Physics Informed Deep Learning (Part I): Data-driven Solutions of Nonlinear Partial Differential Equations

Abstract

We introduce physics informed neural networks -- neural networks that are trained to solve supervised learning tasks while respecting any given law of physics described by general nonlinear partial differential equations. In this two part treatise, we present our developments in the context of solving two main classes of problems: data-driven solution and data-driven discovery of partial differential equations. Depending on the nature and arrangement of the available data, we devise two distinct classes of algorithms, namely continuous time and discrete time models. The resulting neural networks form a new class of data-efficient universal function approximators that naturally encode any underlying physical laws as prior information. In this first part, we demonstrate how these networks can be used to infer solutions to partial differential equations, and obtain physics-informed surrogate models that are fully differentiable with respect to all input coordinates and free parameters.

References in corpus (2)

• Hidden Physics Models: Machine Learning of Nonlinear Partial Differential Equations
• Numerical Gaussian Processes for Time-dependent and Non-linear Partial Differential Equations

Cited by in corpus (234)

• The role of artificial intelligence in achieving the Sustainable Development Goals
• An Energy Approach to the Solution of Partial Differential Equations in Computational Mechanics via Machine Learning: Concepts, Implementation and Applications
• Turbulence Modeling in the Age of Data
• NSFnets (Navier-Stokes Flow nets): Physics-informed neural networks for the incompressible Navier-Stokes equations
• Physics-Constrained Deep Learning for High-dimensional Surrogate Modeling and Uncertainty Quantification without Labeled Data
• Explainable Machine Learning for Scientific Insights and Discoveries
• Data-driven discovery of coordinates and governing equations
• Informed Machine Learning -- A Taxonomy and Survey of Integrating Knowledge into Learning Systems
• Machine learning in cardiovascular flows modeling: Predicting arterial blood pressure from non-invasive 4D flow MRI data using physics-informed neural networks
• Integrating Machine Learning and Multiscale Modeling: Perspectives, Challenges, and Opportunities in the Biological, Biomedical, and Behavioral Sciences
• PDE-Net 2.0: Learning PDEs from Data with A Numeric-Symbolic Hybrid Deep Network
• Quantifying total uncertainty in physics-informed neural networks for solving forward and inverse stochastic problems
• A Deep Collocation Method for the Bending Analysis of Kirchhoff Plate
• A Physics-Informed Machine Learning Approach for Solving Heat Transfer Equation in Advanced Manufacturing and Engineering Applications
• Enforcing Analytic Constraints in Neural-Networks Emulating Physical Systems
• Weak Adversarial Networks for High-dimensional Partial Differential Equations
• Adversarial Uncertainty Quantification in Physics-Informed Neural Networks
• Deep Hidden Physics Models: Deep Learning of Nonlinear Partial Differential Equations
• The Challenge of Machine Learning in Space Weather Nowcasting and Forecasting
• Machine Learning in Aerodynamic Shape Optimization
• Efficient training of physics-informed neural networks via importance sampling
• Data-assisted reduced-order modeling of extreme events in complex dynamical systems
• DeepM&Mnet: Inferring the electroconvection multiphysics fields based on operator approximation by neural networks
• Deep learning of dynamics and signal-noise decomposition with time-stepping constraints
• 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
• Data-driven discovery of PDEs in complex datasets
• Solving Fokker-Planck equation using deep learning
• Probabilistic neural networks for fluid flow surrogate modeling and data recovery
• Recent Advances and Applications of Machine Learning in Experimental Solid Mechanics: A Review
• Multistep Neural Networks for Data-driven Discovery of Nonlinear Dynamical Systems
• D3M: A deep domain decomposition method for partial differential equations
• DeepMoD: Deep learning for Model Discovery in noisy data
