← Back to all news
arXiv Machine Learning By Mohammad Mahdi Abedi, David Pardo, Tariq Alkhalifah

Gabor-Enhanced Physics-Informed Neural Networks for Fast Simulations of Acoustic Wavefields

Read the original on arXiv Machine Learning →

The paper introduces a simplified Physics-Informed Neural Network (PINN) that uses trainable Gabor basis functions to better capture the localized, oscillatory nature of acoustic wavefields, addressing the low‑frequency bias of traditional PINNs. By redefining the network’s task as learning a nonlinear mapping to a custom Gabor coordinate system, the method absorbs Gabor parameters into the mapping, reducing computational complexity and eliminating manual hyperparameter tuning. Numerical experiments on various velocity models demonstrate faster convergence, higher accuracy, and greater robustness compared to conventional PINNs and earlier Gabor‑based approaches, with the implementation made publicly available for reproducibility.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Machine Learning.

Related stories

arXiv Machine Learning
Oct 3

Neural network-driven domain decomposition for efficient solutions to the Helmholtz equation

The paper presents Finite Basis Physics-Informed Neural Networks (FBPINNs) and their multilevel extensions as a new approach to solving the Helmholtz equation. By decomposing the computational domain into overlapping sub‑domains, each governed by a local neural network, the method aims to improve accuracy and computational efficiency for high‑frequency wave problems in complex two‑dimensional domains. The authors evaluate the technique on the homogeneous Helmholtz case, showing its potential to overcome limitations of traditional finite difference and finite element methods.

By Victorita Dolean, Daria Hrebenshchykova, St\'ephane Lanteri, Victor Michel-Dansac
More like this →
arXiv Machine Learning
Oct 8

Fourier Feature Pyramids for Physics-Informed Neural Networks

The paper introduces beignet, a neural field architecture that replaces the random Fourier feature embedding in physics-informed neural networks with a trainable multi‑resolution Fourier feature pyramid. By using Fourier interpolation and spectral derivatives, beignet efficiently computes spatial derivatives and scales accuracy through the feature pyramid rather than the neural network size. Experiments show that beignet achieves more accurate PDE solutions with fewer parameters than existing PINN methods and can reach machine‑precision residuals on the inviscid Burgers blowup problem using the Adam optimizer.

By Brandon Zhao, Yixuan Wang, Jonathan T. Barron, Katherine L. Bouman, Dor Verbin, Pratul P. Srinivasan
ragbenchmarks
More like this →