EUVIMEDEUVIMED entdecken
Crossref

Implicit factorized transformer approach to fast prediction of turbulent channel flows

Huiyu Yang, Yunpeng Wang, Jianchun Wang

Science China Physics, Mechanics & Astronomy · 2026-01 · 69 (1)

DOI: 10.1007/s11433-024-2666-9 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Science China Physics, Mechanics & Astronomy, online erschienen am 01.09.2025. Verfasst von Huiyu Yang und 2 weiteren Autor:innen. Die Arbeit wurde bisher 6-mal zitiert (Crossref) und nennt 57 Literaturangaben.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Transformer neural operators have recently become an effective approach for surrogate modeling of systems governed by partial differential equations (PDEs). In this paper, we introduce a modified implicit factorized transformer (IFactFormer-m) model, replacing the original chained factorized attention with parallel factorized attention. The IFactFormer-m model successfully performs long-term predictions for turbulent channel flow. In contrast, the original IFactFormer (IFactFormer-o), Fourier neural operator (FNO), and implicit Fourier neural operator (IFNO) exhibit a poor performance. Turbulent channel flows are simulated by direct numerical simulation using fine grids at friction Reynolds numbers Reτ ≈ 180, 395, 590, and filtered to coarse grids for training neural operator. The neural operator takes the current flow field as input and predicts the flow field at the next time step, and long-term prediction is achieved in the posterior through an autoregressive approach. The results show that IFactFormer-m, compared with other neural operators and the traditional large eddy simulation (LES) methods, including the dynamic Smagorinsky model (DSM) and the wall-adapted local eddy-viscosity (WALE) model, reduces prediction errors in the short term, and achieves stable and accurate long-term prediction of various statistical properties and flow structures, including the energy spectrum, mean streamwise velocity, root mean square (RMS) values of fluctuating velocities, Reynolds shear stress, and spatial structures of instantaneous velocity. Moreover, the trained IFactFormer-m is much faster than traditional LES methods. By analyzing the attention kernels, we elucidate why IFactFormer-m converges faster and achieves a stable and accurate long-term prediction compared with IFactFormer-o. Code and data are available at: https://github.com/huiyu-2002/IFactFormer-m.

Zitieren

APA

Yang, H., Wang, Y., & Wang, J. (2026). Implicit factorized transformer approach to fast prediction of turbulent channel flows. Science China Physics, Mechanics & Astronomy, 69(1). https://doi.org/10.1007/s11433-024-2666-9

Vancouver

Yang H, Wang Y, Wang J. Implicit factorized transformer approach to fast prediction of turbulent channel flows. Science China Physics, Mechanics & Astronomy. 2026;69(1). doi:10.1007/s11433-024-2666-9

BibTeX
@article{Yang2026,
  author = {Yang, Huiyu and Wang, Yunpeng and Wang, Jianchun},
  title = {Implicit factorized transformer approach to fast prediction of turbulent channel flows},
  journal = {Science China Physics, Mechanics & Astronomy},
  year = {2026},
  volume = {69},
  number = {1},
  doi = {10.1007/s11433-024-2666-9}
}
Kostenlos starten →