PDE-Net 2.0: Learning PDEs from Data with A Numeric-Symbolic Hybrid Deep Network
arXiv:1812.04426 · doi:10.1016/j.jcp.2019.108925
Abstract
Partial differential equations (PDEs) are commonly derived based on empirical observations. However, recent advances of technology enable us to collect and store massive amount of data, which offers new opportunities for data-driven discovery of PDEs. In this paper, we propose a new deep neural network, called PDE-Net 2.0, to discover (time-dependent) PDEs from observed dynamic data with minor prior knowledge on the underlying mechanism that drives the dynamics. The design of PDE-Net 2.0 is based on our earlier work \cite{Long2018PDE} where the original version of PDE-Net was proposed. PDE-Net 2.0 is a combination of numerical approximation of differential operators by convolutions and a symbolic multi-layer neural network for model recovery. Comparing with existing approaches, PDE-Net 2.0 has the most flexibility and expressive power by learning both differential operators and the nonlinear response function of the underlying PDE model. Numerical experiments show that the PDE-Net 2.0 has the potential to uncover the hidden PDE of the observed dynamics, and predict the dynamical behavior for a relatively long time, even in a noisy environment.
16 pages, 15 figures. arXiv admin note: substantial text overlap with arXiv:1710.09668
References in corpus (1)
Cited by in corpus (128)
- PhyGeoNet: Physics-Informed Geometry-Adaptive Convolutional Neural Networks for Solving Parameterized Steady-State PDEs on Irregular Domain
- Weak SINDy For Partial Differential Equations
- Transfer learning based physics-informed neural networks for solving inverse problems in engineering structures under different loading scenarios
- A Physics-Guided Neural Network Framework for Elastic Plates: Comparison of Governing Equations-Based and Energy-Based Approaches
- DeepM&Mnet: Inferring the electroconvection multiphysics fields based on operator approximation by neural networks
- Integration of Neural Network-Based Symbolic Regression in Deep Learning for Scientific Discovery
- A Review on Deep Learning in Medical Image Reconstruction
- Super-resolution and denoising of fluid flow using physics-informed convolutional neural networks without high-resolution labels
- Data-Driven Deep Learning of Partial Differential Equations in Modal Space
- Deep Learning in Deterministic Computational Mechanics
- Physics-informed PointNet: A deep learning solver for steady-state incompressible flows and thermal fields on multiple sets of irregular geometries
- PFNN: A Penalty-Free Neural Network Method for Solving a Class of Second-Order Boundary-Value Problems on Complex Geometries
- DeepMoD: Deep learning for Model Discovery in noisy data
- Hybrid FEM-NN models: Combining artificial neural networks with the finite element method
- MgNet: A Unified Framework of Multigrid and Convolutional Neural Network
- DLGA-PDE: Discovery of PDEs with incomplete candidate library via combination of deep learning and genetic algorithm
- Assessment of unsteady flow predictions using hybrid deep learning based reduced order models
- A physics-informed operator regression framework for extracting data-driven continuum models
- Data-driven recovery of hidden physics in reduced order modeling of fluid flows
- Learning to Optimize: A Primer and A Benchmark
- Uniformly Accurate Machine Learning Based Hydrodynamic Models for Kinetic Equations
- An overview on deep learning-based approximation methods for partial differential equations
- Any equation is a forest: Symbolic genetic algorithm for discovering open-form partial differential equations (SGA-PDE)
- 2022 Review of Data-Driven Plasma Science
- Theory and implementation of inelastic Constitutive Artificial Neural Networks
- Deep learning prediction of patient response time course from early data via neural-pharmacokinetic/pharmacodynamic modeling
- Continuous-time system identification with neural networks: Model structures and fitting criteria
- Solving inverse-PDE problems with physics-aware neural networks
- Feature engineering and symbolic regression methods for detecting hidden physics from sparse sensors
- Multi-resolution partial differential equations preserved learning framework for spatiotemporal dynamics
- On some neural network architectures that can represent viscosity solutions of certain high dimensional Hamilton--Jacobi partial differential equations
