leiterrl/porch

A PyTorch library for Physics-Informed Neural Networks (PINNs)

34
/ 100
Emerging

This library helps scientists and engineers solve complex physics problems, even when they have limited or noisy experimental data. You feed in the physical equations governing your system and any available data, and it outputs a neural network model that can accurately predict system behavior. It's designed for researchers, computational scientists, and anyone working with differential equations in fields like fluid dynamics, material science, or heat transfer.

Use this if you need to model physical systems and solve partial differential equations (PDEs) but struggle with sparse data or traditional numerical methods.

Not ideal if you're looking for a general-purpose machine learning library without a specific focus on physics-informed modeling.

computational-physics scientific-modeling differential-equations engineering-simulation data-driven-science
No Package No Dependents
Maintenance 13 / 25
Adoption 5 / 25
Maturity 16 / 25
Community 0 / 25

How are scores calculated?

Stars

9

Forks

Language

Python

License

MPL-2.0

Last pushed

Mar 17, 2026

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/leiterrl/porch"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.