Deep Hidden Physics Models: Deep Learning of Nonlinear Partial Differential Equations

Abstract

A long-standing problem at the interface of artificial intelligence and applied mathematics is to devise an algorithm capable of achieving human level or even superhuman proficiency in transforming observed data into predictive mathematical models of the physical world. In the current era of abundance of data and advanced machine learning capabilities, the natural question arises: How can we automatically uncover the underlying laws of physics from high-dimensional data generated from experiments? In this work, we put forth a deep learning approach for discovering nonlinear partial differential equations from scattered and potentially noisy observations in space and time. Specifically, we approximate the unknown solution as well as the nonlinear dynamics by two deep neural networks. The first network acts as a prior on the unknown solution and essentially enables us to avoid numerical differentiations which are inherently ill-conditioned and unstable. The second network represents the nonlinear dynamics and helps us distill the mechanisms that govern the evolution of a given spatiotemporal data-set. We test the effectiveness of our approach for several benchmark problems spanning a number of scientific domains and demonstrate how the proposed framework can help us accurately learn the underlying dynamics and forecast future states of the system. In particular, we study the Burgers', Korteweg-de Vries (KdV), Kuramoto-Sivashinsky, nonlinear Schrödinger, and Navier-Stokes equations.

References in corpus (4)

• Hidden Physics Models: Machine Learning of Nonlinear Partial Differential Equations
• Physics Informed Deep Learning (Part I): Data-driven Solutions of Nonlinear Partial Differential Equations
• Multistep Neural Networks for Data-driven Discovery of Nonlinear Dynamical Systems
• Numerical Gaussian Processes for Time-dependent and Non-linear Partial Differential Equations

Cited by in corpus (96)

