SCiarella/TLS_ML_exploration

Active learning to explore glassy landscapes

21
/ 100
Experimental

This project helps materials scientists and physicists efficiently find rare defects, specifically two-level systems (TLS), within glass simulations. You input simulation data representing pairs of amorphous configurations. The system then outputs predictions about which pairs are likely to be TLS, saving significant computational time by avoiding characterization of uninteresting defects. This is for researchers studying the properties of disordered materials at a microscopic level.

No commits in the last 6 months.

Use this if you are trying to identify and characterize rare state-to-state transitions, like quantum tunneling two-level systems, in complex systems with slow dynamics and an exponentially large number of states.

Not ideal if your problem does not involve identifying specific transitions between states or if you can easily characterize all possible transitions without machine learning.

materials-science condensed-matter-physics glassy-systems computational-materials-discovery defect-identification
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 5 / 25
Maturity 16 / 25
Community 0 / 25

How are scores calculated?

Stars

10

Forks

Language

Python

License

MIT

Last pushed

Nov 16, 2024

Commits (30d)

0

Get this data via API

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

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