese Academy of Sciences, Science and Technology Commission of Shanghai Municipality, Shanghai Natural Science Foundation.
Abstract (Originalsprache)
Distributed acoustic sensing (DAS) exhibits great potential for underwater target detection. The line-spectrum component serves as a distinctive acoustic fingerprint for ship detection, and its accurate reconstruction relies on precise DAS phase demodulation. However, complex marine ambient noises severely deteriorate the signal-to-noise ratio (SNR) of the line-spectrum component, introducing additional phase jumps and even distortion during the unwrap process. To address these challenges, this work proposes a residual module nested long short-term memory (RMN-LSTM) neural network for high-SNR phase unwrap and line-spectrum target detection, combining the deep spatial feature extraction of residual module and long-range temporal dependency of the LSTM with symmetric left-right encoder-decoder network structure. The RMN-LSTM directly learns the mapping between distorted wrapped and true phase signals, enabling effective recovery of high-fidelity phase information. Experimental results demonstrate that this method accurately rebuilds line-spectrum signals and significantly outperforms conventional algorithms. The root mean square error (RMSE) of RMN-LSTM is reduced to 0.661, representing decreases of 95.5% and 96.3% against numerical optimization methods, 19.3% reduction against classical convolutional neural network (CNN)-based method, and 4.4% reduction against LSTM-based methods, achieving a comprehensive SNR improvement of about 27 dB. This work provides a robust technical approach for high-SNR underwater target detection without hardware upgrades.
Förderung
- Chinese Academy of Sciences
- Science and Technology Commission of Shanghai Municipality
- Shanghai Natural Science Foundation
Zitieren
APA
Zhan, Y., Deng, W., Wang, Z., Liu, Y., Xie, H., Ding, J., Lan, Y., & Ye, Q. (2026). High-SNR phase unwrap method based on RMN-LSTM for distributed hydro-acoustic detection. Applied Optics, 65(16), 5351. https://doi.org/10.1364/ao.592687
Vancouver
Zhan Y, Deng W, Wang Z, Liu Y, Xie H, Ding J, et al. High-SNR phase unwrap method based on RMN-LSTM for distributed hydro-acoustic detection. Applied Optics. 2026;65(16):5351. doi:10.1364/ao.592687
BibTeX
@article{Zhan2026,
author = {Zhan, Yage and Deng, Weigang and Wang, Zhaoyong and Liu, Yifan and Xie, Hongjiang and Ding, Jianpei and Lan, Yewei and Ye, Qing},
title = {High-SNR phase unwrap method based on RMN-LSTM for distributed hydro-acoustic detection},
journal = {Applied Optics},
year = {2026},
volume = {65},
number = {16},
pages = {5351},
doi = {10.1364/ao.592687}
}
EUVIMED