CoNFiLD-inlet: Synthetic Turbulence Inflow Using Generative Latent Diffusion Models with Neural Fields

TL;DR

This paper introduces CoNFiLD-inlet, a deep learning-based turbulence inflow generator using diffusion models and neural fields, capable of producing realistic, scalable, and robust inflow conditions across various Reynolds numbers for turbulence simulations.

Contribution

It presents a novel diffusion model-based inflow generator that generalizes across Reynolds numbers without retraining, improving realism and robustness over existing methods.

Findings

High fidelity in turbulence inflow generation demonstrated in DNS and WMLES.

Effective generalization across Reynolds numbers $Re_\tau$ between $10^3$ and $10^4$.

Robustness and scalability validated through comprehensive tests.

Abstract

Eddy-resolving turbulence simulations require stochastic inflow conditions that accurately replicate the complex, multi-scale structures of turbulence. Traditional recycling-based methods rely on computationally expensive precursor simulations, while existing synthetic inflow generators often fail to reproduce realistic coherent structures of turbulence. Recent advances in deep learning (DL) have opened new possibilities for inflow turbulence generation, yet many DL-based methods rely on deterministic, autoregressive frameworks prone to error accumulation, resulting in poor robustness for long-term predictions. In this work, we present CoNFiLD-inlet, a novel DL-based inflow turbulence generator that integrates diffusion models with a conditional neural field (CNF)-encoded latent space to produce realistic, stochastic inflow turbulence. By parameterizing inflow conditions using Reynolds numbers, CoNFiLD-inlet generalizes effectively across a wide range of Reynolds numbers ($Re_\tau$ between $10^3$ and $10^4$) without requiring retraining or parameter tuning. Comprehensive validation through a priori and a posteriori tests in Direct Numerical Simulation (DNS) and Wall-Modeled Large Eddy Simulation (WMLES) demonstrates its high fidelity, robustness, and scalability, positioning it as an efficient and versatile solution for inflow turbulence synthesis.