ホーム > 研究活動 > 原著論文 > Machine learning reveals orbital interaction in materials

研究活動

Machine learning reveals orbital interaction in materials

Sci. Technol. Adv. Mater. 18, 756-765 (2017).

2017年10月26日(木)

Tien Lam Pham, Hiori Kino, Kiyoyuki Terakura, Takashi Miyake, Ichigaku Takigawa, Koji Tsudaand Hieu Chi Dam ( http://dx.doi.org/10.1080/14686996.2017.1378060 )

Abstract

We propose a novel representation of materials named an ‘orbital-field matrix (OFM)’, whichis based on the distribution of valence shell electrons. We demonstrate that this newrepresentation can be highly useful in mining material data. Experimental investigation showsthat the formation energies of crystalline materials, atomization energies of molecularmaterials, and local magnetic moments of the constituent atoms in bimetal alloys of lanthanidemetal and transition-metal can be predicted with high accuracy using the OFM. Knowledgeregarding the role of the coordination numbers of the transition-metal and lanthanide elementsin determining the local magnetic moments of the transition-metal sites can be acquireddirectly from decision tree regression analyses using the OFM.

その他特記事項

This work was supported in part by Precursory Research for Embryonic Science and Technology fromJapan Science and Technology Agency (JST), by the Elements Strategy Initiative Project under theauspice of MEXT, by ‘Materials research by Information Integration’ Initiative (MI2 I) project of theSupport 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-Kcomputer, and also by JSPS KAKENHI [Grant Numbers 17K19953 and 17H01783].


研究活動

元素戦略拠点

触媒・電池元素戦略拠点
触媒・電池元素戦略研究拠点 (京都大学)
東工大元素戦略拠点
東工大元素戦略拠点 (東京工業大学)
構造材料元素戦略研究拠点
構造材料元素戦略研究拠点 (京都大学)
高効率モーター用磁性材料技術研究組合
高効率モーター用 磁性材料技術研究組合