nanditadoloi/PINN

Simple PyTorch Implementation of Physics Informed Neural Network (PINN)

46
/ 100
Emerging

This tool helps scientists and engineers solve complex physics problems, like understanding heat flow, by integrating known physical laws directly into a machine learning model. You provide the governing differential equations and boundary conditions, and it outputs a model that approximates the solution, even for challenging scenarios like fluid flow through porous media. This is ideal for researchers in fields like geology, material science, or fluid dynamics.

369 stars. No commits in the last 6 months.

Use this if you need to find numerical solutions to partial differential equations while ensuring the solutions adhere to physical principles, especially when traditional numerical methods are too slow or complex.

Not ideal if your problem doesn't involve physical laws expressible as differential equations or if you're primarily focused on data-driven prediction without physical constraints.

fluid-dynamics geological-modeling numerical-simulation engineering-physics differential-equations
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 20 / 25

How are scores calculated?

Stars

369

Forks

57

Language

Jupyter Notebook

License

MIT

Last pushed

Jul 05, 2024

Commits (30d)

0

Get this data via API

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

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