• Applications of deep learning in traffic congestion detection, prediction and alleviation: A survey
• Time-series learning of latent-space dynamics for reduced-order model closure
• DeePore: a deep learning workflow for rapid and comprehensive characterization of porous materials
• Physics-constrained, low-dimensional models for MHD: First-principles and data-driven approaches
• An overview on deep learning-based approximation methods for partial differential equations
• A Physics-Constrained Data-Driven Approach Based on Locally Convex Reconstruction for Noisy Database
• Hidden Fluid Mechanics: A Navier-Stokes Informed Deep Learning Framework for Assimilating Flow Visualization Data
• Deep Lagrangian Networks: Using Physics as Model Prior for Deep Learning
• Incorporating Symmetry into Deep Dynamics Models for Improved Generalization
• Explore missing flow dynamics by physics-informed deep learning: the parameterised governing systems
• Solving inverse-PDE problems with physics-aware neural networks
• Neural-net-induced Gaussian process regression for function approximation and PDE solution
• Integrated Finite Element Neural Network (I-FENN) for non-local continuum damage mechanics
• Synchronization to big-data: nudging the Navier-Stokes equations for data assimilation of turbulent flows
• Learning Parameters and Constitutive Relationships with Physics Informed Deep Neural Networks
• Long-term predictions of turbulence by implicit U-Net enhanced Fourier neural operator
• Multifidelity Modeling for Physics-Informed Neural Networks (PINNs)
• Physics-informed neural networks (PINNs) for fluid mechanics: A review
• Physics-informed Autoencoders for Lyapunov-stable Fluid Flow Prediction
• On some neural network architectures that can represent viscosity solutions of certain high dimensional Hamilton--Jacobi partial differential equations
• Data driven approximation of parametrized PDEs by Reduced Basis and Neural Networks
• Latent Space Data Assimilation by using Deep Learning
• Active Training of Physics-Informed Neural Networks to Aggregate and Interpolate Parametric Solutions to the Navier-Stokes Equations
• Physics-informed data based neural networks for two-dimensional turbulence
• PI-VAE: Physics-Informed Variational Auto-Encoder for stochastic differential equations
• Poisson CNN: Convolutional neural networks for the solution of the Poisson equation on a Cartesian mesh
• Efficient Deep Learning Techniques for Multiphase Flow Simulation in Heterogeneous Porous Media
• Algorithmically-Consistent Deep Learning Frameworks for Structural Topology Optimization
• HiDeNN-PGD: reduced-order hierarchical deep learning neural networks
• Physics-Informed Generative Adversarial Networks for Stochastic Differential Equations
• Physics-informed deep generative models
• On generalized residue network for deep learning of unknown dynamical systems
• Deep Learning Ensemble for Real-time Gravitational Wave Detection of Spinning Binary Black Hole Mergers
• Port-Hamiltonian Neural Networks for Learning Explicit Time-Dependent Dynamical Systems
• Adaptive deep density approximation for Fokker-Planck equations
• A Physics-Informed Neural Network approach for compartmental epidemiological models
• Machine Learning for Physics-Informed Generation of Dispersed Multiphase Flow Using Generative Adversarial Networks
• Applications of physics informed neural operators
• Turbulence Enrichment using Physics-informed Generative Adversarial Networks
• Differentiable Physics-informed Graph Networks
• Neural Network Forecast of the Sunspot Butterfly Diagram
• Bridging scales in a multiscale pattern-forming system
• Bayesian Physics Informed Neural Networks for Data Assimilation and Spatio-Temporal Modelling of Wildfires
• On quadrature rules for solving Partial Differential Equations using Neural Networks
• A Helmholtz equation solver using unsupervised learning: Application to transcranial ultrasound
• A Discussion on Solving Partial Differential Equations using Neural Networks
• Trend to Equilibrium for the Kinetic Fokker-Planck Equation via the Neural Network Approach
• A physics-aware, probabilistic machine learning framework for coarse-graining high-dimensional systems in the Small Data regime
