Physic Informed Neural Network

Physics-informed neural networks (PINNs) integrate physical laws, typically expressed as differential equations, into neural network training to solve complex scientific problems. Current research focuses on improving PINN accuracy and efficiency through architectural innovations like Fourier-based networks, Kolmogorov-Arnold networks, and wavelet-based approaches, as well as advanced optimization strategies such as dual cone gradient descent and DiffGrad. These advancements aim to overcome limitations in handling high-frequency solutions, complex geometries, and stiff equations, ultimately enhancing the applicability of PINNs across diverse scientific and engineering domains, including fluid dynamics, seismology, and materials science.

Papers

May 29, 2022

Physical Activation Functions (PAFs): An Approach for More Efficient Induction of Physics into Physics-Informed Neural Networks (PINNs)
Jassem Abbasi, Pål Østebø Andersen
Physic Informed Neural Network Activation Function Efficient Learning Theoretical Physic Numerical Method Physical Model

May 28, 2022

Laplace HypoPINN: Physics-Informed Neural Network for hypocenter localization and its predictive uncertainty
Muhammad Izzatullah, Isa Eren Yildirim, Umair Bin Waheed, Tariq Alkhalifah
Physic Informed Neural Network Predictive Uncertainty Earthquake Monitoring Laplace fPINNs Hypocenter Localization

May 27, 2022

May 23, 2022

Generic bounds on the approximation error for physics-informed (and) operator learning
Tim De Ryck, Siddhartha Mishra
Physic Informed Neural Network Operator Learning Physic Informed Neural Network Approximation Social Generic Approximation Error Physic Informed Operator Learning

May 19, 2022

Accelerated Training of Physics-Informed Neural Networks (PINNs) using Meshless Discretizations
Ramansh Sharma, Varun Shankar
Physic Informed Neural Network Radial Basis Function Faster Training PINN Model

May 18, 2022

Revisiting PINNs: Generative Adversarial Physics-informed Neural Networks and Point-weighting Method
Wensheng Li, Chao Zhang, Chuncheng Wang, Hanting Guan, Dacheng Tao
Generative Adversarial Network Physic Informed Neural Network Reg PINNs PINN Method

May 17, 2022

Spiking Neural Operators for Scientific Machine Learning
Adar Kahana, Qian Zhang, Leonard Gleyzer, George Em Karniadakis
Physic Informed Neural Network Scientific Machine Learning Fully Connected Neural Network SNN Based Regression Function

May 16, 2022

May 14, 2022

Bayesian Physics-Informed Extreme Learning Machine for Forward and Inverse PDE Problems with Noisy Data
Xu Liu, Wen Yao, Wei Peng, Weien Zhou
Physic Informed Neural Network Physic Informed Machine Learning Bayesian Perspective Noisy Data Extreme Learning Machine Inverse PDE Problem

May 13, 2022

Hyper-parameter tuning of physics-informed neural networks: Application to Helmholtz problems
Paul Escapil-Inchauspé, Gonzalo A. Ruz
Application Proficiency Physic Informed Neural Network Bayesian Optimization Numerical Experiment Hyper Parameter Optimization Hyper Parameter Tuning Helmholtz Equation

May 12, 2022

Bayesian Physics-Informed Neural Networks for real-world nonlinear dynamical systems
Kevin Linka, Amelie Schafer, Xuhui Meng, Zongren Zou, George Em Karniadakis, Ellen Kuhl
Neural Network Physic Informed Neural Network Real World Dynamical System Bayesian Neural Network Bayesian Perspective Nonlinear Model Physic Based Disease Dynamic

May 6, 2022

Physics-informed neural networks for PDE-constrained optimization and control
Jostein Barry-Straume, Arash Sarshar, Andrey A. Popov, Adrian Sandu
Physic Informed Neural Network External Control Optimal Control Predator Prey Loop Optimal Control Space Optimality

May 5, 2022

Lagrangian PINNs: A causality-conforming solution to failure modes of physics-informed neural networks
Rambod Mojgani, Maciej Balajewicz, Pedram Hassanzadeh
Physic Informed Neural Network Soft Constraint Failure Mode Linear Convection Novel Causal Model Lagrangian Neural Network Convection Diffusion Equation

May 2, 2022

RANG: A Residual-based Adaptive Node Generation Method for Physics-Informed Neural Networks
Wei Peng, Weien Zhou, Xiaoya Zhang, Wen Yao, Zheliang Liu
Physic Informed Neural Network Density Evolution

April 29, 2022

April 26, 2022

Self-scalable Tanh (Stan): Faster Convergence and Better Generalization in Physics-informed Neural Networks
Raghav Gnanasambandam, Bo Shen, Jihoon Chung, Xubo Yue, Zhenyu, Kong
Physic Informed Neural Network Faster Convergence Better Generalization Thermal Conductivity

April 23, 2022

Competitive Physics Informed Networks
Qi Zeng, Yash Kothari, Spencer H. Bryngelson, Florian Schäfer
Physic Informed Neural Network Physic Informed Discretized Governing Equation

Physic Informed Neural Network

Papers

Physical Activation Functions (PAFs): An Approach for More Efficient Induction of Physics into Physics-Informed Neural Networks (PINNs)

Laplace HypoPINN: Physics-Informed Neural Network for hypocenter localization and its predictive uncertainty

Experience report of physics-informed neural networks in fluid simulations: pitfalls and frustration

Auto-PINN: Understanding and Optimizing Physics-Informed Neural Architecture

Generic bounds on the approximation error for physics-informed (and) operator learning

Accelerated Training of Physics-Informed Neural Networks (PINNs) using Meshless Discretizations

Revisiting PINNs: Generative Adversarial Physics-informed Neural Networks and Point-weighting Method

Spiking Neural Operators for Scientific Machine Learning

Loss Landscape Engineering via Data Regulation on PINNs

Scalable algorithms for physics-informed neural and graph networks

Bayesian Physics-Informed Extreme Learning Machine for Forward and Inverse PDE Problems with Noisy Data

Hyper-parameter tuning of physics-informed neural networks: Application to Helmholtz problems

Bayesian Physics-Informed Neural Networks for real-world nonlinear dynamical systems

Physics-informed neural networks for PDE-constrained optimization and control

Lagrangian PINNs: A causality-conforming solution to failure modes of physics-informed neural networks

RANG: A Residual-based Adaptive Node Generation Method for Physics-Informed Neural Networks

RAR-PINN algorithm for the data-driven vector-soliton solutions and parameter discovery of coupled nonlinear equations

Enhanced Physics-Informed Neural Networks with Augmented Lagrangian Relaxation Method (AL-PINNs)

Self-scalable Tanh (Stan): Faster Convergence and Better Generalization in Physics-informed Neural Networks

Competitive Physics Informed Networks