mlsanityData to 7 Oct 2026

Machine-Learned Closure of URANS for Stably Stratified Turbulence: Connecting Physical Timescales & Data Hyperparameters of Deep Time-Series Models

arXiv 2404.16141 ↗First posted 24 Apr 2024physics.flu-dyn cs.LG physics.ao-phcited by 0

Not on the map. Why?

Abstract (arXiv)

We develop time-series machine learning (ML) methods for closure modeling of the Unsteady Reynolds Averaged Navier Stokes (URANS) equations applied to stably stratified turbulence (SST). SST is strongly affected by fine balances between forces and becomes more anisotropic in time for decaying cases. Moreover, there is a limited understanding of the physical phenomena described by some of the terms in the URANS equations. Rather than attempting to model each term separately, it is attractive to explore the capability of machine learning to model groups of terms, i.e., to directly model the force balances. We consider decaying SST which are homogeneous and stably stratified by a uniform density gradient, enabling dimensionality reduction. We consider two time-series ML models: Long Short-Term Memory (LSTM) and Neural Ordinary Differential Equation (NODE). Both models perform accurately and are numerically stable in a posteriori tests. Furthermore, we explore the data requirements of the ML models by extracting physically relevant timescales of the complex system. We find that the ratio of the timescales of the minimum information required by the ML models to accurately capture the dynamics of the SST corresponds to the Reynolds number of the flow. The current framework provides the backbone to explore the capability of such models to capture the dynamics of higher-dimensional complex SST flows.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 20 of its 70 references that are in the map. First posted on arXiv 24 Apr 2024.

Builds on

20 of 70 references.

References · 20

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2018Neural Ordinary Differential Equationscited by 3,733
  3. 2014Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modelingcited by 2,341
  4. 2019Temporal Fusion Transformers for Interpretable Multi-horizon Time Series Forecastingcited by 748
  5. 2016Recurrent Neural Networks for Multivariate Time Series with Missing Valuescited by 548
  6. 2019Machine Learning for Fluid Mechanicscited by 380
  7. 2019Recurrent Neural Networks for Time Series Forecasting: Current Status and Future Directionscited by 172
  8. 2018Deep learning to represent sub-grid processes in climate modelscited by 156
  9. 2022Stabilized Neural Ordinary Differential Equations for Long-Time Forecasting of Dynamical Systemscited by 50
  10. 2019Exploring Interpretable LSTM Neural Networks over Multi-Variable Datacited by 42
  11. 2018Deep Learning with Long Short-Term Memory for Time Series Predictioncited by 39
  12. 2021Constructing Neural Network-Based Models for Simulating Dynamical Systemscited by 29
8 more
  1. 2021Data-Driven Reduced-Order Modeling of Spatiotemporal Chaos with Neural Ordinary Differential Equationscited by 28
  2. 2019Explaining and Interpreting LSTMscited by 23
  3. 2020Assessment of unsteady flow predictions using hybrid deep learning based reduced order modelscited by 19
  4. 2022Data-driven control of spatiotemporal chaos with reduced-order neural ODE-based models and reinforcement learningcited by 16
  5. 2022Neural Ordinary Differential Equations for Nonlinear System Identificationcited by 14
  6. 2023Turbulence control in plane Couette flow using low-dimensional neural ODE-based models and deep reinforcement learningcited by 5
  7. 2022Learning Subgrid-scale Models with Neural Ordinary Differential Equationscited by 4
  8. 2021Neural ODE to model and prognose thermoacoustic instabilitycited by 3

Built on by

Not cited yet.