A Hybrid–Source Ranging Method in Shallow Water Using Modal Dispersion Based on Deep Learning

The relationship between modal elevation angle and the relative arrival time between modes, derived from exploiting modal dispersion, provides source information that is less susceptible to environmental influences. However, the standard method based on modal dispersion has limitations for applicati...

Full description

Saved in:
Bibliographic Details
Published inJournal of marine science and engineering Vol. 11; no. 3; p. 561
Main Authors Wang, Tong, Su, Lin, Ren, Qunyan, Li, He, Jia, Yuqing, Ma, Li
Format Journal Article
LanguageEnglish
Published Basel MDPI AG 01.03.2023
Subjects
Acoustics
Analysis
Beamforming
Deep learning
Dispersion
Elevation angle
Error reduction
Localization
Machine learning
Methods
modal dispersion
Optimization techniques
Propagation
Regression models
Shallow water
Signal processing
Simulation
Sound
source ranging
Time domain analysis
Underwater
Underwater acoustics
Waveguides
Online AccessGet full text

Cover

More Information
Summary:The relationship between modal elevation angle and the relative arrival time between modes, derived from exploiting modal dispersion, provides source information that is less susceptible to environmental influences. However, the standard method based on modal dispersion has limitations for application. To overcome this, we propose a hybrid method for passive source ranging of low-frequency underwater acoustic-pulse signals in a range-independent shallow-water waveguide. Our method leverages deep learning, utilizing the intermediate results from the standard method as inputs, and short-time conventional beamforming to transform signals received by a vertical line array into a beam-time-domain sound-intensity map. The source range is estimated using an attention-based regression model with a ResNet backbone that has been trained on the beam-time-domain sound-intensity map. Our experimental results demonstrate the superiority of the proposed method, with a mean relative-error reduction of 71%, mean root-squared error reduction of 2.25 km, and an accuracy of 85%, compared to matched-field processing.
ISSN:2077-1312
2077-1312
DOI:10.3390/jmse11030561