Blending data and physics for reduced-order modeling of systems with spatiotemporal chaotic dynamics
Not on the map. Why?
Abstract (arXiv)
While data-driven techniques are powerful tools for reduced-order modeling of systems with chaotic dynamics, great potential remains for leveraging known physics (i.e. a full-order model (FOM)) to improve predictive capability. We develop a hybrid reduced order model (ROM), informed by both data and FOM, for evolving spatiotemporal chaotic dynamics on an invariant manifold whose coordinates are found using an autoencoder. This approach projects the vector field of the FOM onto the invariant manifold; then, this physics-derived vector field is either corrected using dynamic data, or used as a Bayesian prior that is updated with data. In both cases, the neural ordinary differential equation approach is used. We consider simulated data from the Kuramoto-Sivashinsky and complex Ginzburg-Landau equations. Relative to the data-only approach, for scenarios of abundant data, scarce data, and even an incorrect FOM (i.e. erroneous parameter values), the hybrid approach yields substantially improved time-series predictions.
Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 32 of its 61 references that are in the map. First posted on arXiv 21 Jul 2025.
Builds on
32 of 61 references.
References · 32
- 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,305
- 2018Neural Ordinary Differential Equationscited by 3,779
- 2020Fourier Neural Operator for Parametric Partial Differential Equationscited by 2,908
- 2019DeepONet: Learning nonlinear operators for identifying differential equations based on the universal approximation theorem of operatorscited by 2,018
- 2018Computational Optimal Transportcited by 780
- 2021Learning the solution operator of parametric partial differential equations with physics-informed DeepOnetscited by 540
- 2021Physics-Informed Neural Operator for Learning Partial Differential Equationscited by 527
- 2022Transformers in Time Series: A Surveycited by 497
- 2017Physics Informed Deep Learning (Part II): Data-driven Discovery of Nonlinear Partial Differential Equationscited by 161
- 2018Data-Driven Forecasting of High-Dimensional Chaotic Systems with Long Short-Term Memory Networkscited by 155
- 2019Backpropagation Algorithms and Reservoir Computing in Recurrent Neural Networks for the Forecasting of Complex Spatiotemporal Dynamicscited by 134
- 2020Multiscale Simulations of Complex Systems by Learning their Effective Dynamicscited by 86
20 more
- 2023β-Variational autoencoders and transformers for reduced-order modelling of fluid flowscited by 77
- 2018Hybrid Forecasting of Chaotic Processes: Using Machine Learning in Conjunction with a Knowledge-Based Modelcited by 57
- 2022Stabilized Neural Ordinary Differential Equations for Long-Time Forecasting of Dynamical Systemscited by 50
- 2020DPM: A Novel Training Method for Physics-Informed Neural Networks in Extrapolationcited by 45
- 2021Data-driven discovery of intrinsic dynamicscited by 45
- 2019Deep learning to discover and predict dynamics on an inertial manifoldcited by 43
- 2020Implicit Rank-Minimizing Autoencodercited by 35
- 2021Data-Driven Reduced-Order Modeling of Spatiotemporal Chaos with Neural Ordinary Differential Equationscited by 30
- 2023Model scale versus domain knowledge in statistical forecasting of chaotic systemscited by 27
- 2022Data-Driven Modeling and Prediction of Non-Linearizable Dynamics via Spectral Submanifoldscited by 25
- 2022Data-driven control of spatiotemporal chaos with reduced-order neural ODE-based models and reinforcement learningcited by 17
- 2023Autoencoders for discovering manifold dimension and coordinates in data from complex dynamical systemscited by 13
- 2021Symmetry reduction for deep reinforcement learning active control of chaotic spatiotemporal dynamicscited by 11
- 2022Data-driven low-dimensional dynamic model of Kolmogorov flowcited by 9
- 2022Deep learning delay coordinate dynamics for chaotic attractors from partial observable datacited by 8
- 2023Dynamics of a data-driven low-dimensional model of turbulent minimal Couette flowcited by 8
- 2023Nonlinear dimensionality reduction then and now: AIMs for dissipative PDEs in the ML eracited by 7
- 2023Turbulence control in plane Couette flow using low-dimensional neural ODE-based models and deep reinforcement learningcited by 5
- 2024On the relationship between Koopman operator approximations and neural ordinary differential equations for data-driven time-evolution predictionscited by 3
- 2023Building symmetries into data-driven manifold dynamics models for complex flows: application to two-dimensional Kolmogorov flowcited by 2
Built on by
Not cited yet.