Guiding diffusion models to reconstruct flow fields from sparse data

TL;DR

This paper introduces a novel diffusion model-based approach for reconstructing unsteady flow fields from sparse measurements, integrating physics knowledge to improve accuracy and outperform existing methods in turbulent flow data reconstruction.

Contribution

The work presents a new sampling method guiding diffusion models with sparse data and physics constraints, enhancing flow field reconstruction fidelity.

Findings

Outperforms other diffusion methods in structure prediction

Achieves higher pixel-wise accuracy in turbulent flow reconstructions

Effective in 2D and 3D flow data scenarios

Abstract

The reconstruction of unsteady flow fields from limited measurements is a challenging and crucial task for many engineering applications. Machine learning models are gaining popularity for solving this problem due to their ability to learn complex patterns from data and to generalize across diverse conditions. Among these, diffusion models have emerged as being particularly powerful for generative tasks, producing high-quality samples by iteratively refining noisy inputs. In contrast to other methods, these generative models are capable of reconstructing the smallest scales of the fluid spectrum. In this work, we introduce a novel sampling method for diffusion models that enables the reconstruction of high-fidelity samples by guiding the reverse process using the available sparse data. Moreover, we enhance the reconstructions with available physics knowledge using a conflict-free update method during training. To evaluate the effectiveness of our method, we conduct experiments on 2 and 3-dimensional turbulent flow data. Our method consistently outperforms other diffusion-based methods in predicting the fluid's structure and in pixel-wise accuracy. This study underscores the remarkable potential of diffusion models in reconstructing flow field data, paving the way for leveraging them in fluid dynamics research and applications ranging from super-resolution to reconstructions of experiments.