SciML/ModelingToolkitNeuralNets.jl

Symbolic-Numeric Neural DAEs and Universal Differential Equations for Automating Scientific Machine Learning (SciML)

47
/ 100
Emerging

This tool helps scientific researchers integrate neural networks directly into complex mathematical models, especially those involving differential equations. It allows you to feed raw experimental data or specific model outputs into neural network components and retrieve predictions that seamlessly fit back into your larger simulation, enhancing the accuracy of models with unknown or hard-to-define physics. It's designed for scientists, engineers, and quantitative analysts who build sophisticated scientific simulations.

Use this if you need to embed machine learning directly within your scientific simulations, particularly when parts of your system are governed by differential equations and require data-driven approximations.

Not ideal if you are looking for a standalone neural network library for general-purpose machine learning tasks outside of scientific modeling contexts.

scientific-modeling differential-equations physics-informed-AI systems-simulation data-driven-modeling
No Package No Dependents
Maintenance 10 / 25
Adoption 7 / 25
Maturity 16 / 25
Community 14 / 25

How are scores calculated?

Stars

40

Forks

6

Language

Julia

License

MIT

Last pushed

Mar 12, 2026

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/SciML/ModelingToolkitNeuralNets.jl"

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