Physics-informed neural operators for the in situ characterization of locally reacting sound absorbers

2026-04-08

AI Summary

This work addresses the challenges of in situ acoustic surface admittance estimation, which is typically hindered by noise, model inaccuracies, and the restrictive assumptions of conventional methods. The authors propose a novel physics-informed neural operator framework—applied for the first time to in situ characterization of acoustic materials—that embeds the Helmholtz equation, linearized momentum equation, and Robin boundary conditions to directly learn frequency-dependent admittance spectra in an end-to-end manner from near-field acoustic pressure and particle velocity measurements. By circumventing explicit forward modeling and per-frequency inversion, the method achieves globally consistent admittance reconstruction that inherently respects physical constraints. Experimental results demonstrate its superior performance in accurately recovering both real and imaginary parts of the admittance over a broad frequency range, significantly outperforming purely data-driven approaches while exhibiting exceptional robustness to noise and sparse spatial sampling.

Abstract

Accurate knowledge of acoustic surface admittance or impedance is essential for reliable wave-based simulations, yet its in situ estimation remains challenging due to noise, model inaccuracies, and restrictive assumptions of conventional methods. This work presents a physics-informed neural operator approach for estimating frequency-dependent surface admittance directly from near-field measurements of sound pressure and particle velocity. A deep operator network is employed to learn the mapping from measurement data, spatial coordinates, and frequency to acoustic field quantities, while simultaneously inferring a globally consistent surface admittance spectrum without requiring an explicit forward model. The governing acoustic relations, including the Helmholtz equation, the linearized momentum equation, and Robin boundary conditions, are embedded into the training process as physics-based regularization, enabling physically consistent and noise-robust predictions while avoiding frequency-wise inversion. The method is validated using synthetically generated data from a simulation model for two planar porous absorbers under semi free-field conditions across a broad frequency range. Results demonstrate accurate reconstruction of both real and imaginary admittance components and reliable prediction of acoustic field quantities. Parameter studies confirm improved robustness to noise and sparse sampling compared to purely data-driven approaches, highlighting the potential of physics-informed neural operators for in situ acoustic material characterization.

Problem

• in situ characterization
• sound absorbers
• surface admittance
• acoustic impedance
• near-field measurements

Innovation

• physics-informed neural operator
• acoustic impedance estimation
• in situ characterization
• Helmholtz equation
• Robin boundary conditions