Turbulence forecasting via Neural ODE

Abstract

Fluid turbulence is characterized by strong coupling across a broad range of scales. Furthermore, besides the usual local cascades, such coupling may extend to interactions that are non-local in scale-space. As such the computational demands associated with explicitly resolving the full set of scales and their interactions, as in the Direct Numerical Simulation (DNS) of the Navier-Stokes equations, in most problems of practical interest are so high that reduced modeling of scales and interactions is required before further progress can be made. While popular reduced models are typically based on phenomenological modeling of relevant turbulent processes, recent advances in machine learning techniques have energized efforts to further improve the accuracy of such reduced models. In contrast to such efforts that seek to improve an existing turbulence model, we propose a machine learning(ML) methodology that captures, de novo, underlying turbulence phenomenology without a pre-specified model form. To illustrate the approach, we consider transient modeling of the dissipation of turbulent kinetic energy, a fundamental turbulent process that is central to a wide range of turbulence models using a Neural ODE approach. After presenting details of the methodology, we show that this approach outperforms state-of-the-art approaches.

References in corpus (8)

• Auto-Encoding Variational Bayes
• Stochastic Backpropagation and Approximate Inference in Deep Generative Models
• Model-Agnostic Interpretability of Machine Learning
• Latent ODEs for Irregularly-Sampled Time Series
• Time-series learning of latent-space dynamics for reduced-order model closure
• NeuPDE: Neural Network Based Ordinary and Partial Differential Equations for Modeling Time-Dependent Data
• InfoCNF: An Efficient Conditional Continuous Normalizing Flow with Adaptive Solvers
• Geometrization of deep networks for the interpretability of deep learning systems

Cited by in corpus (15)

• NeuroBEM: Hybrid Aerodynamic Quadrotor Model
• Data-Driven Reduced-Order Modeling of Spatiotemporal Chaos with Neural Ordinary Differential Equations
• DeepCFD: Efficient Steady-State Laminar Flow Approximation with Deep Convolutional Neural Networks
• Parameterized Neural Ordinary Differential Equations: Applications to Computational Physics Problems
• TorchDyn: A Neural Differential Equations Library
• Neural Ordinary Differential Equations for Model Order Reduction of Stiff Systems
• Neural Dynamical Systems: Balancing Structure and Flexibility in Physical Prediction
• Machine learning structure preserving brackets for forecasting irreversible processes
• Reduced-order Model for Fluid Flows via Neural Ordinary Differential Equations
• Accelerating Training in Artificial Neural Networks with Dynamic Mode Decomposition
• A composable autoencoder-based iterative algorithm for accelerating numerical simulations
• Tensorized Transformer for Dynamical Systems Modeling
• Data-driven geophysical forecasting: Simple, low-cost, and accurate baselines with kernel methods
• A Latent space solver for PDE generalization
• Network Compression for Machine-Learnt Fluid Simulations