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

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.

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

References in corpus (4)

• Deep Learning in Neural Networks: An Overview
• TensorFlow: Large-Scale Machine Learning on Heterogeneous Distributed Systems
• Natural Language Processing (almost) from Scratch
• Source localization in an ocean waveguide using supervised machine learning

Cited by in corpus (6)

• Machine learning in acoustics: theory and applications
• Deep embedded clustering of coral reef bioacoustics
• Training a U-Net based on a random mode-coupling matrix model to recover acoustic interference striations
• Complex data labeling with deep learning methods: Lessons from fisheries acoustics
• Towards Robust Data-Driven Underwater Acoustic Localization: A Deep CNN Solution with Performance Guarantees for Model Mismatch
• Feature Selection based on Principal Component Analysis for Underwater Source Localization by Deep Learning