8–12 Sept 2026
Europe/Vienna timezone

Physics-Informed Neural Networks for Room-Acoustic Simulations within Bayesian Framework

FA2026/790
10 Sept 2026, 11:20
20m
Saal 12A (Messe Congress Graz)

Saal 12A

Messe Congress Graz

A12 Numerical, Computational, and Theoretical Acoustics A12.08/A16.12 Numerical Methods for Room Acoustics

Speaker

Ning Xiang (Rensselaer Polytechnic Institute)

Description

Accurate prediction of sound energy decay in enclosed spaces is essential for acoustic design in performance halls, classrooms, and recording studios. Statistical room-acoustic theory, such as the Sabine reverberation formula, provides fast but spatially limited estimates, while wave-theoretical simulations are physically accurate but computationally expensive. This work presents a Physics-Informed Neural Network (PINN) trained to solve the acoustic diffusion equation, using finite-difference time-domain (FDTD) simulations for supervised learning. The network takes spatial position and time as inputs and predicts sound energy density without requiring re-simulation. The maximum likelihood enforces the governing partial differential equation, boundary conditions, and initial conditions alongside supervised data. Preliminary results show close agreement with FDTD ground truth across the full decay range, accurately reproducing the temporal decay process at the receiver positions. Full temporal coverage of the decay process provides stronger training than spatially dense but temporally sparse sampling. The current work also explores Bayesian probabilistic evaluations to quantify uncertainties during training with the goal of generalizing across room geometries and absorption coefficients without retraining.

Authors

William Zheng (Rensselaer Polytechnic Institute) Ning Xiang (Rensselaer Polytechnic Institute)

Presentation materials