English

Deep-learning source localization using multi-frequency magnitude-only data

Atmospheric and Oceanic Physics 2019-07-19 v2 Signal Processing

Abstract

A deep learning approach based on big data is proposed to locate broadband acoustic sources using a single hydrophone in ocean waveguides with uncertain bottom parameters. Several 50-layer residual neural networks, trained on a huge number of sound field replicas generated by an acoustic propagation model, are used to handle the bottom uncertainty in source localization. A two-step training strategy is presented to improve the training of the deep models. First, the range is discretized in a coarse (5 km) grid. Subsequently, the source range within the selected interval and source depth are discretized on a finer (0.1 km and 2 m) grid. The deep learning methods were demonstrated for simulated magnitude-only multi-frequency data in uncertain environments. Experimental data from the China Yellow Sea also validated the approach.

Keywords

Cite

@article{arxiv.1903.12319,
  title  = {Deep-learning source localization using multi-frequency magnitude-only data},
  author = {Haiqiang Niu and Zaixiao Gong and Emma Ozanich and Peter Gerstoft and Haibin Wang and Zhenglin Li},
  journal= {arXiv preprint arXiv:1903.12319},
  year   = {2019}
}

Comments

It has been published on the Journal of the Acoustical Society of America

R2 v1 2026-06-23T08:22:49.598Z