Awesome Physiscs-Informed Machine Learning (Neuural Networks)

A carefully curated collection of high-quality libraries, projects, tutorials, research papers, and other essential resources focused on Physics-Informed Machine Learning (PIML) and Physics-Informed Neural Networks (PINNs). This repository is designed to be a comprehensive, well-organized knowledge base for researchers and developers working in the growing field of integrating physics with machine learning.

To ensure that the community stays up to date with the latest breakthroughs, our repository is automatically updated with new PINN/PIML-related research papers from arXiv. This feature guarantees access to cutting-edge developments, making it an invaluable resource for anyone exploring physics-constrained learning methods.

Whether you're a researcher modeling complex physical systems, a developer building physics-guided models, or an enthusiast in scientific machine learning, this collection serves as a centralized hub for everything related to PIML, PINNs, and the broader integration of domain knowledge into learning systems, enriched by original peer-reviewed contributions to the field.

Last Updated

June 14, 2025 at 01:20:09 AM UTC

Theorem

Papers (50)

• OmniFluids: Unified Physics Pre-trained Modeling of Fluid Dynamics
• Hamiltonian Learning via Inverse Physics-Informed Neural Networks
• R-PINN: Recovery-type a-posteriori estimator enhanced adaptive PINN
• Generalizable and Fast Surrogates: Model Predictive Control of Articulated Soft Robots using Physics-Informed Neural Networks
• Physics-informed Kolmogorov-Arnold Network with Chebyshev Polynomials for Fluid Mechanics
• TS-PIELM: Time-Stepping Physics-Informed Extreme Learning Machine Facilitates Soil Consolidation Analyses
• Provably Accurate Adaptive Sampling for Collocation Points in Physics-informed Neural Networks
• LT-PINN: Lagrangian Topology-conscious Physics-informed Neural Network for Boundary-focused Engineering Optimization
• BridgeNet: A Hybrid, Physics-Informed Machine Learning Framework for Solving High-Dimensional Fokker-Planck Equations
• Thermodynamically Consistent Latent Dynamics Identification for Parametric Systems
• Neural Tangent Kernel Analysis to Probe Convergence in Physics-informed Neural Solvers: PIKANs vs. PINNs
• Physics-Informed Neural Operators for Generalizable and Label-Free Inference of Temperature-Dependent Thermoelectric Properties
• Learnable Activation Functions in Physics-Informed Neural Networks for Solving Partial Differential Equations
• Learning Fluid-Structure Interaction Dynamics with Physics-Informed Neural Networks and Immersed Boundary Methods
• Physics-Informed Neural Networks for Control of Single-Phase Flow Systems Governed by Partial Differential Equations
• Over-PINNs: Enhancing Physics-Informed Neural Networks via Higher-Order Partial Derivative Overdetermination of PDEs
• Weak Physics Informed Neural Networks for Geometry Compatible Hyperbolic Conservation Laws on Manifolds
• Solving engineering eigenvalue problems with neural networks using the Rayleigh quotient
• SF^2^2Bench: Evaluating Data-Driven Models for Compound Flood Forecasting in South Florida
• Improved Uncertainty Quantification in Physics-Informed Neural Networks Using Error Bounds and Solution Bundles
• A Bayesian PINN Framework for Barrow-Tsallis Holographic Dark Energy with Neutrinos: Toward a Resolution of the Hubble Tension
• An Approximation Theory Perspective on Machine Learning
• Deterministic and statistical calibration of constitutive models from full-field data with parametric physics-informed neural networks
• MoPINNEnKF: Iterative Model Inference using generic-PINN-based ensemble Kalman filter
• DiffPINN: Generative diffusion-initialized physics-informed neural networks for accelerating seismic wavefield representation
• Cluster Reconstruction in Electromagnetic Calorimeters Using Machine Learning Methods
• Unified theoretical guarantees for stability, consistency, and convergence in neural PDE solvers from non-IID data to physics-informed networks
• Machine learning meets \mathfrak{su}(n)\mathfrak{su}(n) Lie algebra: Enhancing quantum dynamics learning with exact trace conservation
• On the definition and importance of interpretability in scientific machine learning
• CPINN-ABPI: Physics-Informed Neural Networks for Accurate Power Estimation in MPSoCs
• PADAM: Parallel averaged Adam reduces the error for stochastic optimization in scientific machine learning
• Locking-Free Training of Physics-Informed Neural Network for Solving Nearly Incompressible Elasticity Equations
• A Physics-Informed Learning Framework to Solve the Infinite-Horizon Optimal Control Problem
• Are Statistical Methods Obsolete in the Era of Deep Learning?
• Godunov Loss Functions for Modelling of Hyperbolic Conservation Laws
• Dual Natural Gradient Descent for Scalable Training of Physics-Informed Neural Networks
• A data augmentation strategy for deep neural networks with application to epidemic modelling
• Advancing Molecular Machine Learning Representations with Stereoelectronics-Infused Molecular Graphs
• Solving Euler equations with Multiple Discontinuities via Separation-Transfer Physics-Informed Neural Networks
• Uncertainty Quantification for Physics-Informed Neural Networks with Extended Fiducial Inference
• Convergence Analysis of Natural Gradient Descent for Over-parameterized Physics-Informed Neural Networks
• Perception-Informed Neural Networks: Beyond Physics-Informed Neural Networks
• KITINet: Kinetics Theory Inspired Network Architectures with PDE Simulation Approaches
• SetPINNs: Set-based Physics-informed Neural Networks
• Repulsive Ensembles for Bayesian Inference in Physics-informed Neural Networks
• A Unified Framework for Simultaneous Parameter and Function Discovery in Differential Equations
• Equivariant Eikonal Neural Networks: Grid-Free, Scalable Travel-Time Prediction on Homogeneous Spaces
• Machine learning on manifolds for inverse scattering: Lipschitz stability analysis
• Fourier-Invertible Neural Encoder (FINE) for Homogeneous Flows
• Hybrid Adaptive Modeling in Process Monitoring: Leveraging Sequence Encoders and Physics-Informed Neural Networks

Library

Tutorial

Written Tutorials

Video Tutorials

Contributing

We welcome contributions to this repository! If you have a resource that you believe should be included, please submit a pull request or open an issue. Contributions can include:

• New libraries or tools related to PIML or PINNs
• Tutorials or guides that help users understand and implement PIML techniques
• Research papers that advance the field of PIML or PINNs
• Any other resources that you find valuable for the community

How to Contribute

1. Fork the repository.
2. Create a new branch for your changes.
3. Make your changes and commit them with a clear message.
4. Push your changes to your forked repository.
5. Submit a pull request to the main repository.

Before contributing, take a look at the existing resources to avoid duplicates.

License

This repository is licensed under the Creative Commons Attribution 4.0 International License (CC BY 4.0). You are free to share and adapt the material, provided you give appropriate credit, link to the license, and indicate if changes were made.

Star History