EddyFormer: Accelerated Neural Simulations of Three-Dimensional Turbulence at Scale

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Du, Yiheng, Krishnapriyan, Aditi S.
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917047896637440
author Du, Yiheng
Krishnapriyan, Aditi S.
author_facet Du, Yiheng
Krishnapriyan, Aditi S.
contents Computationally resolving turbulence remains a central challenge in fluid dynamics due to its multi-scale interactions. Fully resolving large-scale turbulence through direct numerical simulation (DNS) is computationally prohibitive, motivating data-driven machine learning alternatives. In this work, we propose EddyFormer, a Transformer-based spectral-element (SEM) architecture for large-scale turbulence simulation that combines the accuracy of spectral methods with the scalability of the attention mechanism. We introduce an SEM tokenization that decomposes the flow into grid-scale and subgrid-scale components, enabling capture of both local and global features. We create a new three-dimensional isotropic turbulence dataset and train EddyFormer to achieves DNS-level accuracy at 256^3 resolution, providing a 30x speedup over DNS. When applied to unseen domains up to 4x larger than in training, EddyFormer preserves accuracy on physics-invariant metrics-energy spectra, correlation functions, and structure functions-showing domain generalization. On The Well benchmark suite of diverse turbulent flows, EddyFormer resolves cases where prior ML models fail to converge, accurately reproducing complex dynamics across a wide range of physical conditions.
format Preprint
id arxiv_https___arxiv_org_abs_2510_24173
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle EddyFormer: Accelerated Neural Simulations of Three-Dimensional Turbulence at Scale
Du, Yiheng
Krishnapriyan, Aditi S.
Machine Learning
Numerical Analysis
Dynamical Systems
Fluid Dynamics
Computationally resolving turbulence remains a central challenge in fluid dynamics due to its multi-scale interactions. Fully resolving large-scale turbulence through direct numerical simulation (DNS) is computationally prohibitive, motivating data-driven machine learning alternatives. In this work, we propose EddyFormer, a Transformer-based spectral-element (SEM) architecture for large-scale turbulence simulation that combines the accuracy of spectral methods with the scalability of the attention mechanism. We introduce an SEM tokenization that decomposes the flow into grid-scale and subgrid-scale components, enabling capture of both local and global features. We create a new three-dimensional isotropic turbulence dataset and train EddyFormer to achieves DNS-level accuracy at 256^3 resolution, providing a 30x speedup over DNS. When applied to unseen domains up to 4x larger than in training, EddyFormer preserves accuracy on physics-invariant metrics-energy spectra, correlation functions, and structure functions-showing domain generalization. On The Well benchmark suite of diverse turbulent flows, EddyFormer resolves cases where prior ML models fail to converge, accurately reproducing complex dynamics across a wide range of physical conditions.
title EddyFormer: Accelerated Neural Simulations of Three-Dimensional Turbulence at Scale
topic Machine Learning
Numerical Analysis
Dynamical Systems
Fluid Dynamics
url https://arxiv.org/abs/2510.24173