AryaAftab/Physics-based-neural-network

Physics-based neural network with Sine Activation Function

25
/ 100
Experimental

This project helps scientists and engineers approximate solutions to complex partial differential equations (PDEs) that describe physical phenomena, like fluid flow or heat transfer. You input the PDE and its boundary conditions, and it outputs a learned function that approximates the true solution, without needing a traditional grid-based computational mesh. Researchers in computational physics, engineering, or applied mathematics would find this useful.

No commits in the last 6 months.

Use this if you need to find numerical solutions to PDEs and want to explore modern, computationally efficient methods that avoid meshing complexities.

Not ideal if you prefer established, grid-based finite element or finite difference methods, or if your PDEs are simple enough for analytical solutions.

numerical-methods partial-differential-equations computational-physics scientific-modeling engineering-simulation
No License Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 5 / 25
Maturity 8 / 25
Community 12 / 25

How are scores calculated?

Stars

11

Forks

2

Language

Jupyter Notebook

License

Last pushed

Aug 28, 2021

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/AryaAftab/Physics-based-neural-network"

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