Guided Unconditional and Conditional Generative Models for Super-Resolution and Inference of Quasi-Geostrophic Turbulence

Abstract

Typically, numerical simulations of Earth systems are coarse, and Earth observations are sparse and gappy. We apply four generative diffusion modeling approaches to super-resolution and inference of forced two-dimensional quasi-geostrophic turbulence on the beta-plane from coarse, sparse, and gappy observations. Two guided approaches minimally adapt a pre-trained unconditional model: SDEdit modifies the initial condition, and Diffusion Posterior Sampling (DPS) modifies the reverse diffusion process score. Two conditional approaches, a vanilla variant and classifier-free guidance, require training with paired high-resolution and observation data. We consider multiple test cases spanning: two regimes, eddy and anisotropic-jet turbulence; two Reynolds numbers, 10^3 and 10^4; and two observation types, 4x coarse-resolution fields and coarse, sparse and gappy observations. Our comprehensive skill metrics include norms of the reconstructed vorticity fields, turbulence statistical quantities, and quantifications of the super-resolved probabilistic ensembles and their errors. We also study the sensitivity to tuning parameters such as guidance strength. Results show that the generated super-resolution fields of SDEdit are unphysical, while those of DPS are reasonable but with smoothed fine-scale features; however, neither of these lower-cost models propagates observational information effectively to unobserved regions. The two conditional models require re-training, but reconstruct missing fine-scale features, are cycle-consistent with observations, and predict correct turbulence statistics, including the tails. Further, their mean errors are highly correlated with and predictable from their ensemble standard deviations. Results highlight the tradeoffs between ease of implementation, fidelity (sharpness), and cycle-consistency of the diffusion models, and offer practical guidance for deployment.

47 pages, 16 figures, 5 tables

References in corpus (23)

• An Introduction to Variational Autoencoders
• Super-resolution reconstruction of turbulent flows with machine learning
• Curse-of-dimensionality revisited: Collapse of the particle filter in very large scale systems
• Machine learning based spatio-temporal super resolution reconstruction of turbulent flows
• Sub-grid modelling for two-dimensional turbulence using neural networks
• Unsupervised deep learning for super-resolution reconstruction of turbulence
• Super-resolution and denoising of fluid flow using physics-informed convolutional neural networks without high-resolution labels
• Robust flow field reconstruction from limited measurements via sparse representation
• Stable a posteriori LES of 2D turbulence using convolutional neural networks: Backscattering analysis and generalization to higher Re via transfer learning
• Resolvent-based estimation of space-time flow statistics
• Hitchhiker's Guide to Super-Resolution: Introduction and Recent Advances
• A posteriori learning for quasi-geostrophic turbulence parametrization
• Learning physics-constrained subgrid-scale closures in the small-data regime for stable and accurate LES
• Solution of Physics-based Bayesian Inverse Problems with Deep Generative Priors
• Explaining the physics of transfer learning a data-driven subgrid-scale closure to a different turbulent flow
• Dynamical Origins for Non-Gaussian Vorticity Distributions in Turbulent Flows
• Single-snapshot machine learning for super-resolution of turbulence
• A framework for the evaluation of turbulence closures used in mesoscale ocean large-eddy simulations
• Generative data-driven approaches for stochastic subgrid parameterizations in an idealized ocean model
• Neural Closure Models for Dynamical Systems
• Learning Closed-form Equations for Subgrid-scale Closures from High-fidelity Data: Promises and Challenges
• Spectrally Decomposed Diffusion Models for Generative Turbulence Recovery
• Taming Uncertainty in a Complex World: The Rise of Uncertainty Quantification -- A Tutorial for Beginners