Physics-aware graph learning for sound-field reconstruction from sparse measurements
The Journal of the Acoustical Society of America · 01.03.2026 · 159 (3) · 1973-1986
DOI: 10.1121/10.0042849 ↗Kurz gefasst
Fachartikel in der Zeitschrift The Journal of the Acoustical Society of America, online erschienen am 06.03.2026. Verfasst von Fangchao Chen und 3 weiteren Autor:innen. Beteiligte Einrichtung: College of Power and Energy Engineering, Harbin Engineering University, Harbin 150001, China. Die Arbeit nennt 43 Literaturangaben. Gefördert von: National Natural Science Foundation of China.
Abstract (Originalsprache)
A graph neural network (GNN) framework is presented for reconstructing room-acoustic sound fields from sparse microphone measurements. Microphones, sources, and candidate field points are represented as a graph whose node and edge embeddings encode geometric priors and physics-aware features related to wave propagation. A principal neighbourhood aggregation architecture performs message passing and readout to estimate complex acoustic pressure at unobserved locations. Experiments on the MeshRIR dataset demonstrate robust reconstruction across a wide range of sampling sparsities and frequencies. Compared with cylindrical harmonics and plane wave expansion with regularized least squares, the proposed GNN yields consistently lower reconstruction error and higher spatial correlation, with gains most evident under very sparse sampling and at higher frequencies. These results indicate that graph-based learning, equipped with geometric and physics-aware representations, provides an effective and physically consistent approach to sound-field reconstruction for room acoustics.
Autor:innen und Institutionen
- College of Power and Energy Engineering, Harbin Engineering University, Harbin 150001, China.
- School of Civil Aviation, Northwestern Polytechnical University, Xi'an 710072, China.
- State Key Laboratory of Airliner Integration Technology and Flight Simulation, Shanghai 200126, China.
- National Key Laboratory of Strength and Structural Integrity, Xi'an 710072, China.
- China Shipbuilding Industry Corporation, No.708 Research Institute, Shanghai 200126, China.
ORCID-Profile: Fangchao Chen, Youhong Xiao, Liang Yu, Laixu Jiang
Förderung
- National Natural Science Foundation of China
Zitieren
APA
Chen, F., Xiao, Y., Yu, L., & Jiang, L. (2026). Physics-aware graph learning for sound-field reconstruction from sparse measurements. The Journal of the Acoustical Society of America, 159(3), 1973-1986. https://doi.org/10.1121/10.0042849
Vancouver
Chen F, Xiao Y, Yu L, Jiang L. Physics-aware graph learning for sound-field reconstruction from sparse measurements. The Journal of the Acoustical Society of America. 2026;159(3):1973-1986. doi:10.1121/10.0042849
BibTeX
@article{Chen2026,
author = {Chen, Fangchao and Xiao, Youhong and Yu, Liang and Jiang, Laixu},
title = {Physics-aware graph learning for sound-field reconstruction from sparse measurements},
journal = {The Journal of the Acoustical Society of America},
year = {2026},
volume = {159},
number = {3},
pages = {1973--1986},
doi = {10.1121/10.0042849}
}
EUVIMED