NeuroDiffGym/neurodiffeq

A library for solving differential equations using neural networks based on PyTorch, used by multiple research groups around the world, including at Harvard IACS.

58
/ 100
Established

This tool helps scientists and engineers solve complex differential equations (ODEs and PDEs) that describe how systems change over time or space. You provide the equations and boundary conditions, and it uses neural networks to produce continuous, differentiable solutions. It's designed for researchers, academics, and domain experts who need to model intricate physical or biological phenomena without relying solely on traditional numerical methods.

773 stars. No commits in the last 6 months. Available on PyPI.

Use this if you need to find continuous and differentiable solutions for challenging differential equations, especially those that are non-linear or chaotic, and you are comfortable working with a Python library.

Not ideal if you need extremely fast, high-precision solutions for simple, well-behaved linear differential equations where traditional numerical methods are sufficient.

mathematical-modeling computational-physics engineering-simulation scientific-computing systems-dynamics
Stale 6m
Maintenance 2 / 25
Adoption 10 / 25
Maturity 25 / 25
Community 21 / 25

How are scores calculated?

Stars

773

Forks

102

Language

Python

License

MIT

Last pushed

Jul 27, 2025

Commits (30d)

0

Dependencies

14

Get this data via API

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

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