Realisable E(3)-equivariant graph networks with near-wall reinforcement learning for turbulence closure
Transport Phenomena · 25.09.2026 · 1 (3)
DOI: 10.1515/tp-2026-0063 ↗Kurz gefasst
Fachartikel in der Zeitschrift Transport Phenomena, online erschienen am 14.07.2026. Verfasst von Fredrik Dubay Myklebust und 1 weiteren Autor:innen. Die Arbeit nennt 32 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Ministry of Education (MOE), Singapore.
Abstract (Originalsprache)
Accurate prediction of turbulent flows remains a critical challenge in computational fluid dynamics, particularly for complex, non-equilibrium environments where traditional Reynolds-averaged Navier–Stokes (RANS) models fail to capture deep anisotropy and nonlocal interactions. While data-driven turbulence modeling, such as tensor basis neural networks (TBNNs) offers a promising alternative, these approaches frequently struggle with physical realisability and the inherent nonlocality of turbulent transport. To address these limitations, this work introduces a realisability-preserving E(3)-equivariant graph neural network (E(3)-GNN) for Reynolds-stress anisotropy closure. By leveraging equivariant message passing and a spherical-tensor formulation, the architecture explicitly captures nonlocal neighborhood interactions while guaranteeing Galilean invariance. Furthermore, a stabilized positive semi-definite projection ensures that all predicted states permanently reside within the physically admissible Lumley triangle, completely eliminating the unphysical predictions that traditionally destabilize coupled solvers. Because accurate a priori stress predictions do not guarantee a posteriori stability during active RANS simulation, we additionally propose a solver-in-the-loop fine-tuning methodology using Group Relative Policy Optimization (GRPO). This step directly optimizes a scalar production-correction policy within the active RANS environment to capture dynamic energy propagation. Evaluated on the parameterised periodic hill benchmark family, with training and testing performed on distinct hill geometries, our E(3)-GNN achieves strict physical realisability by construction. Through GRPO fine-tuning, the fully coupled model successfully recovers the intense turbulent kinetic energy ( k ) peaks and mean velocity profiles in the separated shear layer that purely supervised models fail to capture, bridging the gap between offline regression accuracy and stable, coupled solver performance.
Förderung
- Ministry of Education (MOE), Singapore
Zitieren
APA
Myklebust, F. D., & Li, Y. P. (2026). Realisable E(3)-equivariant graph networks with near-wall reinforcement learning for turbulence closure. Transport Phenomena, 1(3). https://doi.org/10.1515/tp-2026-0063
Vancouver
Myklebust FD, Li YP. Realisable E(3)-equivariant graph networks with near-wall reinforcement learning for turbulence closure. Transport Phenomena. 2026;1(3). doi:10.1515/tp-2026-0063
BibTeX
@article{Myklebust2026,
author = {Myklebust, Fredrik Dubay and Li, Yuzhu Pearl},
title = {Realisable E(3)-equivariant graph networks with near-wall reinforcement learning for turbulence closure},
journal = {Transport Phenomena},
year = {2026},
volume = {1},
number = {3},
doi = {10.1515/tp-2026-0063}
}
EUVIMED