Data Driven Governing Equations Approximation Using Deep Neural Networks

Abstract

We present a numerical framework for approximating unknown governing equations using observation data and deep neural networks (DNN). In particular, we propose to use residual network (ResNet) as the basic building block for equation approximation. We demonstrate that the ResNet block can be considered as a one-step method that is exact in temporal integration. We then present two multi-step methods, recurrent ResNet (RT-ResNet) method and recursive ReNet (RS-ResNet) method. The RT-ResNet is a multi-step method on uniform time steps, whereas the RS-ResNet is an adaptive multi-step method using variable time steps. All three methods presented here are based on integral form of the underlying dynamical system. As a result, they do not require time derivative data for equation recovery and can cope with relatively coarsely distributed trajectory data. Several numerical examples are presented to demonstrate the performance of the methods.

References in corpus (5)

• Deep Learning in Neural Networks: An Overview
• Hidden Physics Models: Machine Learning of Nonlinear Partial Differential Equations
• Deep learning of dynamics and signal-noise decomposition with time-stepping constraints
• A machine learning approach for efficient uncertainty quantification using multiscale methods
• Numerical Aspects for Approximating Governing Equations Using Data

Cited by in corpus (77)

• PDE-Net 2.0: Learning PDEs from Data with A Numeric-Symbolic Hybrid Deep Network
• A Deep Collocation Method for the Bending Analysis of Kirchhoff Plate
• Efficient training of physics-informed neural networks via importance sampling
• Stiff-PINN: Physics-Informed Neural Network for Stiff Chemical Kinetics
• PhyCRNet: Physics-informed Convolutional-Recurrent Network for Solving Spatiotemporal PDEs
• Weak SINDy For Partial Differential Equations
• Deep learning of dynamics and signal-noise decomposition with time-stepping constraints
• A deep learning enabler for non-intrusive reduced order modeling of fluid flows
• Data-Driven Deep Learning of Partial Differential Equations in Modal Space
• Simulator-free Solution of High-Dimensional Stochastic Elliptic Partial Differential Equations using Deep Neural Networks
• Deep learning of free boundary and Stefan problems
• DLGA-PDE: Discovery of PDEs with incomplete candidate library via combination of deep learning and genetic algorithm
• A physics-informed operator regression framework for extracting data-driven continuum models
• Physics-Driven Regularization of Deep Neural Networks for Enhanced Engineering Design and Analysis
• Deep learning prediction of patient response time course from early data via neural-pharmacokinetic/pharmacodynamic modeling
• Deep-learning of Parametric Partial Differential Equations from Sparse and Noisy Data
• GFINNs: GENERIC Formalism Informed Neural Networks for Deterministic and Stochastic Dynamical Systems
• Efficient Deep Learning Techniques for Multiphase Flow Simulation in Heterogeneous Porous Media
• On generalized residue network for deep learning of unknown dynamical systems
• Using Deep Learning to Extend the Range of Air-Pollution Monitoring and Forecasting
• A neural network multigrid solver for the Navier-Stokes equations
• Accelerating hydrodynamic simulations of urban drainage systems with physics-guided machine learning
• Deep-learning based discovery of partial differential equations in integral form from sparse and noisy data
• Approaching epidemiological dynamics of COVID-19 with physics-informed neural networks
• PARC: Physics-Aware Recurrent Convolutional Neural Networks to Assimilate Meso-scale Reactive Mechanics of Energetic Materials
• Sparse dynamical system identification with simultaneous structural parameters and initial condition estimation
• Extended Dynamic Mode Decomposition for Inhomogeneous Problems
• A Perspective on Regression and Bayesian Approaches for System Identification of Pattern Formation Dynamics
• Physics-integrated hybrid framework for model form error identification in nonlinear dynamical systems
• WeakIdent: Weak formulation for Identifying Differential Equations using Narrow-fit and Trimming
• Structure-preserving Method for Reconstructing Unknown Hamiltonian Systems from Trajectory Data
• EM-like Learning Chaotic Dynamics from Noisy and Partial Observations
• NeuPDE: Neural Network Based Ordinary and Partial Differential Equations for Modeling Time-Dependent Data
• IDENT: Identifying Differential Equations with Numerical Time evolution
• Data-driven Prediction of General Hamiltonian Dynamics via Learning Exactly-Symplectic Maps
• Model Order Reduction based on Runge-Kutta Neural Network
• Hypersolvers: Toward Fast Continuous-Depth Models
• Multiple scattering simulation via physics-informed neural networks
• KiNet: A Deep Neural Network Representation of Chemical Kinetics
• System Identification Through Lipschitz Regularized Deep Neural Networks
• Reduced Order Modeling with Shallow Recurrent Decoder Networks
• Deep Euler method: solving ODEs by approximating the local truncation error of the Euler method
• Robust Modeling of Unknown Dynamical Systems via Ensemble Averaged Learning
• Learning and Meta-Learning of Stochastic Advection-Diffusion-Reaction Systems from Sparse Measurements
• Discovery of Dynamics Using Linear Multistep Methods
• Sparse Symplectically Integrated Neural Networks
• Recurrent Neural Networks for Partially Observed Dynamical Systems
• DeePN${}^2$: A deep learning-based non-Newtonian hydrodynamic model
• Bayesian Sparse learning with preconditioned stochastic gradient MCMC and its applications
• Neural Dynamics on Complex Networks
• Modeling Unknown Stochastic Dynamical System via Autoencoder
• Variational Deep Learning for the Identification and Reconstruction of Chaotic and Stochastic Dynamical Systems from Noisy and Partial Observations
• SPADE4: Sparsity and Delay Embedding based Forecasting of Epidemics
• Learning stochastic dynamical systems with neural networks mimicking the Euler-Maruyama scheme
• Multi-objective discovery of PDE systems using evolutionary approach
• A learned conservative semi-Lagrangian finite volume scheme for transport simulations
• Hierarchical deep learning-based adaptive time-stepping scheme for multiscale simulations
• Data-driven learning of non-autonomous systems
• Deep Neural Network Modeling of Unknown Partial Differential Equations in Nodal Space
• The Discovery of Dynamics via Linear Multistep Methods and Deep Learning: Error Estimation
• Discovery of Governing Equations with Recursive Deep Neural Networks
• Deep learning-based computational method for soft matter dynamics: Deep Onsager-Machlup method
• A Neural Network Ensemble Approach to System Identification
• Deep learning of parameterized equations with applications to uncertainty quantification
• Methods to Recover Unknown Processes in Partial Differential Equations Using Data
• Accuracy and Architecture Studies of Residual Neural Network solving Ordinary Differential Equations
• Clustered active-subspace based local Gaussian Process emulator for high-dimensional and complex computer models
• An artificial neural network approximation for Cauchy inverse problems
• Model-free inference of unseen attractors: Reconstructing phase space features from a single noisy trajectory using reservoir computing
• Critical Sampling for Robust Evolution Operator Learning of Unknown Dynamical Systems
• Discovering Phase Field Models from Image Data with the Pseudo-spectral Physics Informed Neural Networks
• Optimization with learning-informed differential equation constraints and its applications
• Generative Adversarial Network for Probabilistic Forecast of Random Dynamical System
• Toward real-time optimization through model reduction and model discrepancy sensitivities
• Data-informed Emulators for Multi-Physics Simulations
• Finite Difference Nets: A Deep Recurrent Framework for Solving Evolution PDEs
• Data-Driven Continuum Dynamics via Transport-Teleport Duality