This repository explores Physics-Informed Neural Networks (PINNs) using PyTorch.
PINNs integrate physical laws, expressed as partial differential equations (PDEs), into the training of neural networks.
This approach is especially useful when data is scarce but the governing physics is well-understood.
This project demonstrates how to implement PINNs to solve PDEs by embedding physical constraints directly into the loss function of a neural network.
📝 For a detailed tutorial, check out the accompanying Medium article.
git clone https://github.com/TheodoreWolf/pinns.git
cd pinns
It is recommended to use a virtual environment.
python -m venv .venv # Create a virtual environment
source .venv/bin/activate # activate the virtual environment
Install the dependencies listed in pyproject.toml.
pip install -e .
Inspired by the foundational work by Raissi et al.
This repo aims to provide an approachable and practical introduction to PINNs with PyTorch.