mala-project/mala

Materials Learning Algorithms. A framework for machine learning materials properties from first-principles data.

51
/ 100
Established

This tool helps materials scientists and researchers predict material properties faster and more efficiently. It takes data from first-principles simulations, specifically density functional theory (DFT) calculations, and generates machine learning models. The output is a surrogate model that can rapidly predict material behavior, bypassing computationally intensive simulations. Materials scientists, computational chemists, and condensed matter physicists would find this useful for multiscale modeling.

Use this if you need to accelerate your materials science research by replacing expensive density functional theory (DFT) calculations with fast, machine-learned predictions.

Not ideal if you are not working with first-principles simulation data or need to perform full, high-fidelity DFT calculations for fundamental research.

materials-science computational-chemistry density-functional-theory multiscale-modeling materials-discovery
No Package No Dependents
Maintenance 6 / 25
Adoption 9 / 25
Maturity 16 / 25
Community 20 / 25

How are scores calculated?

Stars

98

Forks

27

Language

Python

License

BSD-3-Clause

Last pushed

Jan 05, 2026

Commits (30d)

0

Get this data via API

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

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