[8a-N302-1~11] 18.1 Materials Informatics

9:30 AM - 9:45 AM JST(12:30 AM - 12:45 AM UTC)Presentation by Applicant for JSAP Young Scientists Presentation Award

[8a-N302-3] Reconstruction of 3D Crystal Structures from Density of States and Partial Density of States

〇Haruki Nagata¹, Hidekazu Ikeno¹ (1.Osaka Metropolitan Univ.)

Keywords:

Machine Learning,Density of States,Inverse Design

The physical properties of materials are governed by their electronic states. If crystal structures can be predicted from the density of states (DOS), the inverse design of materials based on their functional properties will become achievable. Therefore, in this study, we developed a machine learning method capable of directly reconstructing 3D crystal structures from the DOS, without being constrained by the number of atoms or the specific atomic species within the structure. In some cases, this model successfully predicted crystal structures with high accuracy. The prediction time was only a few seconds, suggesting its potential to contribute to accelerating the materials discovery process.