mathLab/PINA
Physics-Informed Neural networks for Advanced modeling
This tool helps scientists and engineers build predictive models that adhere to known physical laws or integrate with existing data. You input your scientific problem, including any governing equations or experimental data, and it outputs a trained neural network that can simulate complex systems or make predictions while respecting physics. It's designed for researchers, computational scientists, and anyone working with scientific data and simulations.
719 stars.
Use this if you need to develop machine learning models for scientific or engineering problems where physical principles (like differential equations) are important, or you need to combine real-world data with scientific laws.
Not ideal if your problem is purely data-driven without any underlying physical laws to enforce, or if you only need standard machine learning models without scientific constraints.
Stars
719
Forks
95
Language
Python
License
MIT
Category
Last pushed
Mar 05, 2026
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/mathLab/PINA"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Compare
Related frameworks
NVIDIA/physicsnemo
Open-source deep-learning framework for building, training, and fine-tuning deep learning models...
SciML/NeuralPDE.jl
Physics-Informed Neural Networks (PINN) Solvers of (Partial) Differential Equations for...
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...
jdtoscano94/NABLA-SciML
Physics Informed Machine Learning Tutorials (Pytorch and Jax)