• An Energy Approach to the Solution of Partial Differential Equations in Computational Mechanics via Machine Learning: Concepts, Implementation and Applications
• Physics-Informed Multi-LSTM Networks for Metamodeling of Nonlinear Structures
• 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
• Adversarial Uncertainty Quantification in Physics-Informed Neural Networks
• SciANN: A Keras/Tensorflow wrapper for scientific computations and physics-informed deep learning using artificial neural networks
• CAN-PINN: A Fast Physics-Informed Neural Network Based on Coupled-Automatic-Numerical Differentiation Method
• Modeling the Dynamics of PDE Systems with Physics-Constrained Deep Auto-Regressive Networks
• Efficient training of physics-informed neural networks via importance sampling
• Data Driven Governing Equations Approximation Using Deep Neural Networks
• PhyCRNet: Physics-informed Convolutional-Recurrent Network for Solving Spatiotemporal PDEs
• A Physics-Informed Deep Learning Paradigm for Car-Following Models
• Deep learning of dynamics and signal-noise decomposition with time-stepping constraints
• A two-stage physics-informed neural network method based on conserved quantities and applications in localized wave solutions
• Biologically-informed neural networks guide mechanistic modeling from sparse experimental data
• Data-Driven Deep Learning of Partial Differential Equations in Modal Space
• Multi-Objective Loss Balancing for Physics-Informed Deep Learning
• Algorithms for Solving High Dimensional PDEs: From Nonlinear Monte Carlo to Machine Learning
• Data-driven discovery of PDEs in complex datasets
• Deep splitting method for parabolic PDEs
• Physics-informed Neural Networks for Solving Nonlinear Diffusivity and Biot's equations
• DeepMoD: Deep learning for Model Discovery in noisy data
• Hybrid FEM-NN models: Combining artificial neural networks with the finite element method
• Maximizing information from chemical engineering data sets: Applications to machine learning
• Stochastic analysis of heterogeneous porous material with modified neural architecture search (NAS) based physics-informed neural networks using transfer learning
• Physics and Equality Constrained Artificial Neural Networks: Application to Forward and Inverse Problems with Multi-fidelity Data Fusion
• Learning in Sinusoidal Spaces with Physics-Informed Neural Networks
• A deep learning energy-based method for classical elastoplasticity
• Learning Variational Data Assimilation Models and Solvers
• Physics-Driven Regularization of Deep Neural Networks for Enhanced Engineering Design and Analysis
• An overview on deep learning-based approximation methods for partial differential equations
• Classification of chaotic time series with deep learning
• Solving forward and inverse problems of the logarithmic nonlinear Schrodinger equation with PT-symmetric harmonic potential via deep learning
• Variational Onsager Neural Networks (VONNs): A thermodynamics-based variational learning strategy for non-equilibrium PDEs
• Pre-training strategy for solving evolution equations based on physics-informed neural networks
• Deep-learning of Parametric Partial Differential Equations from Sparse and Noisy Data
• Physics-Informed Deep Learning For Traffic State Estimation: A Survey and the Outlook
• A Derivative-Free Method for Solving Elliptic Partial Differential Equations with Deep Neural Networks
• On spike-and-slab priors for Bayesian equation discovery of nonlinear dynamical systems via sparse linear regression
• Physics-informed deep generative models
• Deep energy method in topology optimization applications
• On generalized residue network for deep learning of unknown dynamical systems
• Robust and optimal sparse regression for nonlinear PDE models
• Deep Learning Methods for Partial Differential Equations and Related Parameter Identification Problems
• A feed-forward neural network as a nonlinear dynamics integrator for supercontinuum generation
• Multi-Output Physics-Informed Neural Networks for Forward and Inverse PDE Problems with Uncertainties
• Learning Dynamical Systems from Partial Observations
• Derivative-based SINDy (DSINDy): Addressing the challenge of discovering governing equations from noisy data
• On the use of graph neural networks and shape-function-based gradient computation in the deep energy method
• Neural Network Forecast of the Sunspot Butterfly Diagram
• Overcoming the curse of dimensionality in the numerical approximation of Allen-Cahn partial differential equations via truncated full-history recursive multilevel Picard approximations
• Latent-space time evolution of non-intrusive reduced-order models using Gaussian process emulation
• Physics-Guided Machine Learning for Scientific Discovery: An Application in Simulating Lake Temperature Profiles
• Learning stable and predictive structures in kinetic systems: Benefits of a causal approach
• Discovering Sparse Interpretable Dynamics from Partial Observations
• ViscoelasticNet: A physics informed neural network framework for stress discovery and model selection
• Numerical simulations for full history recursive multilevel Picard approximations for systems of high-dimensional partial differential equations
• ModalPINN: an extension of Physics-Informed Neural Networks with enforced truncated Fourier decomposition for periodic flow reconstruction using a limited number of imperfect sensors
• A deep learning method for multi-material diffusion problems based on physics-informed neural networks
• Sparse dynamical system identification with simultaneous structural parameters and initial condition estimation
• Weakly-Supervised Deep Learning of Heat Transport via Physics Informed Loss
• Can Transfer Neuroevolution Tractably Solve Your Differential Equations?
• Physics-constrained Deep Learning for Robust Inverse ECG Modeling
• Noise-aware Physics-informed Machine Learning for Robust PDE Discovery
• Discovery of partial differential equations from highly noisy and sparse data with physics-informed information criterion
• Koopman operator learning using invertible neural networks
• Sparse Methods for Automatic Relevance Determination
• Data-driven Identification of 2D Partial Differential Equations using extracted physical features
• Quantum Quantile Mechanics: Solving Stochastic Differential Equations for Generating Time-Series
• Physics-informed machine learning improves detection of head impacts
• Deep neural network approximations for Monte Carlo algorithms
• CD-ROM: Complemented Deep-Reduced Order Model
• Spectrally Adapted Physics-Informed Neural Networks for Solving Unbounded Domain Problems
• System Identification Through Lipschitz Regularized Deep Neural Networks
• A hybrid inference system for improved curvature estimation in the level-set method using machine learning
• An unsupervised deep learning approach in solving partial integro-differential equations
• HyperPINN: Learning parameterized differential equations with physics-informed hypernetworks
• Robust Modeling of Unknown Dynamical Systems via Ensemble Averaged Learning
• Error-correcting neural networks for semi-Lagrangian advection in the level-set method
• Bridging the Gap: Machine Learning to Resolve Improperly Modeled Dynamics
• Stochastic Modeling of Inhomogeneities in the Aortic Wall and Uncertainty Quantification using a Bayesian Encoder-Decoder Surrogate
• Neural Dynamics on Complex Networks
• Learning the Tangent Space of Dynamical Instabilities from Data
• Solving Elliptic Equations with Brownian Motion: Bias Reduction and Temporal Difference Learning
• Improving Long-term Autoregressive Spatiotemporal Predictions: A Proof of Concept with Fluid Dynamics
• A Deep Learning Approach for Predicting Spatiotemporal Dynamics From Sparsely Observed Data
• Extension of Dynamic Mode Decomposition for dynamic systems with incomplete information based on t-model of optimal prediction
• Deep Learning for Mean Field Games with non-separable Hamiltonians
• Unraveled Multilevel Transformation Networks for Predicting Sparsely-Observed Spatiotemporal Dynamics
• Uncertainty Quantification of Graph Convolution Neural Network Models of Evolving Processes
• Constrained or Unconstrained? Neural-Network-Based Equation Discovery from Data
• Principled interpolation of Green's functions learned from data
• Transformer-based Koopman Autoencoder for Linearizing Fisher's Equation
• A Survey on Machine Learning Applied to Dynamic Physical Systems
• Critical Sampling for Robust Evolution Operator Learning of Unknown Dynamical Systems
• How to find the evolution operator of dissipative PDEs from particle fluctuations?