Abstract
Significant advances have been made in predicting new topological materials using high-throughput empirical descriptors or symmetry-based indicators. To date, these approaches have been applied to materials in existing databases, and are severely limited to systems with well-defined symmetries, leaving a much larger materials space unexplored. Using tetradymites as a prototypical class of examples, we uncover a two-dimensional descriptor by applying an artificial intelligence (AI)-based approach for fast and reliable identification of the topological characters of a drastically expanded range of materials, without prior determination of their specific symmetries and detailed band structures. By leveraging this descriptor that contains only the atomic number and electronegativity of the constituent species, we have readily scanned a huge number of alloys in the tetradymite family. Strikingly, nearly half of them are identified to be topological insulators, revealing a much larger territory of the topological materials world. The present work also attests to the increasingly important role of such AI-based approaches in modern materials discovery.
Highlights
Topological insulators (TIs) constitute a new class of quantum materials with insulating bulk but metallic boundary states
In contrast to other artificial intelligence (AI)-based approaches applied to the prediction of TIs [30,31,32,33,34,35], SISSO is built to determine descriptors that are elementary functions of key physical inputs, enabling human inspection into the underlying mechanisms
To construct a reliable training set, we have computed the topological characters of 243 tetradymites by combining group-VA elements (As, Sb, and Bi) with group-VIA elements (S, Se, and Te) in a five-atom unit cell. These systems can be viewed as stackings of quintuple layers (QLs) along the c direction, where van der Waals (vdW) interactions bind neighboring QLs to each other
Summary
Topological insulators (TIs) constitute a new class of quantum materials with insulating bulk but metallic boundary states. Using tetradymites as a prototypical class of examples, we establish an artificial intelligence (AI)-based descriptor for the prediction of TIs without prior determination of their specific symmetries and detailed band structures, covering a previously uncharted and much larger territory in the materials space. To this goal, we first investigate a moderate number (hundreds) of layered tetradymites by using accurate first-principles calculations that account for van der Waals (vdW) interactions [23,24,25] and many-body effects [26,27] at a perturbative level. We employ the SISSO (Sure Independence Screening and Sparsifying Operator) approach [28,29] based on the compressedsensing technique to establish a simple and physically
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
