What question did this study set out to answer?

To develop and validate machine learning approaches for in situ estimation of acoustic surface impedance using sound pressure measurements.

May 14, 2026The Journal of the Acoustical Society of America

Machine learning-based approaches for the in situ estimation of the acoustic surface impedance

View Full Paper

Ask AI

Bookmark

Authors

SSchmid JSJohannes D. Schmid SMSteffen Marburg

Discussion

Member takes

Overview

Randomized trial demonstrates machine learning techniques for estimating acoustic impedance in real-world scenarios, suggesting improved boundary condition analysis.

Key Points

To develop and validate machine learning approaches for in situ estimation of acoustic surface impedance using sound pressure measurements.
Proposed two machine learning techniques: a Bayesian approach and a Deep Operator Network.
Utilized a finite element model for the Bayesian method to approximate unknown impedances.
Validated approaches on representative acoustic problems to assess accuracy and robustness.
The Bayesian approach accurately approximated the posterior distribution of unknown impedances, validated under practical conditions.
The Deep Operator Network effectively learned mappings from sound pressure fields to boundary conditions, showing flexibility and accuracy.
Both methods demonstrated strong performance for real-world acoustic applications.

Cite This Study

Schmid et al. (2025) studied this question.

synapsesocial.com/papers/6a0566bda550a87e60a1ea8b https://doi.org/10.1121/10.0040225

View Full Paper

Ask AI

Bookmark

May 14, 2026The Journal of the Acoustical Society of America

Machine learning-based approaches for the in situ estimation of the acoustic surface impedance

View Full Paper

Ask AI

Bookmark

Authors

SSchmid JSJohannes D. Schmid SMSteffen Marburg

Discussion

Member takes

Overview

Randomized trial demonstrates machine learning techniques for estimating acoustic impedance in real-world scenarios, suggesting improved boundary condition analysis.

Key Points

To develop and validate machine learning approaches for in situ estimation of acoustic surface impedance using sound pressure measurements.
Proposed two machine learning techniques: a Bayesian approach and a Deep Operator Network.
Utilized a finite element model for the Bayesian method to approximate unknown impedances.
Validated approaches on representative acoustic problems to assess accuracy and robustness.
The Bayesian approach accurately approximated the posterior distribution of unknown impedances, validated under practical conditions.
The Deep Operator Network effectively learned mappings from sound pressure fields to boundary conditions, showing flexibility and accuracy.
Both methods demonstrated strong performance for real-world acoustic applications.

Cite This Study

Schmid et al. (2025) studied this question.

synapsesocial.com/papers/6a0566bda550a87e60a1ea8b https://doi.org/10.1121/10.0040225

View Full Paper

Ask AI

Bookmark