• Implicit Geometric Regularization for Learning Shapes
• Interpreting neural network models of residual scalar flux
• What machine learning can do for computational solid mechanics
• MINN: Learning the dynamics of differential-algebraic equations and application to battery modeling
• A comparative study of physics-informed neural network models for learning unknown dynamics and constitutive relations
• Blending Diverse Physical Priors with Neural Networks
• Comparing recurrent and convolutional neural networks for predicting wave propagation
• Incorporating physical constraints in a deep probabilistic machine learning framework for coarse-graining dynamical systems
• Data-driven discovery of free-form governing differential equations
• BubbleNet: Inferring micro-bubble dynamics with semi-physics-informed deep learning
• The Neural Network Approach to Inverse Problems in Differential Equations
• Meta-learning Pseudo-differential Operators with Deep Neural Networks
• Solving Bayesian Inverse Problems via Variational Autoencoders
• On the Art and Science of Machine Learning Explanations
• Predicting Critical Transitions in Multiscale Dynamical Systems Using Reservoir Computing
• A comprehensive and fair comparison of two neural operators (with practical extensions) based on FAIR data
• Unsupervised Deep Learning Algorithm for PDE-based Forward and Inverse Problems
• Accelerating Physics-Informed Neural Network Training with Prior Dictionaries
• A probabilistic generative model for semi-supervised training of coarse-grained surrogates and enforcing physical constraints through virtual observables
• Artifact Reduction in 3D and 4D Cone-beam Computed Tomography Images with Deep Learning -- A Review
• Physics-Informed Machine Learning for Grade Prediction in Froth Flotation
• Physics Informed Deep Learning for Transport in Porous Media. Buckley Leverett Problem
• NeuPDE: Neural Network Based Ordinary and Partial Differential Equations for Modeling Time-Dependent Data
• Applications of machine learning in gravitational wave research with current interferometric detectors
• IDENT: Identifying Differential Equations with Numerical Time evolution
• Magnetohydrodynamics with Physics Informed Neural Operators
• An unsupervised learning approach to solving heat equations on chip based on Auto Encoder and Image Gradient
• Encoding Invariances in Deep Generative Models
• A Combined Data-driven and Physics-driven Method for Steady Heat Conduction Prediction using Deep Convolutional Neural Networks
• Machines Learn to Infer Stellar Parameters Just by Looking at a Large Number of Spectra
• Linearly Constrained Neural Networks
• Learning in Modal Space: Solving Time-Dependent Stochastic PDEs Using Physics-Informed Neural Networks
• Highly-scalable, physics-informed GANs for learning solutions of stochastic PDEs
• Deep Hierarchical Super Resolution for Scientific Data
• Accelerating PDE-constrained Inverse Solutions with Deep Learning and Reduced Order Models
• Deep Learning of Conjugate Mappings
• Beltrami Flow and Neural Diffusion on Graphs
• Physics-Informed Neural Networks for Securing Water Distribution Systems
• Neural Implicit Surface Evolution
• Neural representation of a time optimal, constant acceleration rendezvous
• POD-DL-ROM: enhancing deep learning-based reduced order models for nonlinear parametrized PDEs by proper orthogonal decomposition
• Elvet -- a neural network-based differential equation and variational problem solver
• A hybrid inference system for improved curvature estimation in the level-set method using machine learning
• Modelling parametric uncertainty in PDEs models via Physics-Informed Neural Networks
• Accelerating High-Strain Continuum-Scale Brittle Fracture Simulations with Machine Learning
• Physics-informed attention-based neural network for solving non-linear partial differential equations
• Active Image Synthesis for Efficient Labeling
• Deep learning for full-field ultrasonic characterization
• Explicit physics-informed neural networks for non-linear upscaling closure: the case of transport in tissues
• Parareal with a physics-informed neural network as coarse propagator
• Self-Adaptive Physics-Informed Quantum Machine Learning for Solving Differential Equations
