Neural Radiated-Noise Fields for Unmanned Underwater Vehicle Noise Spectrum Prediction in Three-Dimensional Scenes

2026-05-29

AI Summary

This work addresses the limitations of traditional physics-based methods for predicting radiated noise from unmanned underwater vehicles (UUVs), which rely on precise structural and environmental information and struggle to model continuous spectral responses in three-dimensional space. To overcome this, the authors propose a Neural Radiated Noise Field (NRNF) that represents the noise spectrum as a continuous function of UUV position, hydrophone location, yaw angle, and frequency, enabling query-based prediction at arbitrary spatial points. The approach integrates a learnable 3D feature grid to explicitly encode environmental structure and acoustic propagation effects, augmented with sinusoidal position–frequency encoding to enhance high-dimensional input modeling. Trained on lake trial data, the model achieves an average error of 3.5 dB across 50–5000 Hz, demonstrating strongest performance in horizontal extrapolation, moderate generalization across missions, and greatest difficulty in depth extrapolation, with the feature grid substantially improving prediction stability.

Abstract

Radiated noise in unmanned underwater vehicles (UUVs) is an important indicator for characterizing acoustic signatures and evaluating platform performance. To address the strong dependence of traditional physics-based modeling and numerical simulation methods on target structural information and environmental boundary conditions, and their inability to achieve continuous spatial spectrum-response modeling in three-dimensional scenes, this paper proposes a neural radiated-noise field (NRNF). An NRNF represents the UUV radiated-noise spectrum as a continuous function of the three-dimensional UUV position, the three-dimensional hydrophone position, the UUV yaw angle, and the frequency, enabling query-based prediction at arbitrary spatial locations. The proposed method employs sinusoidal encoding for position and frequency, and introduces a learnable three-dimensional scene feature grid to explicitly represent environmental structure and propagation effects. A spectrum-prediction dataset is constructed from lake trials, and the proposed model is evaluated under three settings: horizontal extrapolation, depth extrapolation, and cross-run generalization. Results show that the NRNF achieves an average prediction error of 3.5 dB in the 50 to 5000 Hz band. Horizontal extrapolation is easiest, depth extrapolation is the most challenging, and cross-run generalization is of intermediate difficulty. Further ablation results demonstrate that the scene feature grid significantly improves the prediction stability and spatial generalization of the model.

Problem

• radiated noise
• unmanned underwater vehicle
• spectrum prediction
• three-dimensional scenes
• acoustic signature

Innovation

• Neural Radiated-Noise Field
• 3D acoustic modeling
• scene feature grid
• spectrum prediction
• spatial generalization