Data mining is a broad discipline that aims to develop and use methods for extracting meaningful information and knowledge from large data sets. Recently, data mining methods have successfully been employed to the field of computational materials science. In this work, through examples, we demonstrate that data mining techniques can be used to extract practical knowledge of chemical physics from materials systems automatically. A predictive data mining approach can be applied to first-principles calculation data to computationally model the chemical and physical properties of materials with high accuracy and low computational cost. A descriptive data mining approach can be used to obtain interpretable insights into the actuating mechanisms of physical phenomena from experimental and first-principles calculation data. We also discuss the foundation and future of this research direction from both mathematical and physical/chemical perspectives.

Determining physical/chemical properties for material systems with data mining

255th National Meeting (2018)

The official archive and repository for all ACS Meetings & Expositions abstracts and select posters or presentations.