Generative Reconstruction of Spatiotemporal Wall-Pressure in Turbulent Boundary Layers via Patchwise Latent Diffusion

TL;DR

This paper introduces a novel probabilistic generative model that reconstructs full spatiotemporal wall-pressure fields in turbulent boundary layers from sparse measurements, enabling accurate, uncertainty-aware predictions at high Reynolds numbers.

Contribution

It develops a patchwise neural field combined with a latent diffusion model for zero-shot adaptation and detailed spatiotemporal reconstruction of wall-pressure fields.

Findings

Accurately recovers instantaneous pressure fields and statistics.

Supports zero-shot adaptation to new sensor layouts.

Produces calibrated uncertainty ensembles.

Abstract

Wall-pressure fluctuations in turbulent boundary layers drive flow-induced noise, structural vibration, and hydroacoustic disturbances, especially in underwater and aerospace systems. Accurate prediction of their wavenumber-frequency spectra is critical for mitigation and design, yet empirical/analytical models rely on simplifying assumptions and miss the full spatiotemporal complexity, while high-fidelity simulations are prohibitive at high Reynolds numbers. Experimental measurements, though accessible, typically provide only pointwise signals and lack the resolution to recover full spatiotemporal fields. We propose a probabilistic generative framework that couples a patchwise (domain-decomposed) conditional neural field with a latent diffusion model to synthesize spatiotemporal wall-pressure fields under varying pressure-gradient conditions. The model conditions on sparse surface-sensor measurements and a low-cost mean-pressure descriptor, supports zero-shot adaptation to new sensor layouts, and produces ensembles with calibrated uncertainty. Validation against reference data shows accurate recovery of instantaneous fields and key statistics.