# Physics-informed neural networks for one-dimensional sound field predictions with parameterized sources and impedance boundaries

arXiv: https://arxiv.org/abs/2109.11313 · HTML: https://mlsanity.com/paper/2109.11313/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 23 Sep 2021.

## Built on by (most cited first, 7 of 7)

- [Sound propagation in realistic interactive 3D scenes with parameterized sources using deep neural operators](https://mlsanity.com/paper/2308.05141/) (2023)
- [Continual Learning of Range-Dependent Transmission Loss for Underwater Acoustic using Conditional Convolutional Neural Net](https://mlsanity.com/paper/2404.08091/) (2024)
- [Point Neuron Learning: A New Physics-Informed Neural Network Architecture](https://mlsanity.com/paper/2408.16969/) (2024)
- [Physics-Informed Regression: Parameter Estimation in Parameter-Linear Nonlinear Dynamic Models](https://mlsanity.com/paper/2508.19249/) (2025)
- [HergNet: a Fast Neural Surrogate Model for Sound Field Predictions via Superposition of Plane Waves](https://mlsanity.com/paper/2510.24279/) (2025)
- [Physics-informed neural operators for the in situ characterization of locally reacting sound absorbers](https://mlsanity.com/paper/2604.07412/) (2026)
- [Quadrature-Aware Complex-Linear Neural Operator for Boundary-to-Field Prediction in Resonant Acoustics](https://mlsanity.com/paper/2607.04407/) (2026)

## Abstract (arXiv)

Realistic sound is essential in virtual environments, such as computer games and mixed reality. Efficient and accurate numerical methods for pre-calculating acoustics have been developed over the last decade; however, pre-calculating acoustics makes handling dynamic scenes with moving sources challenging, requiring intractable memory storage. A physics-informed neural network (PINN) method in 1D is presented, which learns a compact and efficient surrogate model with parameterized moving Gaussian sources and impedance boundaries, and satisfies a system of coupled equations. The model shows relative mean errors below 2%/0.2 dB and proposes a first step in developing PINNs for realistic 3D scenes.