























Abstract:Accurate autoregressive prediction of 3D turbulent flows remains challenging for neural PDE solvers, as small errors in fine-scale structures can accumulate rapidly over rollout. In this paper, we propose FlowRefiner, a flow matching-based iterative refinement framework for 3D turbulent flow simulation. The method replaces stochastic denoising refinement with deterministic ODE-based correction, uses a unified velocity-field regression objective across all refinement stages, and introduces a decoupled sigma schedule that fixes the noise range independently of refinement depth. These design choices yield stable and effective refinement in the small-noise regime. Experiments on large-scale 3D turbulence with rich multi-scale structures show that FlowRefiner achieves state-of-the-art autoregressive prediction accuracy and strong physical consistency. Although developed for turbulent flow simulation, the proposed framework is broadly applicable to iterative refinement problems in scientific modeling.
| Subjects: | Fluid Dynamics (physics.flu-dyn); Machine Learning (cs.LG) |
| Cite as: | arXiv:2604.17149 [physics.flu-dyn] |
| (or arXiv:2604.17149v2 [physics.flu-dyn] for this version) | |
| https://doi.org/10.48550/arXiv.2604.17149 arXiv-issued DOI via DataCite |
From: Runlong Yu [view email]
[v1]
Sat, 18 Apr 2026 21:17:00 UTC (6,013 KB)
[v2]
Sat, 25 Apr 2026 03:55:48 UTC (6,013 KB)
此内容由惯性聚合(RSS阅读器)自动聚合整理,仅供阅读参考。 原文来自 — 版权归原作者所有。