Distilled one-step consistency model from optimal-transport flow-matching teacher reconstructs high-fidelity dynamical system flows from low-fidelity data with 12x speedup, half the parameters, and 23.1% better SSIM than scratch-trained baselines.
Title resolution pending
5 Pith papers cite this work. Polarity classification is still indexing.
5
Pith papers citing it
citation-role summary
baseline 1
dataset 1
citation-polarity summary
verdicts
UNVERDICTED 5representative citing papers
LESnets integrates LES equations and the law of the wall into F-FNO to enable data-free, stable long-term predictions of wall-bounded turbulence at Re_tau up to 1000 on coarse grids, matching traditional LES accuracy at higher efficiency.
A k-omega turbulence model is enhanced with PINN-derived turbulent viscosity correction and NN-adjusted coefficients, producing improved velocity, skin friction, and turbulent kinetic energy profiles against DNS in channel and periodic hill flows.
Eddy viscosity in wall turbulence varies with outer boundary conditions across configurations, and a parametric outer correction embedded in a Cess-van Driest framework improves mean-flow accuracy for open channels while matching classical results elsewhere.
Inner-scaled linear contribution to wall-pressure variance remains O(1) at high Reynolds numbers, based on collapse of measured factors and inverse decay of gradient variance in the inertial layer.
citing papers explorer
-
Physical Fidelity Reconstruction via Improved Consistency-Distilled Flow Matching for Dynamical Systems
Distilled one-step consistency model from optimal-transport flow-matching teacher reconstructs high-fidelity dynamical system flows from low-fidelity data with 12x speedup, half the parameters, and 23.1% better SSIM than scratch-trained baselines.
-
Large-eddy simulation nets (LESnets) based on physics-informed neural operator for wall-bounded turbulence
LESnets integrates LES equations and the law of the wall into F-FNO to enable data-free, stable long-term predictions of wall-bounded turbulence at Re_tau up to 1000 on coarse grids, matching traditional LES accuracy at higher efficiency.
-
Using Physics Informed Neural Network (PINN) and Neural Network (NN) to Improve a $k-\omega$ Turbulence Model
A k-omega turbulence model is enhanced with PINN-derived turbulent viscosity correction and NN-adjusted coefficients, producing improved velocity, skin friction, and turbulent kinetic energy profiles against DNS in channel and periodic hill flows.
-
Revisit eddy viscosity in pressure-driven wall turbulence at high Reynolds number
Eddy viscosity in wall turbulence varies with outer boundary conditions across configurations, and a parametric outer correction embedded in a Cess-van Driest framework improves mean-flow accuracy for open channels while matching classical results elsewhere.
-
An Inner-Scaled Linear Contribution to Wall-Pressure Variance at High Reynolds Number
Inner-scaled linear contribution to wall-pressure variance remains O(1) at high Reynolds numbers, based on collapse of measured factors and inverse decay of gradient variance in the inertial layer.