Machine Learning with Material Databases in Python (Getting started)

Refer to: https://doi.org/10.1007/s10853-023-08...
Computational materials science is now powerful enough that it can predict many properties of materials before those materials are ever synthesized in the lab. Many existing material databases exist that characterize the material of your choice and can tell associated properties determined experimentally and computationally. These databases can be used to search for new materials or determine properties of new materials using machine learning. The problem is, you must know how to access these material databases easily in python. There are several python packages that address this problem: Pymatgen, Matminer.

This video introduces you to these packages in the following ways:

How can you import material structures from a database?
How can you import material properties from a database for machine learning?
How can you use these packages to featurize your material structures as appropriate machine learning inputs?
How can you install these packages in your Conda python environment?

All of this is done in Jupiter notebook in local machine, but you can use google collab.

Purpose of this video is not to teach you about machine learning algorithms, there is ample content out there on it. But only to demonstrate usage of material science packages in python.

For queries or contact, email to [email protected]

Thank you for watching this video. Subscribe and press notification icon for future updates.