Scientific Machine Learning Through Physics–Informed Neural Networks: Where we are and What’s Next (2022-01-14T00:00:00.000000Z)

TL;DR

This article provides a comprehensive review of the literature on PINNs and indicates that most research has focused on customizing the PINN through different activation functions, gradient optimization techniques, neural network structures, and loss function structures.

Abstract

Physics-Informed Neural Networks (PINN) are neural networks (NNs) that encode model equations, like Partial Differential Equations (PDE), as a component of the neural network itself. PINNs are nowadays used to solve PDEs, fractional equations, integral-differential equations, and stochastic PDEs. This novel methodology has arisen as a multi-task learning framework in which a NN must fit observed data while reducing a PDE residual. This article provides a comprehensive review of the literature on PINNs: while the primary goal of the study was to characterize these networks and their related advantages and disadvantages. The review also attempts to incorporate publications on a broader range of collocation-based physics informed neural networks, which stars form the vanilla PINN, as well as many other variants, such as physics-constrained neural networks (PCNN), variational hp-VPINN, and conservative PINN (CPINN). The study indicates that most research has focused on customizing the PINN through different activation functions, gradient optimization techniques, neural network structures, and loss function structures. Despite the wide range of applications for which PINNs have been used, by demonstrating their ability to be more feasible in some contexts than classical numerical techniques like Finite Element Method (FEM), advancements are still possible, most notably theoretical issues that remain unresolved.

Authors

S. Cuomo

1 papers

Vincenzo Schiano Di Cola

1 papers

F. Giampaolo

1 papers

TL;DR

Abstract

Authors

References219 items

Improved Training of Physics-Informed Neural Networks with Model Ensembles

A-PINN: Auxiliary physics informed neural networks for forward and inverse problems of nonlinear integro-differential equations

Certified machine learning: A posteriori error estimation for physics-informed neural networks

Error estimates for physics informed neural networks approximating the Navier-Stokes equations

Respecting causality is all you need for training physics-informed neural networks

Learning To Estimate Regions Of Attraction Of Autonomous Dynamical Systems Using Physics-Informed Neural Networks

Solving Partial Differential Equations with Point Source Based on Physics-Informed Neural Networks

CAN-PINN: A Fast Physics-Informed Neural Network Based on Coupled-Automatic-Numerical Differentiation Method

A seamless multiscale operator neural network for inferring bubble dynamics

Physics-informed deep learning characterizes morphodynamics of Asian soybean rust disease

Mesh-Free Surrogate Models for Structural Mechanic FEM Simulation: A Comparative Study of Approaches

Data-driven vector soliton solutions of coupled nonlinear Schrödinger equation using a deep learning algorithm

Solving inverse problems in stochastic models using deep neural networks and adversarial training

Learning in Sinusoidal Spaces With Physics-Informed Neural Networks

Structural identification with physics-informed neural ordinary differential equations

Modeling of the Forward Wave Propagation Using Physics-Informed Neural Networks

U-FNO - an enhanced Fourier neural operator based-deep learning model for multiphase flow

Characterizing possible failure modes in physics-informed neural networks

Recent advance in machine learning for partial differential equation

NeuralPDE: Automating Physics-Informed Neural Networks (PINNs) with Error Approximations

Finite basis physics-informed neural networks (FBPINNs): a scalable domain decomposition approach for solving differential equations

IDRLnet: A Physics-Informed Neural Network Library

Error analysis for physics-informed neural networks (PINNs) approximating Kolmogorov PDEs

Physics-Informed Neural Networks for Non-linear System Identification for Power System Dynamics

Extreme theory of functional connections: A fast physics-informed neural network method for solving ordinary and partial differential equations

A physics-informed deep learning framework for inversion and surrogate modeling in solid mechanics

Physics-Informed Neural Networks for Heat Transfer Problems

Physics-informed machine learning

Physics-informed neural networks (PINNs) for fluid mechanics: a review

Distributed Multigrid Neural Solvers on Megavoxel Domains

Efficient training of physics‐informed neural networks via importance sampling

On the approximation of functions by tanh neural networks

A High-Efficient Hybrid Physics-Informed Neural Networks Based on Convolutional Neural Network

Identifiability and predictability of integer- and fractional-order epidemiological models using physics-informed neural networks

Conditional physics informed neural networks

Elvet - a neural network-based differential equation and variational problem solver

Knowledge Integration into deep learning in dynamical systems: an overview and taxonomy

Interpretable Machine Learning: Fundamental Principles and 10 Grand Challenges

The Old and the New: Can Physics-Informed Deep-Learning Replace Traditional Linear Solvers?

Estimating model inadequacy in ordinary differential equations with physics-informed neural networks

SPINN: Sparse, Physics-based, and partially Interpretable Neural Networks for PDEs

Three ways to solve partial differential equations with neural networks — A review

Learning atrial fiber orientations and conductivity tensors from intracardiac maps using physics-informed neural networks

Towards Causal Representation Learning

Physics-informed machine learning: case studies for weather and climate modelling

A study on a feedforward neural network to solve partial differential equations in hyperbolic-transport problems

Deep Learning Method Based on Physics Informed Neural Network with Resnet Block for Solving Fluid Flow Problems

ANNs-Based Method for Solving Partial Differential Equations : A Survey

Machine learning for accelerating 2D flood models: Potential and challenges

Towards neural Earth system modelling by integrating artificial intelligence in Earth system science

Reconstruction of nanoscale particles from single-shot wide-angle free-electron-laser diffraction patterns with physics-informed neural networks.

HypoSVI: Hypocenter inversion with Stein variational inference and Physics Informed Neural Networks

Can Transfer Neuroevolution Tractably Solve Your Differential Equations?

Deep Neural Network Model for Approximating Eigenmodes Localized by a Confining Potential

Physics-informed neural networks with hard constraints for inverse design

Understanding and Mitigating Gradient Flow Pathologies in Physics-Informed Neural Networks

Operator learning for predicting multiscale bubble growth dynamics.

Physics‐Informed Neural Network Method for Forward and Backward Advection‐Dispersion Equations

Data-driven rogue waves and parameter discovery in the defocusing NLS equation with a potential using the PINN deep learning

NVIDIA SimNet^{TM}: an AI-accelerated multi-physics simulation framework

Thermodynamically consistent physics-informed neural networks for hyperbolic systems

DPM: A Novel Training Method for Physics-Informed Neural Networks in Extrapolation

Physics-Informed Neural Network for Modelling the Thermochemical Curing Process of Composite-Tool Systems During Manufacture

Deep learning in nano-photonics: inverse design and beyond

ADCME: Learning Spatially-varying Physical Fields using Deep Neural Networks

Theory-guided Auto-Encoder for Surrogate Construction and Inverse Modeling

DeepM&Mnet for hypersonics: Predicting the coupled flow and finite-rate chemistry behind a normal shock using neural-network approximation of operators

A tutorial on solving ordinary differential equations using Python and hybrid physics-informed neural network

Error estimates of residual minimization using neural networks for linear PDEs

A Physics-Guided Neural Network Framework for Elastic Plates: Comparison of Governing Equations-Based and Energy-Based Approaches

Extraction of material properties through multi-fidelity deep learning from molecular dynamics simulation

DeepM&Mnet: Inferring the electroconvection multiphysics fields based on operator approximation by neural networks

Physics Informed Neural Networks for Simulating Radiative Transfer

Uncovering turbulent plasma dynamics via deep learning from partial observations.

Large-scale Neural Solvers for Partial Differential Equations

Self-Adaptive Physics-Informed Neural Networks using a Soft Attention Mechanism