AmeyaJagtap/XPINNs

Extended Physics-Informed Neural Networks (XPINNs): A Generalized Space-Time Domain Decomposition Based Deep Learning Framework for Nonlinear Partial Differential Equations

48
/ 100
Emerging

When solving complex physics problems, this framework helps researchers and engineers model systems governed by nonlinear partial differential equations (PDEs), even those with intricate geometries or discontinuous behaviors. It takes your PDE problem definition and produces a trained neural network model that can predict system behavior more efficiently than standard methods. This tool is ideal for computational scientists, physicists, and engineers working on simulations and analyses where traditional PDE solvers struggle with complexity or computational cost.

248 stars. No commits in the last 6 months.

Use this if you need to solve complex partial differential equations and require a method that can handle arbitrary domain geometries, reduce computation time through parallelization, and adapt to varying solution complexities across different regions.

Not ideal if your problems are simple and can be solved efficiently with conventional numerical methods or if you prefer a single-network approach over a domain decomposition strategy.

computational-physics fluid-dynamics-simulation materials-science-modeling numerical-analysis engineering-simulations
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 22 / 25

How are scores calculated?

Stars

248

Forks

52

Language

License

MIT

Last pushed

Feb 01, 2023

Commits (30d)

0

Get this data via API

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

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