DOAJ Open Access 2025

Stable adaptive training for physics-informed neural networks in acoustic wave propagation

Márcio Marques Leonardo Mendonça Arthur Bizzi Leonardo Moreira Christian Oliveira +8 lainnya

Lihat Sumber DOI

Abstrak

Physics-informed neural networks (PINNs) have emerged as a promising tool for simulating various phenomena. However, their application in underwater acoustics remains challenging, primarily due to the need to sample large computational domains and to convergence to trivial solutions. This study presents a strategy to address these issues by combining adaptive domain sampling with absorbing boundary conditions. The adaptive sampler dynamically focuses computational effort on regions where the acoustic energy is localized, while the absorbing boundaries perform training stabilization. Numerical experiments show that our method improves the stability and convergence of PINN training, leading to more accurate and reliable wave propagation simulations.

Topik & Kata Kunci

Acoustics. Sound

Penulis (13)

Márcio Marques

Leonardo Mendonça

Arthur Bizzi

Leonardo Moreira

Christian Oliveira

Deborah Oliveira

Lucas Fernandez

Vitor Balestro

João Pereira

Daniel Yukimura

Tiago Novello

Pavel Petrov

Lucas Nissenbaum

Format Sitasi

APA MLA BibTeX

Marques, M., Mendonça, L., Bizzi, A., Moreira, L., Oliveira, C., Oliveira, D. et al. (2025). Stable adaptive training for physics-informed neural networks in acoustic wave propagation. https://doi.org/10.1121/10.0039767

Akses Cepat

Lihat di Sumber doi.org/10.1121/10.0039767

Informasi Jurnal

Tahun Terbit: 2025
Sumber Database: DOAJ
DOI: 10.1121/10.0039767
Akses: Open Access ✓