GaborPINN: Efficient physics informed neural networks using multiplicative filtered networks

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Huang, Xinquan, Alkhalifah, Tariq
Natura: Preprint
Pubblicazione: 2023
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866910579857293312
author Huang, Xinquan
Alkhalifah, Tariq
author_facet Huang, Xinquan
Alkhalifah, Tariq
contents The computation of the seismic wavefield by solving the Helmholtz equation is crucial to many practical applications, e.g., full waveform inversion. Physics-informed neural networks (PINNs) provide functional wavefield solutions represented by neural networks (NNs), but their convergence is slow. To address this problem, we propose a modified PINN using multiplicative filtered networks, which embeds some of the known characteristics of the wavefield in training, e.g., frequency, to achieve much faster convergence. Specifically, we use the Gabor basis function due to its proven ability to represent wavefields accurately and refer to the implementation as GaborPINN. Meanwhile, we incorporate prior information on the frequency of the wavefield into the design of the method to mitigate the influence of the discontinuity of the represented wavefield by GaborPINN. The proposed method achieves up to a two-magnitude increase in the speed of convergence as compared with conventional PINNs.
format Preprint
id arxiv_https___arxiv_org_abs_2308_05843
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle GaborPINN: Efficient physics informed neural networks using multiplicative filtered networks
Huang, Xinquan
Alkhalifah, Tariq
Geophysics
Machine Learning
The computation of the seismic wavefield by solving the Helmholtz equation is crucial to many practical applications, e.g., full waveform inversion. Physics-informed neural networks (PINNs) provide functional wavefield solutions represented by neural networks (NNs), but their convergence is slow. To address this problem, we propose a modified PINN using multiplicative filtered networks, which embeds some of the known characteristics of the wavefield in training, e.g., frequency, to achieve much faster convergence. Specifically, we use the Gabor basis function due to its proven ability to represent wavefields accurately and refer to the implementation as GaborPINN. Meanwhile, we incorporate prior information on the frequency of the wavefield into the design of the method to mitigate the influence of the discontinuity of the represented wavefield by GaborPINN. The proposed method achieves up to a two-magnitude increase in the speed of convergence as compared with conventional PINNs.
title GaborPINN: Efficient physics informed neural networks using multiplicative filtered networks
topic Geophysics
Machine Learning
url https://arxiv.org/abs/2308.05843