leiterrl/porch
A PyTorch library for Physics-Informed Neural Networks (PINNs)
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.
Stars
9
Forks
—
Language
Python
License
MPL-2.0
Category
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.
Higher-rated alternatives
SciML/NeuralPDE.jl
Physics-Informed Neural Networks (PINN) Solvers of (Partial) Differential Equations for...
NVIDIA/physicsnemo
Open-source deep-learning framework for building, training, and fine-tuning deep learning models...
NVIDIA/physicsnemo-sym
Framework providing pythonic APIs, algorithms and utilities to be used with PhysicsNeMo core to...
idrl-lab/idrlnet
IDRLnet, a Python toolbox for modeling and solving problems through Physics-Informed Neural...
mathLab/PINA
Physics-Informed Neural networks for Advanced modeling