Machine learning reveals orbital interaction in materials

Abstract

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

Graphical Abstract

Keywords:

• Material descriptor
• machine learning
• data mining
• magnetic materials
• material informatics

Classification:

• 60 New topics/Others
• 404 Materials informatics / Genomics
• 203 Magnetics / Spintronics / Superconductors

Notes

No potential conflict of interest was reported by the authors.

Supplemental data for this article can be accessed at https://doi.org/10.1080/14686996.2017.1378060.

Additional information

Funding

This work was supported in part by Precursory Research for Embryonic Science and Technology from Japan Science and Technology Agency (JST), by the Elements Strategy Initiative Project under the auspice of MEXT, by ‘Materials research by Information Integration’ Initiative (MI2 I) project of the Support Program for Starting Up Innovation Hub from Japan Science and Technology Agency (JST), by MEXT as a social and scientific priority issue (Creation of new functional devices and high-performance materials to support next-generation industries; CDMSI) to be tackled by using post-K computer, and also by JSPS KAKENHI [Grant Numbers 17K19953 and 17H01783]..