Ensemble flow reconstruction in the atmospheric boundary layer from spatially limited measurements through latent diffusion models

Abstract

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.

arXiv comment35 pages, 19 figures

References in corpus (21)

• Array Programming with NumPy
• Large Scale GAN Training for High Fidelity Natural Image Synthesis
• Instance Normalization: The Missing Ingredient for Fast Stylization
• Diffusion Models Beat GANs on Image Synthesis
• Deep Unsupervised Learning using Nonequilibrium Thermodynamics
• Score-Based Generative Modeling through Stochastic Differential Equations
• Generative Modeling by Estimating Gradients of the Data Distribution
• Skillful Precipitation Nowcasting using Deep Generative Models of Radar
• Super-resolution reconstruction of turbulent flows with machine learning
• Flow over an espresso cup: Inferring 3D velocity and pressure fields from tomographic background oriented schlieren videos via physics-informed neural networks
• Machine learning based spatio-temporal super resolution reconstruction of turbulent flows
• Super-Resolution Analysis via Machine Learning: A Survey for Fluid Flows
• Understanding Diffusion Models: A Unified Perspective
• High-fidelity reconstruction of turbulent flow from spatially limited data using enhanced super-resolution generative adversarial network
• Reconstruction of turbulent data with deep generative models for semantic inpainting from TURB-Rot database
• RePaint: Inpainting using Denoising Diffusion Probabilistic Models
• Synchronization to big-data: nudging the Navier-Stokes equations for data assimilation of turbulent flows
• State estimation in turbulent channel flow from limited observations
• Reconstructing velocity and pressure from sparse noisy particle tracks using Physics-Informed Neural Networks
• Nudging-based data assimilation of the turbulent flow around a square cylinder
• Semi Conditional Variational Auto-Encoder for Flow Reconstruction and Uncertainty Quantification from Limited Observations

Cited by in corpus (1)

• Interpretable structural model error discovery from sparse assimilation increments using spectral bias-reduced neural networks: A quasi-geostrophic turbulence test case