A Model-Constrained Tangent Slope Learning Approach for Dynamical Systems
arXiv:2208.04995 · doi:10.1080/10618562.2022.2146677
Abstract
Real-time accurate solutions of large-scale complex dynamical systems are in critical need for control, optimization, uncertainty quantification, and decision-making in practical engineering and science applications, especially digital twin applications. This paper contributes in this direction a model-constrained tangent slope learning (mcTangent) approach. At the heart of mcTangent is the synergy of several desirable strategies: i) a tangent slope learning to take advantage of the neural network speed and the time-accurate nature of the method of lines; ii) a model-constrained approach to encode the neural network tangent slope with the underlying governing equations; iii) sequential learning strategies to promote long-time stability and accuracy; and iv) data randomization approach to implicitly enforce the smoothness of the neural network tangent slope and its likeliness to the truth tangent slope up second order derivatives in order to further enhance the stability and accuracy of mcTangent solutions. Rigorous results are provided to analyze and justify the proposed approach. Several numerical results for the transport equation, viscous Burgers equation, and Navier-Stokes equation are presented to study and demonstrate the robustness and long-time accuracy of the proposed mcTangent learning approach.
References in corpus (26)
- Discovering governing equations from data: Sparse identification of nonlinear dynamical systems
- DeepXDE: A deep learning library for solving differential equations
- Hidden Physics Models: Machine Learning of Nonlinear Partial Differential Equations
- Fourier Neural Operator for Parametric Partial Differential Equations
- Machine learning accelerated computational fluid dynamics
- Physics Informed Deep Learning (Part I): Data-driven Solutions of Nonlinear Partial Differential Equations
- Physics-informed neural networks for inverse problems in nano-optics and metamaterials
- Machine Learning of Linear Differential Equations using Gaussian Processes
- Deep neural networks for the evaluation and design of photonic devices
- Deep UQ: Learning deep neural network surrogate models for high dimensional uncertainty quantification
- Learning to Simulate Complex Physics with Graph Networks
- Adversarial Uncertainty Quantification in Physics-Informed Neural Networks
- Deep Learning for Time Series Forecasting: Tutorial and Literature Survey
- Perspectives on Machine Learning-augmented Reynolds-averaged and Large Eddy Simulation Models of Turbulence
- Graph networks as learnable physics engines for inference and control
- Deep Learning for Physical Processes: Incorporating Prior Scientific Knowledge
- Deep Fluids: A Generative Network for Parameterized Fluid Simulations
- Long-time predictive modeling of nonlinear dynamical systems using neural networks
- Active learning of deep surrogates for PDEs: Application to metasurface design
- Learned discretizations for passive scalar advection in a 2-D turbulent flow
- A neural network multigrid solver for the Navier-Stokes equations
- Learning Large-scale Subsurface Simulations with a Hybrid Graph Network Simulator
- Model Order Reduction based on Runge-Kutta Neural Network
- Using Machine Learning to Augment Coarse-Grid Computational Fluid Dynamics Simulations
- Deep, Skinny Neural Networks are not Universal Approximators
- A Unified and Constructive Framework for the Universality of Neural Networks