A curated PINN learning path from theory to practice — covering landmark papers, mainstream solvers and real-world cases.
Updated Nov 3, 2026 18 resources
Introduction
Why this collection
Physics-informed neural networks (PINNs), proposed in 2019, are now a core branch of scientific machine learning. The material online is scattered and the learning path is unclear, so this collection helps you go from the classic papers through the mainstream toolchain and finally into real physical scenarios.
The collection is organised as follows:
Paper reading — from the founding work to recent surveys, building a solid theoretical base.
Tooling — get started with solvers such as DeepXDE and implement your first PINN in Python.
Practical cases — see how PINNs are applied to real engineering problems in aerodynamics and structural mechanics.
A focused survey of PINN improvements via transfer learning and meta-learning, addressing PINN's notorious convergence difficulty and the need to re-optimize on every PDE parameter change - the engineering reference for productionizing PINNs.
arXiv preprint (copyright held by authors)PINNTransfer LearningMeta Learning
💬Editor note: A full survey of adaptive strategies for PINN training — start with the loss-weighting section.
A beginner-friendly PINN library with thorough Chinese docs and TensorFlow/PyTorch/JAX/PaddlePaddle backends - a common starting point for scientific machine learning and PDE solving.
NewGNU Lesser General Public License v2.1PINNBeginnerChinese Docs
💬Editor note: The most mature open-source PINN solver, covering 50+ PDEs, with translated documentation for a quick start.
Presents AKAPINN, a mesh-free KAN-PINN method for nonlinear strain-limiting PDEs with exact hard boundary ansatz and pseudo-Huber loss, evaluated across three material-parameter pairs.
See LICENSE filePINNKolmogorov-Arnold NetworkQuasilinear PDE
A unified framework combining physics-informed neural networks with finite element methods via functional Gauss-Newton problems and Petrov-Galerkin discretization.
See LICENSE filePINNfinite element methodPDE solver
A HuggingFace-hosted model repository for bubble dynamics using Physics-Informed Neural Networks (PINN), with the model name indicating focus on PINN-based bubble dynamics applications.
A joint training approach that addresses neural operator out-of-distribution degradation and PINN multi-solution convergence errors by leveraging imperfect neural operators to guide PINN optimization.
PhD course lecture notes from University of Bozen/Bolzano covering Physics Informed Neural Networks and Neural Operators with PyTorch implementation tutorials.
A free online textbook from TU Munich covering physics + deep learning: differentiable physics, PINNs, neural operators and turbulence modeling, with runnable code.
A HuggingFace repository hosting a physics-informed neural network model for computational fluid dynamics, implementing physics constraints embedded within neural network architectures.
See LICENSE filePINNCFDphysics-informed neural network
A Chinese structured tutorial implementing PINN from minimal dependencies, built chapter by chapter around the 1D heat equation — ML basics, separation of variables, FDM/FEM comparisons, PINN model construction and optimizer comparison, GMM and curriculum learning, plus locELM, random-feature and RaNN extensions. MIT licensed - the best start for Chinese-speaking learners.
A systematic review of 2025-2026 progress in physics-informed ML - neural operators, diffusion for PDE solving, large benchmarks and industrial deployment.
NVIDIA's physics-ML framework (formerly Modulus, renamed in 2025), a PyTorch-based library for PINN, neural operators and physics-constrained training - architecture, versions, comparisons and failure boundaries.
Julia SciML ecosystem library unifying PINN/DeepONet/NeuralOperator solvers with seamless DifferentialEquations.jl interoperability and GPU/autodiff out of the box.
A periodic physics-informed neural network (P-PINN) framework is proposed for solving parametric periodic flows and analyzing finite-amplitude aeroelastic responses in a purely physics-driven manner.