| Full text | |
| Author(s): |
Ogoshi, Elton
;
Popolin-Neto, Mario
;
Acosta, Carlos Mera
;
Nascimento, Gabriel M.
;
Rodrigues, Joao N. B.
;
Oliveira Jr, Osvaldo N.
;
Paulovich, Fernando V.
;
Dalpian, Gustavo M.
Total Authors: 8
|
| Document type: | Journal article |
| Source: | DISCOVER MATERIALS; v. 4, n. 1, p. 14-pg., 2024-02-29. |
| Abstract | |
Having a direct or indirect band gap can influence the potential applications of a semiconductor, for indirect band gap materials are usually not suitable for optoelectronic devices. Even though this is a fundamental property of semiconducting materials, discussed in textbooks, no unified theory exists to explain why a material has a direct or indirect band gap. Here we used an interpretable machine learning model, the multiVariate dAta eXplanation (VAX) method, to gather information from a dataset of materials extracted from the Materials Project. The dataset contains more than 10000 entries, and atomic properties such as the number of electrons, electronic affinity and orbital energies were used as features to build random forest models that successfully explain the directness of the band gaps. Our results indicate that symmetry is an important feature that dictates the target property, which is the reason why our analysis is made based on sub-groups with similar structures. These sub-groups include materials with zincblende, rocksalt, wurtzite, and perovskite structures. Besides the symmetry of the materials, the existence or not of d bands and the relative energy of atomic orbitals were found to be important in defining whether a material's band gap is direct or indirect. In conclusion, interpretable machine learning methods such as VAX can be useful in obtaining physical interpretation from materials databases. (AU) | |
| FAPESP's process: | 17/02317-2 - Interfaces in materials: electronic, magnetic, structural and transport properties |
| Grantee: | Adalberto Fazzio |
| Support Opportunities: | Research Projects - Thematic Grants |
| FAPESP's process: | 19/04176-2 - Searching for new two dimensional materials: thermodynamic properties |
| Grantee: | Gabriel de Miranda Nascimento |
| Support Opportunities: | Scholarships in Brazil - Scientific Initiation |
| FAPESP's process: | 18/11856-7 - Interface-induced effects in quantum materials |
| Grantee: | Carlos Augusto Mera Acosta |
| Support Opportunities: | Scholarships in Brazil - Post-Doctoral |
| FAPESP's process: | 18/11641-0 - Machine learning methods applied to the study of interfaces between semiconductors |
| Grantee: | Elton Ogoshi de Melo |
| Support Opportunities: | Scholarships in Brazil - Doctorate (Direct) |
| FAPESP's process: | 18/22214-6 - Towards a convergence of technologies: from sensing and biosensing to information visualization and machine learning for data analysis in clinical diagnosis |
| Grantee: | Osvaldo Novais de Oliveira Junior |
| Support Opportunities: | Research Projects - Thematic Grants |