Generative data-driven approaches for stochastic subgrid parameterizations in an idealized ocean model

Abstract

Subgrid parameterizations of mesoscale eddies continue to be in demand for climate simulations. These subgrid parameterizations can be powerfully designed using physics and/or data-driven methods, with uncertainty quantification. For example, Guillaumin and Zanna (2021) proposed a Machine Learning (ML) model that predicts subgrid forcing and its local uncertainty. The major assumption and potential drawback of this model is the statistical independence of stochastic residuals between grid points. Here, we aim to improve the simulation of stochastic forcing with generative models of ML, such as Generative adversarial network (GAN) and Variational autoencoder (VAE). Generative models learn the distribution of subgrid forcing conditioned on the resolved flow directly from data and they can produce new samples from this distribution. Generative models can potentially capture not only the spatial correlation but any statistically significant property of subgrid forcing. We test the proposed stochastic parameterizations offline and online in an idealized ocean model. We show that generative models are able to predict subgrid forcing and its uncertainty with spatially correlated stochastic forcing. Online simulations for a range of resolutions demonstrated that generative models are superior to the baseline ML model at the coarsest resolution.

References in corpus (16)

• PyTorch: An Imperative Style, High-Performance Deep Learning Library
• Conditional Generative Adversarial Nets
• A neural network approach for the blind deconvolution of turbulent flows
• Diversity-Sensitive Conditional Generative Adversarial Networks
• Stable a posteriori LES of 2D turbulence using convolutional neural networks: Backscattering analysis and generalization to higher Re via transfer learning
• A posteriori learning for quasi-geostrophic turbulence parametrization
• Learning physics-constrained subgrid-scale closures in the small-data regime for stable and accurate LES
• A priori analysis on deep learning of subgrid-scale parameterizations for Kraichnan turbulence
• Physical invariance in neural networks for subgrid-scale scalar flux modeling
• Non-local parameterization of atmospheric subgrid processes with neural networks
• Conditional Variational Autoencoder for Neural Machine Translation
• Parameterizing Vertical Mixing Coefficients in the Ocean Surface Boundary Layer using Neural Networks
• Climate-Invariant Machine Learning
• Frame invariant neural network closures for Kraichnan turbulence
• Turbulence closure with small, local neural networks: Forced two-dimensional and $\beta$-plane flows
• History-Based, Bayesian, Closure for Stochastic Parameterization: Application to Lorenz '96

Cited by in corpus (8)

• A stable implementation of a data-driven scale-aware mesoscale parameterization
• Subgrid parameterizations of ocean mesoscale eddies based on Germano decomposition
• Stochastic Latent Transformer: Efficient Modelling of Stochastically Forced Zonal Jets
• Towards Physically Consistent Deep Learning For Climate Model Parameterizations
• Electron neural closure for turbulent magnetosheath simulations: energy channels
• Guided Unconditional and Conditional Generative Models for Super-Resolution and Inference of Quasi-Geostrophic Turbulence
• Evaluation of Analytical Turbulence Closures for Quasi-Geostrophic Ocean Flows with Coastal Boundaries
• Data-driven multiscale modeling for correcting dynamical systems