IBM/simulai

A toolkit with data-driven pipelines for physics-informed machine learning.

45
/ 100
Emerging

This toolkit helps researchers and engineers build physics-informed machine learning models to simulate complex physical systems. You input observational data and known physical laws, and it outputs predictive models that adhere to scientific principles. It's designed for scientists, physicists, and engineers working with simulations, fluid dynamics, or material science.

197 stars. No commits in the last 6 months.

Use this if you need to develop machine learning models that not only learn from data but also respect the underlying physical laws of the system you are studying.

Not ideal if your problem domain does not involve physical systems or if you require models that are purely data-driven without incorporating physical constraints.

scientific-computing physical-modeling engineering-simulation computational-physics predictive-modeling
Stale 6m No Package No Dependents
Maintenance 2 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 17 / 25

How are scores calculated?

Stars

197

Forks

28

Language

Python

License

Apache-2.0

Last pushed

Sep 17, 2025

Commits (30d)

0

Get this data via API

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

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