Hankel-FNO: Fast Underwater Acoustic Charting Via Physics-Encoded Fourier Neural Operator

2025-12-06

AI Summary

Underwater acoustic mapping is critical for environmental perception and path planning of autonomous underwater vehicles; however, conventional numerical solvers are computationally prohibitive and lack real-time scalability, while existing deep learning approaches suffer from fixed-resolution constraints or explicit PDE modeling, resulting in poor generalization. This paper proposes Hankel-FNO, a Fourier Neural Operator–based model that implicitly encodes wave propagation physics via Hankel transforms and fuses multi-source environmental features (e.g., seafloor topography). It requires no explicit PDE constraints or predefined spatial resolution, enabling cross-domain generalization and high-fidelity, long-range acoustic field prediction. Experiments demonstrate that Hankel-FNO achieves two orders-of-magnitude speedup over traditional solvers, significantly outperforms state-of-the-art data-driven models in accuracy, and adapts to new environments with minimal fine-tuning.

Technology Category

• Machine Learning: Deep Generative Models & Autoencoders
• Search and Optimization: Learning to Search
• Planning, Routing, and Scheduling: Optimization of Spatio-temporal Systems

Application Category

• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications

Abstract

Fast and accurate underwater acoustic charting is crucial for downstream tasks such as environment-aware sensor placement optimization and autonomous vehicle path planning. Conventional methods rely on computationally expensive while accurate numerical solvers, which are not scalable for large-scale or real-time applications. Although deep learning-based surrogate models can accelerate these computations, they often suffer from limitations such as fixed-resolution constraints or dependence on explicit partial differential equation formulations. These issues hinder their applicability and generalization across diverse environments. We propose Hankel-FNO, a Fourier Neural Operator (FNO)-based model for efficient and accurate acoustic charting. By incorporating sound propagation knowledge and bathymetry, our method has high accuracy while maintaining high computational speed. Results demonstrate that Hankel-FNO outperforms traditional solvers in speed and surpasses data-driven alternatives in accuracy, especially in long-range predictions. Experiments show the model's adaptability to diverse environments and sound source settings with minimal fine-tuning.

Problem

• Accelerates underwater acoustic charting for real-time applications
• Overcomes fixed-resolution and PDE dependency in deep learning models
• Enhances accuracy and speed for long-range acoustic predictions

Innovation

• Fourier Neural Operator for acoustic charting
• Incorporates sound propagation and bathymetry knowledge
• Outperforms traditional solvers in speed and accuracy