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

arXiv: https://arxiv.org/abs/2503.23260 · HTML: https://mlsanity.com/paper/2503.23260/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 5 of its 30 references that are in the map.
- First posted on arXiv 30 Mar 2025.

## Builds on (most cited first, 5 of 5)

- [Implicit Neural Representations with Periodic Activation Functions](https://mlsanity.com/paper/2006.09661/) (2020)
- [How transferable are features in deep neural networks?](https://mlsanity.com/paper/1411.1792/) (2014)
- [Source localization in an ocean waveguide using supervised machine learning](https://mlsanity.com/paper/1701.08431/) (2017)
- [SCORE: A Second-Order Conic Initialization for Range-Aided SLAM](https://mlsanity.com/paper/2210.03177/) (2022)
- [Data-aided Underwater Acoustic Ray Propagation Modeling](https://mlsanity.com/paper/2205.06066/) (2022)

## Abstract (arXiv)

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.