- Deep-learning of Parametric Partial Differential Equations from Sparse and Noisy Data
- On generalized residue network for deep learning of unknown dynamical systems
- DySMHO: Data-Driven Discovery of Governing Equations for Dynamical Systems via Moving Horizon Optimization
- Deep learning neural networks for the third-order nonlinear Schrodinger equation: Solitons, breathers, and rogue waves
- Embedding Hard Physical Constraints in Neural Network Coarse-Graining of 3D Turbulence
- Latent-space time evolution of non-intrusive reduced-order models using Gaussian process emulation
- Deep-learning based discovery of partial differential equations in integral form from sparse and noisy data
- Extracting Interpretable Physical Parameters from Spatiotemporal Systems using Unsupervised Learning
- A Framework Based on Symbolic Regression Coupled with eXtended Physics-Informed Neural Networks for Gray-Box Learning of Equations of Motion from Data
- Short-term traffic prediction using physics-aware neural networks
- Differentiable Molecular Simulations for Control and Learning
- Physics-driven Learning of the Steady Navier-Stokes Equations using Deep Convolutional Neural Networks
- Sparse Identification of Truncation Errors
- PARC: Physics-Aware Recurrent Convolutional Neural Networks to Assimilate Meso-scale Reactive Mechanics of Energetic Materials
- FiniteNet: A Fully Convolutional LSTM Network Architecture for Time-Dependent Partial Differential Equations
- Physics-informed GANs for Coastal Flood Visualization
- Extended Dynamic Mode Decomposition for Inhomogeneous Problems
- A Method for Computing Inverse Parametric PDE Problems with Random-Weight Neural Networks
- Accelerating Physics-Informed Neural Network Training with Prior Dictionaries
- Physics-integrated hybrid framework for model form error identification in nonlinear dynamical systems
- Physics-informed generative neural network: an application to troposphere temperature prediction
- NeuPDE: Neural Network Based Ordinary and Partial Differential Equations for Modeling Time-Dependent Data
- Image Inversion and Uncertainty Quantification for Constitutive Laws of Pattern Formation
- Data-driven Identification of 2D Partial Differential Equations using extracted physical features
- Data-driven, multi-moment fluid modeling of Landau damping
- Neural network architectures using min-plus algebra for solving certain high dimensional optimal control problems and Hamilton-Jacobi PDEs
- Deep Ritz Method with Adaptive Quadrature for Linear Elasticity
- Data-driven modeling of Landau damping by physics-informed neural networks
- Parsimony-Enhanced Sparse Bayesian Learning for Robust Discovery of Partial Differential Equations
- PDE-GCN: Novel Architectures for Graph Neural Networks Motivated by Partial Differential Equations
- PDE-NetGen 1.0: from symbolic PDE representations of physical processes to trainable neural network representations
- Hypersolvers: Toward Fast Continuous-Depth Models
- Stability selection enables robust learning of partial differential equations from limited noisy data
- Deep Euler method: solving ODEs by approximating the local truncation error of the Euler method
- Learning Thermodynamically Stable and Galilean Invariant Partial Differential Equations for Non-equilibrium Flows
- Physics-informed Convolutional Neural Networks for Temperature Field Prediction of Heat Source Layout without Labeled Data
- Predicting Rigid Body Dynamics using Dual Quaternion Recurrent Neural Networks with Quaternion Attention
- Data-driven Discovery of Partial Differential Equations for Multiple-Physics Electromagnetic Problem
- Learning Generalized Quasi-Geostrophic Models Using Deep Neural Numerical Models
- Structure Preservation for the Deep Neural Network Multigrid Solver
- Discovery of Dynamics Using Linear Multistep Methods
- Computational model discovery with reinforcement learning
- Physics-Integrated Variational Autoencoders for Robust and Interpretable Generative Modeling
- Influence of initial conditions on data-driven model identification and information entropy for ideal mhd problems
- Physics-informed Deep Learning to Solve Three-dimensional Terzaghi Consolidation Equation: Forward and Inverse Problems
- A Spectral Approach for Learning Spatiotemporal Neural Differential Equations
- Automated differential equation solver based on the parametric approximation optimization