• Data-driven Discovery of Partial Differential Equations for Multiple-Physics Electromagnetic Problem
• Physics-Aware Neural Implicit Solvers for multiscale, parametric PDEs with applications in heterogeneous media
• Modeling Stochastic Microscopic Traffic Behaviors: a Physics Regularized Gaussian Process Approach
• Temporal Normalizing Flows
• Bridging the Gap: Machine Learning to Resolve Improperly Modeled Dynamics
• Computational model discovery with reinforcement learning
• Machine Discovery of Partial Differential Equations from Spatiotemporal Data
• Analyzing Koopman approaches to physics-informed machine learning for long-term sea-surface temperature forecasting
• Cell-average based neural network method for hyperbolic and parabolic partial differential equations
• Value Iteration in Continuous Actions, States and Time
• Learning continuous-time PDEs from sparse data with graph neural networks
• SubTSBR to tackle high noise and outliers for data-driven discovery of differential equations
• Efficient time stepping for numerical integration using reinforcement learning
• Meta-MgNet: Meta Multigrid Networks for Solving Parameterized Partial Differential Equations
• MaxwellNet: Physics-driven deep neural network training based on Maxwell's equations
• Physics-informed State-space Neural Networks for Transport Phenomena
• Bayesian Sparse learning with preconditioned stochastic gradient MCMC and its applications
• Deep Multi-Fidelity Active Learning of High-dimensional Outputs
• Physics-Informed Neural Networks for Transonic Flows around an Airfoil
• Physics-informed Neural Networks approach to solve the Blasius function
• Analytical derivatives of Neural Networks
• Sparsely constrained neural networks for model discovery of PDEs
• Multi-Constitutive Neural Network for Large Deformation Poromechanics Problem
• Deep Learning Convective Flow Using Conditional Generative Adversarial Networks
• Enforcing exact physics in scientific machine learning: a data-driven exterior calculus on graphs
• A deep surrogate approach to efficient Bayesian inversion in PDE and integral equation models
• Overcoming the curse of dimensionality for some Hamilton--Jacobi partial differential equations via neural network architectures
• Solving Differential Equation with Constrained Multilayer Feedforward Network
• Uncertainty quantification in a mechanical submodel driven by a Wasserstein-GAN
• Learning Potentials of Quantum Systems using Deep Neural Networks
• Physics Informed Deep Learning for Flow and Transport in Porous Media
• Prediction of Ultrasonic Guided Wave Propagation in Solid-fluid and their Interface under Uncertainty using Machine Learning
• Machine Learning of Partial Differential Equations from Noise Data
• Fatigue-PINN: Physics-Informed Fatigue-Driven Motion Modulation and Synthesis
• Using neural networks to solve the 2D Poisson equation for electric field computation in plasma fluid simulations
• Neural Network Model for Structure Factor of Polymer Systems
• Potential Flow Generator with $L_2$ Optimal Transport Regularity for Generative Models
• Parametric Complexity Bounds for Approximating PDEs with Neural Networks
• Domain-informed neural networks for interaction localization within astroparticle experiments
• FD-Net with Auxiliary Time Steps: Fast Prediction of PDEs using Hessian-Free Trust-Region Methods
• Sobolev neural network with residual weighting as a surrogate in linear and non-linear mechanics
• Meta-Learning Dynamics Forecasting Using Task Inference
• About optimal loss function for training physics-informed neural networks under respecting causality
• Learning to Discretize: Solving 1D Scalar Conservation Laws via Deep Reinforcement Learning
• Residual U-Net for accurate and efficient prediction of hemodynamics in two-dimensional asymmetric stenosis
• Physics-Informed Machine Learning with Conditional Karhunen-Loève Expansions
• An Iterative Scientific Machine Learning Approach for Discovery of Theories Underlying Physical Phenomena
• Informative Neural Ensemble Kalman Learning
• Deep Learning for Mean Field Games with non-separable Hamiltonians
• Neural Network Analysis of S-Star Dynamics: Implications for Modified Gravity
