je-santos/ms_net

The MultiScale Network for hierarchical regression (MS-Net) performs 3D regression based on a hierarchical principle: coarse inputs provide broad information about the data, and progressively finer-scale inputs can be used to refine this information.

40
/ 100
Emerging

This tool helps researchers and engineers who work with complex 3D simulations, particularly in fields like porous media flow. It takes large 3D arrays representing material structures or simulation conditions and predicts properties, such as fluid flow or electrical conductivity, efficiently. Users can input data from sources like the Digital Rocks Portal to get refined predictions without excessive computational cost.

No commits in the last 6 months.

Use this if you need to perform accurate predictions on large, complex 3D simulation data without overwhelming your computational resources.

Not ideal if your data is simple, small, or primarily 1D/2D, as the multi-scale approach's benefits might not outweigh its setup for less complex problems.

porous-media-simulation materials-science geological-modeling fluid-dynamics computational-physics
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 7 / 25
Maturity 16 / 25
Community 17 / 25

How are scores calculated?

Stars

27

Forks

8

Language

Jupyter Notebook

License

MIT

Last pushed

Dec 07, 2022

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/je-santos/ms_net"

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