• Corpus ID: 244709497

Learning Low-Dimensional Quadratic-Embeddings of High-Fidelity Nonlinear Dynamics using Deep Learning

  title={Learning Low-Dimensional Quadratic-Embeddings of High-Fidelity Nonlinear Dynamics using Deep Learning},
  author={Pawan Goyal and Peter Benner},
Learning dynamical models from data plays a vital role in engineering design, optimization, and predictions. Building models describing dynamics of complex processes (e.g., weather dynamics, or reactive flows) using empirical knowledge or first principles are onerous or infeasible. Moreover, these models are high-dimensional but spatially correlated. It is, however, observed that the dynamics of high-fidelity models often evolve in low-dimensional manifolds. Furthermore, it is also known that… 
1 Citations

Figures from this paper

Operator inference for non-intrusive model reduction with nonlinear manifolds
This paper proposes a novel approach for learning a data-driven quadratic manifold from high-dimensional data, then employing the quadRatic manifold to derive efficient physics-based reduced-order models, using a polynomial mapping between high- dimensional states and a low-dimensional embedding.


Deep learning for universal linear embeddings of nonlinear dynamics
It is often advantageous to transform a strongly nonlinear system into a linear one in order to simplify its analysis for prediction and control, so the authors combine dynamical systems with deep learning to identify these hard-to-find transformations.
Deep convolutional recurrent autoencoders for learning low-dimensional feature dynamics of fluid systems
This work proposes a deep learning-based strategy for nonlinear model reduction that is inspired by projection-based model reduction where the idea is to identify some optimal low-dimensional representation and evolve it in time.
Model reduction of dynamical systems on nonlinear manifolds using deep convolutional autoencoders
Learning Deep Neural Network Representations for Koopman Operators of Nonlinear Dynamical Systems
This paper introduces a computational framework for learning Koopman operators of nonlinear dynamical systems using deep learning and shows that this novel method automatically selects efficient deep dictionaries, requiring much lower dimensional dictionaries while outperforming state-of-the-art methods.
Learning Dynamics from Noisy Measurements using Deep Learning with a Runge-Kutta Constraint
The proposed approach provides a promising methodology to learn dynamic models, where the first-principle understanding remains opaque, by learning a neural network that implicitly represents the data and an additional network that models the vector fields of the dependent variables.
LQResNet: A Deep Neural Network Architecture for Learning Dynamic Processes
This work suggests combining the operator inference with certain deep neural network approaches to infer the unknown nonlinear dynamics of the system and demonstrates that the proposed methodology accomplishes the desired tasks for dynamics processes encountered in neural dynamics and the glycolytic oscillator.
Operator Inference and Physics-Informed Learning of Low-Dimensional Models for Incompressible Flows
This work utilizes the intrinsic structure of the Navier-Stokes equations for incompressible flows and shows that learning dynamics of the velocity and pressure can be decoupled, thus leading to an efficient operator inference approach for learning the underlying dynamics of incompressable flows.
Discovering governing equations from data by sparse identification of nonlinear dynamical systems
This work develops a novel framework to discover governing equations underlying a dynamical system simply from data measurements, leveraging advances in sparsity techniques and machine learning and using sparse regression to determine the fewest terms in the dynamic governing equations required to accurately represent the data.