PINA: Physics-Informed Neural networks for Advance modeling

Physics Informed Neural network for Advanced modeling (PINA) is an open-source Python library providing an intuitive interface for Scientific Machine Learning with State-of-the-Art models, from PINNs to Neural Operators, ROMs and more. Based on PyTorch and PyTorchLightning, PINA offers a simple and intuitive way to formalize a specific (differential) problem and solve it using neural networks. The approximated solution of a differential equation can be implemented using PINA in a few lines of code thanks to the intuitive and user-friendly interface.

PINA is freely available under the MIT License and is currently part of the PyTorch Ecosystem.

Download the source code and tutorials at github.com.

PINA is developed and maintained at SISSA mathLab and Fast Computing, see the complete maintainers list. For further information or questions about PINA contact us by email (pina.mathlab@gmail.com), or feel free to open a pull requests.