MscaleFNO: Multi-scale Fourier Neural Operator Learning for Oscillatory Function Spaces

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: You, Zhilin, Xu, Zhenli, Cai, Wei
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910766237483008
author You, Zhilin
Xu, Zhenli
Cai, Wei
author_facet You, Zhilin
Xu, Zhenli
Cai, Wei
contents In this paper, a multi-scale Fourier neural operator (MscaleFNO) is proposed to reduce the spectral bias of the FNO in learning the mapping between highly oscillatory functions, with application to the nonlinear mapping between the coefficient of the Helmholtz equation and its solution. The MscaleFNO consists of a series of parallel normal FNOs with scaled input of the function and the spatial variable, and their outputs are shown to be able to capture various high-frequency components of the mapping's image. Numerical methods demonstrate the substantial improvement of the MscaleFNO for the problem of wave scattering in the high-frequency regime over the normal FNO with a similar number of network parameters.
format Preprint
id arxiv_https___arxiv_org_abs_2412_20183
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle MscaleFNO: Multi-scale Fourier Neural Operator Learning for Oscillatory Function Spaces
You, Zhilin
Xu, Zhenli
Cai, Wei
Numerical Analysis
In this paper, a multi-scale Fourier neural operator (MscaleFNO) is proposed to reduce the spectral bias of the FNO in learning the mapping between highly oscillatory functions, with application to the nonlinear mapping between the coefficient of the Helmholtz equation and its solution. The MscaleFNO consists of a series of parallel normal FNOs with scaled input of the function and the spatial variable, and their outputs are shown to be able to capture various high-frequency components of the mapping's image. Numerical methods demonstrate the substantial improvement of the MscaleFNO for the problem of wave scattering in the high-frequency regime over the normal FNO with a similar number of network parameters.
title MscaleFNO: Multi-scale Fourier Neural Operator Learning for Oscillatory Function Spaces
topic Numerical Analysis
url https://arxiv.org/abs/2412.20183