Submit

Login Login

Register Register

Home / Journals / CMC / Online First / doi:10.32604/cmc.2026.085901
Journal Menu
Special Issues
Table of Content

All issues

Online First

2026

2025

2024

2023

2022

2021

2020

2019

2018

2017

2016

2015

2014

2013

2012

2011

2010

2009

2008

2007

2006

2005

2004

Open Access

REVIEW

Multi-Source Data Fusion for Underwater Geophysical Field Matching Navigation: A Systematic Review of Methodologies, Challenges, and Future Trends

Jiaqi Mi1, Congcong Ma2, Xinrui Li1, Sixu Huang1, Kunpeng He1,*
1 College of Artificial Intelligence, Nankai University, Tianjin, China
2 Hebei Provincial Engineering Research Center for Power System Generative AI Technology, Baoding, China
* Corresponding Author: Kunpeng He. Email: email
(This article belongs to the Special Issue: Data and Image Processing in Intelligent Information Systems, 2nd Edition)

Computers, Materials & Continua https://doi.org/10.32604/cmc.2026.085901

Received 20 May 2026; Accepted 11 August 2026; Published online 10 September 2026

Abstract

In underwater environments where global navigation satellite systems are unavailable, autonomous underwater vehicles and other underwater vehicles require autonomous navigation methods, among which matching navigation based on seafloor topography, gravity anomalies, and geomagnetic anomalies can effectively mitigate the cumulative errors of inertial navigation systems. To exploit the complementary characteristics of different geophysical fields, multi-source data fusion has become a key technique for improving the robustness and accuracy of underwater matching navigation. This review systematically examines recent advances in underwater geophysical-field data fusion. First, existing methods are categorized into three levels: map-level, feature-level, and decision-level fusion, and a standardized preprocessing pipeline is summarized. On this basis, the core fusion strategies at each level are distilled. Map-level fusion focuses on spatial interpolation and multi-source joint inversion. Feature-level fusion covers the evolution from traditional descriptors to lightweight deep representations and decision-level fusion discusses filtering-based mechanisms, factor graph-based frameworks, and robust matching strategies. Furthermore, a comprehensive testing and benchmarking scheme is proposed, covering datasets, task definitions, and evaluation metrics. Finally, emerging directions, including the integration of physical modeling with learning-based enhancement and adaptive uncertainty management, are discussed. This review aims to provide a unified and reproducible reference for future research and system implementation in underwater geophysical-field fusion navigation.

Keywords

Underwater navigation; geophysical-field matching; data fusion; seafloor topography; gravity anomaly; geomagnetic anomaly; robust matching; benchmarking

  • 98

    View

  • 23

    Download

  • 0

    Like

Related articles
Copyright© 2026 Tech Science Press
© 1997-2026 TSP (Henderson, USA) unless otherwise stated

Share Link