NVIDIA/physicsnemo
Open-source deep-learning framework for building, training, and fine-tuning deep learning models using state-of-the-art Physics-ML methods
This framework helps scientists and engineers build, train, and fine-tune AI models that combine real-world data with known physics principles. It takes scientific and engineering data (like point clouds or meshes) and physics equations as input to produce predictive AI models for complex systems. Researchers and domain experts in fields like climate science or computational fluid dynamics would use this to create models that offer real-time predictions.
2,530 stars. Actively maintained with 28 commits in the last 30 days.
Use this if you need to develop highly accurate, scalable AI models for scientific or engineering problems that benefit from incorporating known physics laws, especially when working with large datasets and GPU acceleration.
Not ideal if your problem does not involve physics-based phenomena or if you primarily work with standard machine learning tasks that don't require specialized scientific data handling or physics integration.
Stars
2,530
Forks
605
Language
Python
License
Apache-2.0
Category
Last pushed
Mar 12, 2026
Commits (30d)
28
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/NVIDIA/physicsnemo"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Related frameworks
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...
mathLab/PINA
Physics-Informed Neural networks for Advanced modeling
jdtoscano94/NABLA-SciML
Physics Informed Machine Learning Tutorials (Pytorch and Jax)