Ensemble flow reconstruction in the atmospheric boundary layer from spatially limited measurements through latent diffusion models
This addresses the challenge of limited atmospheric measurements for researchers in fluid dynamics and meteorology, representing an incremental advance by extending existing methods to a new 3D domain.
The authors tackled the problem of reconstructing unobserved three-dimensional atmospheric boundary layer flows from sparse measurements by posing it as an inpainting problem and using a latent diffusion model, achieving realistic reconstructions even with less than 1% volume coverage and generating diverse samples usable as initial conditions for simulations.
Due to costs and practical constraints, field campaigns in the atmospheric boundary layer typically only measure a fraction of the atmospheric volume of interest. Machine learning techniques have previously successfully reconstructed unobserved regions of flow in canonical fluid mechanics problems and two-dimensional geophysical flows, but these techniques have not yet been demonstrated in the three-dimensional atmospheric boundary layer. Here, we conduct a numerical analogue of a field campaign with spatially limited measurements using large-eddy simulation. We pose flow reconstruction as an inpainting problem, and reconstruct realistic samples of turbulent, three-dimensional flow with the use of a latent diffusion model. The diffusion model generates physically plausible turbulent structures on larger spatial scales, even when input observations cover less than 1% of the volume. Through a combination of qualitative visualization and quantitative assessment, we demonstrate that the diffusion model generates meaningfully diverse samples when conditioned on just one observation. These samples successfully serve as initial conditions for a large-eddy simulation code. We find that diffusion models show promise and potential for other applications for other turbulent flow reconstruction problems.