A derivative-free framework for capturing macroscopic behavior of incompressible turbulent flows
Abstract
The derivative-free loss method (DFLM) is a mesh-free neural network approach for solving partial differential equations by simulating stochastic walkers rather than computing derivatives directly. Although DFLM has previously been applied to the Navier--Stokes equations, extending it to turbulent flows reveals two limitations of its simplest implementation. The walkers do not account for the swirling, directionally stretching motion of the flow, and randomly sampling the walkers used to evaluate the target introduces noise into the learned solution. We address both limitations with an analytic approximation of the walkers' local motion that captures directional stretching and eliminates this sampling noise, while remaining computationally efficient. We study the resulting method as a non-intrusive multiscale solver capable of learning macroscopic flow behavior without resolving every scale on a fine grid or explicitly coupling coarse- and fine-scale models. For two turbulent two-dimensional flows, the proposed method reproduces the macroscopic energy spectrum of fully resolved reference simulations more accurately than the standard method, particularly where directional stretching is strongest, confirming DFLM's efficacy as a multiscale solver for turbulent fluid systems.
Related
- Global Regularity for the 3D Incompressible Navier–Stokes Equations via the Frohmanian Symplectic Tether: Lean 4 Formalization and Conditional Cubic Comparison Framework (v2.1)
- Stroh--Hamiltonian Framework for Modeling Incompressible Poroelastic Materials
- A Joint Information-Theoretic and Graph Learning Framework for Sensor Placement and Macroscopic Traffic State Reconstruction
- A new formulation of Discontinuous Galerkin method for interface capturing approaches
- Dynamics of a Harvested Predator-Prey Model with a Generalized Holling Type~III Response Capturing Group Defense
BibTeX
@misc{han2026derivativefree,
title = {{A derivative-free framework for capturing macroscopic behavior of incompressible turbulent flows}},
author = {Jihun Han and Yoonsang Lee},
howpublished = {arXiv},
year = {2026},
month = sep,
doi = {10.48550/arxiv.2609.17323},
eprint = {2609.17323},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2609.17323},
}
RIS
TY - UNPB
TI - A derivative-free framework for capturing macroscopic behavior of incompressible turbulent flows
AU - Jihun Han
AU - Yoonsang Lee
PY - 2026
DA - 2026/09/15
PB - arXiv
DO - 10.48550/arxiv.2609.17323
UR - https://arxiv.org/abs/2609.17323
AB - The derivative-free loss method (DFLM) is a mesh-free neural network approach for solving partial differential equations by simulating stochastic walkers rather than computing derivatives directly. Although DFLM has previously been applied to the Navier--Stokes equations, extending it to turbulent flows reveals two limitations of its simplest implementation. The walkers do not account for the swirling, directionally stretching motion of the flow, and randomly sampling the walkers used to evaluate the target introduces noise into the learned solution. We address both limitations with an analytic approximation of the walkers' local motion that captures directional stretching and eliminates this sampling noise, while remaining computationally efficient. We study the resulting method as a non-intrusive multiscale solver capable of learning macroscopic flow behavior without resolving every scale on a fine grid or explicitly coupling coarse- and fine-scale models. For two turbulent two-dimensional flows, the proposed method reproduces the macroscopic energy spectrum of fully resolved reference simulations more accurately than the standard method, particularly where directional stretching is strongest, confirming DFLM's efficacy as a multiscale solver for turbulent fluid systems.
ER -