MURI Seminar 09/06/2022: Topogivity: A Machine-Learned Chemical Rule for Discovering Topological Materials

Andrew Ma from Massachusetts Institute of Technology will present a talk titled “A Machine-Learned Chemical Rule for Discovering Topological Materials”. 

Abstract:

A fundamental question in the field of topological materials is why some materials are topological while others are not. In this talk, I will discuss our work on a machine-learned heuristic rule that diagnoses whether a material is topological using only its chemical formula. Our approach enables chemical insights into electronic band topology via a notion that we term topogivity, which is a numerical value for each chemical element that loosely captures its tendency to form topological materials. By implementing a high-throughput procedure based on heuristic rule prediction followed by ab initio validation, we discover new topological materials that would have been difficult to find using existing methods.