Phase-Retrieval-Based Physics-Informed Neural Networks For Acoustic Magnitude Field Reconstruction

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Schrader, Karl, Koyama, Shoichi, Nakamura, Tomohiko, Pezzoli, Mirco
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917225107030016
author Schrader, Karl
Koyama, Shoichi
Nakamura, Tomohiko
Pezzoli, Mirco
author_facet Schrader, Karl
Koyama, Shoichi
Nakamura, Tomohiko
Pezzoli, Mirco
contents We propose a method for estimating the magnitude distribution of an acoustic field from spatially sparse magnitude measurements. Such a method is useful when phase measurements are unreliable or inaccessible. Physics-informed neural networks (PINNs) have shown promise for sound field estimation by incorporating constraints derived from governing partial differential equations (PDEs) into neural networks. However, they do not extend to settings where phase measurements are unavailable, as the loss function based on the governing PDE relies on phase information. To remedy this, we propose a phase-retrieval-based PINN for magnitude field estimation. By representing the magnitude and phase distributions with separate networks, the PDE loss can be computed based on the reconstructed complex amplitude. We demonstrate the effectiveness of our phase-retrieval-based PINN through experimental evaluation.
format Preprint
id arxiv_https___arxiv_org_abs_2601_19297
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Phase-Retrieval-Based Physics-Informed Neural Networks For Acoustic Magnitude Field Reconstruction
Schrader, Karl
Koyama, Shoichi
Nakamura, Tomohiko
Pezzoli, Mirco
Sound
Audio and Speech Processing
We propose a method for estimating the magnitude distribution of an acoustic field from spatially sparse magnitude measurements. Such a method is useful when phase measurements are unreliable or inaccessible. Physics-informed neural networks (PINNs) have shown promise for sound field estimation by incorporating constraints derived from governing partial differential equations (PDEs) into neural networks. However, they do not extend to settings where phase measurements are unavailable, as the loss function based on the governing PDE relies on phase information. To remedy this, we propose a phase-retrieval-based PINN for magnitude field estimation. By representing the magnitude and phase distributions with separate networks, the PDE loss can be computed based on the reconstructed complex amplitude. We demonstrate the effectiveness of our phase-retrieval-based PINN through experimental evaluation.
title Phase-Retrieval-Based Physics-Informed Neural Networks For Acoustic Magnitude Field Reconstruction
topic Sound
Audio and Speech Processing
url https://arxiv.org/abs/2601.19297