MunzirH/Applications-of-Physics-Informed-Machine-Learning

🌌 Applications of Physics-Informed ML: A collection of notebooks from my Masters research, exploring how machine learning can solve scientific problems by embedding physical laws directly into models. Includes projects on discovering the Burgers equation, using PINNs for PDEs, and employing SINDy for dynamic systems analaysis with sparse data.

27
/ 100
Experimental

This project helps scientists and engineers discover the underlying physical equations governing dynamic systems, even with limited or noisy experimental data. It takes in observational data from physical phenomena and outputs mathematical equations or highly accurate predictive models that inherently respect physical laws. Researchers in fluid dynamics, mechanical engineering, and applied physics would find this useful for analyzing complex systems.

No commits in the last 6 months.

Use this if you need to uncover the governing equations from sparse or noisy scientific data, or if you want to model physical systems with machine learning while ensuring the models adhere to fundamental physical laws.

Not ideal if your problem does not involve physical systems, or if you have abundant, clean data and don't require the explicit embedding of physical constraints into your models.

fluid-dynamics systems-modeling scientific-computing experimental-data-analysis physics-research
No License Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 5 / 25
Maturity 8 / 25
Community 14 / 25

How are scores calculated?

Stars

11

Forks

3

Language

Jupyter Notebook

License

Last pushed

Nov 09, 2024

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/MunzirH/Applications-of-Physics-Informed-Machine-Learning"

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