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

2026-01-27

AI Summary

This work addresses the challenge of reconstructing a complete acoustic field from sparse magnitude-only measurements in scenarios where phase information is missing or unreliable. To this end, the authors propose a novel approach that integrates phase retrieval with physics-informed neural networks (PINNs). The method employs a dual-branch neural network architecture to separately model the magnitude and phase components, reconstructing the complex acoustic field while enforcing the Helmholtz equation as a physical constraint. This study represents the first integration of phase retrieval mechanisms into the PINN framework, significantly extending its applicability to acoustic inverse problems. Experimental results demonstrate that the proposed method accurately recovers the full acoustic field from sparse magnitude observations, substantially outperforming conventional PINN-based approaches.

Technology Category

Cognitive Modeling & Cognitive Systems: Neural Spike CodingMachine Learning: Multimodal LearningConstraint Satisfaction and Optimization: Constraint Learning and Acquisition

Application Category

Search and Retrieval-Augmented AI: Multilingual and cross-lingual Web searchGraph Algorithms and Modeling for the Web: Algorithms and analysis for incomplete, noisy, or partially observed Web-related graphsSystems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications

Abstract

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.

Problem

• phase retrieval
• acoustic field reconstruction
• magnitude-only measurements
• physics-informed neural networks
• phase-less sensing

Innovation

• phase retrieval
• physics-informed neural networks
• acoustic field reconstruction
• magnitude-only measurements
• complex amplitude modeling