# Machine learning reveals orbital interaction in crystalline materials

## TL;DR

This paper introduces the orbital-field matrix (OFM), a new representation for crystalline materials based on valence electrons, enabling accurate predictions of formation energies, atomization energies, and magnetic moments.

## Contribution

The paper presents the OFM as a novel representation that captures orbital interactions, improving data mining and predictive modeling in materials science.

## Key findings

- High-accuracy prediction of formation energies and atomization energies.
- Identification of coordination number roles in magnetic moments.
- Decision tree analysis reveals orbital interaction insights.

## Abstract

We propose a novel representation of crystalline materials named orbital-field matrix (OFM) based on the distribution of valence shell electrons. We demonstrate that this new representation can be highly useful in mining material data. Our experiment shows that the formation energies of crystalline materials, the atomization energies of molecular materials, and the local magnetic moments of the constituent atoms in transition metal--rare-earth metal bimetal alloys can be predicted with high accuracy using the OFM. Knowledge regarding the role of coordination numbers of transition-metal and rare-earth metal elements in determining the local magnetic moment of transition metal sites can be acquired directly from decision tree regression analyses using the OFM.