• An Extensible Benchmark Suite for Learning to Simulate Physical Systems
• Deep Neural Network Modeling of Unknown Partial Differential Equations in Nodal Space
• Thermodynamic Consistent Neural Networks for Learning Material Interfacial Mechanics
• The Newton Scheme for Deep Learning
• SISMIK for brain MRI: Deep-learning-based motion estimation and model-based motion correction in k-space
• A Model-Constrained Tangent Slope Learning Approach for Dynamical Systems
• Physics-Informed Learning for High Impedance Faults Detection
• Physics Enhanced Artificial Intelligence
• STENCIL-NET: Data-driven solution-adaptive discretization of partial differential equations
• Empirical Models for Multidimensional Regression of Fission Systems
• Bayesian Hidden Physics Models: Uncertainty Quantification for Discovery of Nonlinear Partial Differential Operators from Data
• Variational Autoencoding of PDE Inverse Problems
• Approximation and Generalization Capacities of Parametrized Quantum Circuits for Functions in Sobolev Spaces
• Adaptive Physics-Informed Neural Networks for Markov-Chain Monte Carlo
• Residual fourier neural operator for thermochemical curing of composites
• Modified physics-informed neural network method based on the conservation law constraint and its prediction of optical solitons
• Uncertainty Quantification of Locally Nonlinear Dynamical Systems using Neural Networks
• Error bounds for PDE-regularized learning
• Parameter identification for a damage model using a physics informed neural network
• Estimating Traffic Speeds using Probe Data: A Deep Neural Network Approach
• Batch Multi-Fidelity Bayesian Optimization with Deep Auto-Regressive Networks
• Deep learning based inverse method for layout design
• Investigation of Numerical Diffusion in Aerodynamic Flow Simulations with Physics Informed Neural Networks
• Assessment of End-to-End and Sequential Data-driven Learning of Fluid Flows
• Understanding ML driven HPC: Applications and Infrastructure
• Finite Difference Neural Networks: Fast Prediction of Partial Differential Equations
• Deep Orthogonal Decompositions for Convective Nowcasting
• Neural Stream Functions
• Learning the geometry of wave-based imaging
• A Two-Stage Training Method for Modeling Constrained Systems With Neural Networks
• Rodent: Relevance determination in differential equations
• Multiscale and Nonlocal Learning for PDEs using Densely Connected RNNs
• Neural Symplectic Integrator with Hamiltonian Inductive Bias for the Gravitational $N$-body Problem
• Theory-training deep neural networks for an alloy solidification benchmark problem
• Discovery of Quasi-Integrable Equations from traveling-wave data using the Physics-Informed Neural Networks
• Model discovery in the sparse sampling regime
• Algebraically-Informed Deep Networks (AIDN): A Deep Learning Approach to Represent Algebraic Structures
• Identification of state functions by physically-guided neural networks with physically-meaningful internal layers
• Fully differentiable model discovery
• MFPC-Net: Multi-fidelity Physics-Constrained Neural Process
• Numerical Approximation in CFD Problems Using Physics Informed Machine Learning
• Data-Driven Shadowgraph Simulation of a 3D Object
• Towards Comparative Physical Interpretation of Spatial Variability Aware Neural Networks: A Summary of Results
• Physics Informed Convex Artificial Neural Networks (PICANNs) for Optimal Transport based Density Estimation
• Physics-Augmented Learning: A New Paradigm Beyond Physics-Informed Learning
• Learning Full Configuration Interaction Electron Correlations with Deep Learning
• Invertible Surrogate Models: Joint surrogate modelling and reconstruction of Laser-Wakefield Acceleration by invertible neural networks
• Lyapunov-Net: A Deep Neural Network Architecture for Lyapunov Function Approximation
• Physics-Aware Downsampling with Deep Learning for Scalable Flood Modeling
• Recurrent convolutional neural network for the surrogate modeling of subsurface flow simulation
• Object classification in analytical chemistry via data-driven discovery of partial differential equations
• Physics-based polynomial neural networks for one-shot learning of dynamical systems from one or a few samples