mlsanityData to 14 Oct 2026

Deep Parallel Spectral Neural Operators for Solving Partial Differential Equations with Enhanced Low-Frequency Learning Capability

arXiv 2409.19976 ↗First posted 30 Sep 2024cs.LG cs.NA math.NAcited by 0

Not on the map. Why?

Abstract (arXiv)

Designing universal artificial intelligence (AI) solver for partial differential equations (PDEs) is an open-ended problem and a significant challenge in science and engineering. Currently, data-driven solvers have achieved great success, such as neural operators. However, the ability of various neural operator solvers to learn low-frequency information still needs improvement. In this study, we propose a Deep Parallel Spectral Neural Operator (DPNO) to enhance the ability to learn low-frequency information. Our method enhances the neural operator's ability to learn low-frequency information through parallel modules. In addition, due to the presence of truncation coefficients, some high-frequency information is lost during the nonlinear learning process. We smooth this information through convolutional mappings, thereby reducing high-frequency errors. We selected several challenging partial differential equation datasets for experimentation, and DPNO performed exceptionally well. As a neural operator, DPNO also possesses the capability of resolution invariance.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 25 of its 43 references that are in the map. First posted on arXiv 30 Sep 2024.

Builds on

25 of 43 references.

References · 25

  1. 2017Attention Is All You Needcited by 60,361
  2. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,713
  3. 2021Swin Transformer: Hierarchical Vision Transformer using Shifted Windowscited by 12,139
  4. 2020Fourier Neural Operator for Parametric Partial Differential Equationscited by 2,908
  5. 2020Implicit Neural Representations with Periodic Activation Functionscited by 2,238
  6. 2016Inception-v4, Inception-ResNet and the Impact of Residual Connections on Learningcited by 1,512
  7. 2020Neural Operator: Graph Kernel Network for Partial Differential Equationscited by 734
  8. 2021Machine learning accelerated computational fluid dynamicscited by 471
  9. 2020Time Series Forecasting With Deep Learning: A Surveycited by 459
  10. 2022Fourier Neural Operator with Learned Deformations for PDEs on General Geometriescited by 427
  11. 2023GNOT: A General Neural Operator Transformer for Operator Learningcited by 336
  12. 2024Transolver: A Fast Transformer Solver for PDEs on General Geometriescited by 326
13 more
  1. 2021U-FNO -- An enhanced Fourier neural operator-based deep-learning model for multiphase flowcited by 297
  2. 2022Transformer for Partial Differential Equations' Operator Learningcited by 283
  3. 2021Factorized Fourier Neural Operatorscited by 249
  4. 2021Multiwavelet-based Operator Learning for Differential Equationscited by 234
  5. 2022U-NO: U-shaped Neural Operatorscited by 230
  6. 2023Scalable Transformer for PDE Surrogate Modelingcited by 128
  7. 2013Fast Training of Convolutional Networks through FFTscited by 89
  8. 2023Solving High-Dimensional PDEs with Latent Spectral Modelscited by 89
  9. 2019Learning to Optimize Multigrid PDE Solverscited by 79
  10. 2020MeshfreeFlowNet: A Physics-Constrained Deep Continuous Space-Time Super-Resolution Frameworkcited by 78
  11. 2023Improved Operator Learning by Orthogonal Attentioncited by 61
  12. 2023Koopman neural operator as a mesh-free solver of non-linear partial differential equationscited by 29
  13. 2022Incremental Spatial and Spectral Learning of Neural Operators for Solving Large-Scale PDEscited by 25

Built on by

Not cited yet.