English

Fourier neural operators for spatiotemporal dynamics in two-dimensional turbulence

Fluid Dynamics 2024-09-26 v3 Machine Learning Chaotic Dynamics

Abstract

High-fidelity direct numerical simulation of turbulent flows for most real-world applications remains an outstanding computational challenge. Several machine learning approaches have recently been proposed to alleviate the computational cost even though they become unstable or unphysical for long time predictions. We identify that the Fourier neural operator (FNO) based models combined with a partial differential equation (PDE) solver can accelerate fluid dynamic simulations and thus address computational expense of large-scale turbulence simulations. We treat the FNO model on the same footing as a PDE solver and answer important questions about the volume and temporal resolution of data required to build pre-trained models for turbulence. We also discuss the pitfalls of purely data-driven approaches that need to be avoided by the machine learning models to become viable and competitive tools for long time simulations of turbulence.

Keywords

Cite

@article{arxiv.2409.14660,
  title  = {Fourier neural operators for spatiotemporal dynamics in two-dimensional turbulence},
  author = {Mohammad Atif and Pulkit Dubey and Pratik P. Aghor and Vanessa Lopez-Marrero and Tao Zhang and Abdullah Sharfuddin and Kwangmin Yu and Fan Yang and Foluso Ladeinde and Yangang Liu and Meifeng Lin and Lingda Li},
  journal= {arXiv preprint arXiv:2409.14660},
  year   = {2024}
}
R2 v1 2026-06-28T18:53:12.168Z