Resampling with neural networks for stochastic parameterization in multiscale systems

Abstract

In simulations of multiscale dynamical systems, not all relevant processes can be resolved explicitly. Taking the effect of the unresolved processes into account is important, which introduces the need for paramerizations. We present a machine-learning method, used for the conditional resampling of observations or reference data from a fully resolved simulation. It is based on the probabilistic classiffcation of subsets of reference data, conditioned on macroscopic variables. This method is used to formulate a parameterization that is stochastic, taking the uncertainty of the unresolved scales into account. We validate our approach on the Lorenz 96 system, using two different parameter settings which are challenging for parameterization methods.

arXiv comment27 pages, 17 figures. Submitted

References in corpus (9)

• Deep learning to represent sub-grid processes in climate models
• Stochastic Parameterization: Towards a new view of Weather and Climate Models
• Hybrid Forecasting of Chaotic Processes: Using Machine Learning in Conjunction with a Knowledge-Based Model
• Sub-grid modelling for two-dimensional turbulence using neural networks
• Machine Learning for Stochastic Parameterization: Generative Adversarial Networks in the Lorenz '96 Model
• Data-driven parameterization of the generalized Langevin equation
• Data-driven model reduction, Wiener projections, and the Koopman-Mori-Zwanzig formalism
• Coupled online learning as a way to tackle instabilities and biases in neural network parameterizations
• The Kernel Mixture Network: A Nonparametric Method for Conditional Density Estimation of Continuous Random Variables

Cited by in corpus (6)

• VECMAtk: A Scalable Verification, Validation and Uncertainty Quantification Toolkit for Scientific Simulations
• Controlled abstention neural networks for identifying skillful predictions for regression problems
• Controlled abstention neural networks for identifying skillful predictions for classification problems
• Data-driven dynamical coarse-graining for condensed matter systems
• Reduced Data-Driven Turbulence Closure for Capturing Long-Term Statistics
• Analyzing High-Resolution Clouds and Convection using Multi-Channel VAEs