|About this Abstract
||2019 TMS Annual Meeting & Exhibition
||Computational Approaches for Big Data, Artificial Intelligence and Uncertainty Quantification in Computational Materials Science
||Research Progress in Machine Learning Building Layered Material Model and Predicting Thermoelectric Performance
||Lihao Chen, Ben Xu, Ke Bi
|On-Site Speaker (Planned)
Layered-semiconductor(LS) materials have excellent performance in the field of thermoelectric materials. In order to explore the characteristics of layered materials at the elemental level, chemical properties, macrostructures, etc., in order to obtain better thermoelectric properties in LS materials, we use a variety of machine learning methods to explore them. And through the feature extraction method, the material is deeply excavated. In this brief review, we summarize the atomic arrangement characteristics common to LS materials, construct element information with its special structure as a template, and then use appropriate chemical information and structural information for material modeling, and demonstrate our views on some of the key information about layered semiconductor materials require further research, including band engineering and doping calculations. Machine learning methods may clarify the relationship between the internal characteristics of materials and various thermoelectric properties, and serve as the basis for the selection and preparation of new thermoelectric materials.
||Planned: Supplemental Proceedings volume