Mismatch-Robust Underwater Acoustic Localization Using A Differentiable Modular Forward Model

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Kari, Dariush, Zhuang, Yongjie, Singer, Andrew C.
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913766366511104
author Kari, Dariush
Zhuang, Yongjie
Singer, Andrew C.
author_facet Kari, Dariush
Zhuang, Yongjie
Singer, Andrew C.
contents In this paper, we study the underwater acoustic localization in the presence of environmental mismatch. Especially, we exploit a pre-trained neural network for the acoustic wave propagation in a gradient-based optimization framework to estimate the source location. To alleviate the effect of mismatch between the training data and the test data, we simultaneously optimize over the network weights at the inference time, and provide conditions under which this method is effective. Moreover, we introduce a physics-inspired modularity in the forward model that enables us to learn the path lengths of the multipath structure in an end-to-end training manner without access to the specific path labels. We investigate the validity of the assumptions in a simple yet illustrative environment model.
format Preprint
id arxiv_https___arxiv_org_abs_2503_23260
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Mismatch-Robust Underwater Acoustic Localization Using A Differentiable Modular Forward Model
Kari, Dariush
Zhuang, Yongjie
Singer, Andrew C.
Sound
Machine Learning
Audio and Speech Processing
Signal Processing
In this paper, we study the underwater acoustic localization in the presence of environmental mismatch. Especially, we exploit a pre-trained neural network for the acoustic wave propagation in a gradient-based optimization framework to estimate the source location. To alleviate the effect of mismatch between the training data and the test data, we simultaneously optimize over the network weights at the inference time, and provide conditions under which this method is effective. Moreover, we introduce a physics-inspired modularity in the forward model that enables us to learn the path lengths of the multipath structure in an end-to-end training manner without access to the specific path labels. We investigate the validity of the assumptions in a simple yet illustrative environment model.
title Mismatch-Robust Underwater Acoustic Localization Using A Differentiable Modular Forward Model
topic Sound
Machine Learning
Audio and Speech Processing
Signal Processing
url https://arxiv.org/abs/2503.23260