- Learning Differential Operators for Interpretable Time Series Modeling
- Weak Collocation Regression method: fast reveal hidden stochastic dynamics from high-dimensional aggregate data
- Neural Networks with Physics-Informed Architectures and Constraints for Dynamical Systems Modeling
- Overcoming the curse of dimensionality for some Hamilton--Jacobi partial differential equations via neural network architectures
- A Data Driven Method for Computing Quasipotentials
- Neural Ordinary Differential Equations for Data-Driven Reduced Order Modeling of Environmental Hydrodynamics
- Machine Learning of Partial Differential Equations from Noise Data
- Meta-Auto-Decoder: A Meta-Learning Based Reduced Order Model for Solving Parametric Partial Differential Equations
- Learning to Discretize: Solving 1D Scalar Conservation Laws via Deep Reinforcement Learning
- Data-driven learning of non-autonomous systems
- Data-Driven Constitutive Relation Reveals Scaling Law for Hydrodynamic Transport Coefficients
- Frame-independent vector-cloud neural network for nonlocal constitutive modeling on arbitrary grids
- Physics-Guided Discovery of Highly Nonlinear Parametric Partial Differential Equations
- The Discovery of Dynamics via Linear Multistep Methods and Deep Learning: Error Estimation
- Adaptive parameters identification for nonlinear dynamics using deep permutation invariant networks
- A Deep Learning Approach for Predicting Spatiotemporal Dynamics From Sparsely Observed Data
- A Neural Solver for Variational Problems on CAD Geometries with Application to Electric Machine Simulation
- Robust discovery of partial differential equations in complex situations
- DynaBench: A benchmark dataset for learning dynamical systems from low-resolution data
- Learning of discrete models of variational PDEs from data
- Translating Diffusion, Wavelets, and Regularisation into Residual Networks
- Latent assimilation with implicit neural representations for unknown dynamics
- RODE-Net: Learning Ordinary Differential Equations with Randomness from Data
- STENCIL-NET: Data-driven solution-adaptive discretization of partial differential equations
- Uncovering Closed-form Governing Equations of Nonlinear Dynamics from Videos
- CTSR: Cartesian tensor-based sparse regression for data-driven discovery of high-dimensional invariant governing equations
- Partial Differential Equations is All You Need for Generating Neural Architectures -- A Theory for Physical Artificial Intelligence Systems
- Learnable-Differentiable Finite Volume Solver for Accelerated Simulation of Flows
- Physics-informed AI and ML-based sparse system identification algorithm for discovery of PDE's representing nonlinear dynamic systems
- Constrained or Unconstrained? Neural-Network-Based Equation Discovery from Data
- Symbolically Solving Partial Differential Equations using Deep Learning
- TIME: A Transparent, Interpretable, Model-Adaptive and Explainable Neural Network for Dynamic Physical Processes
- Methods to Recover Unknown Processes in Partial Differential Equations Using Data
- Deep Domain Decomposition Method: Elliptic Problems
- Machine learning and serving of discrete field theories -- when artificial intelligence meets the discrete universe
- Deep learning of parameterized equations with applications to uncertainty quantification
- Physics-informed Spline Learning for Nonlinear Dynamics Discovery
- A Natural Deep Ritz Method for Essential Boundary Value Problems
- Data-Driven Theory-guided Learning of Partial Differential Equations using SimultaNeous Basis Function Approximation and Parameter Estimation (SNAPE)
- CONFIDE: Contextual Finite Differences Modelling of PDEs
- Critical Sampling for Robust Evolution Operator Learning of Unknown Dynamical Systems
- Hyperparameter Optimization in the Estimation of PDE and Delay-PDE models from data
- Enhancing Human-Machine Teaming for Medical Prognosis Through Neural Ordinary Differential Equations (NODEs)
- An artificial neural network approximation for Cauchy inverse problems
- Multiscale and Nonlocal Learning for PDEs using Densely Connected RNNs
- Deep Domain Decomposition Method for Solving the Variational Inequality Problems
- Taylor saves for later: disentanglement for video prediction using Taylor representation
- UniSymNet: A Unified Symbolic Network Guided by Transformer
- SlotPi: Physics-informed Object-centric Reasoning Models
- The Machine Learning Approach to Moment Closure Relations for Plasma: A Review