Material informatics for layered high-TC superconductors
Superconductors were typically discovered by trial-and-error aided by the knowledge and intuition of individual researchers. In this work, using materials informatics aided by machine learning (ML), we build an ML model of superconductors, which is based on several material descriptors with apparent...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
AIP Publishing LLC
2020-06-01
|
| Series: | APL Materials |
| Online Access: | http://dx.doi.org/10.1063/5.0004641 |
| _version_ | 1818325731695919104 |
|---|---|
| author | Zhong-Li Liu Peng Kang Yu Zhu Lei Liu Hong Guo |
| author_facet | Zhong-Li Liu Peng Kang Yu Zhu Lei Liu Hong Guo |
| author_sort | Zhong-Li Liu |
| collection | DOAJ |
| description | Superconductors were typically discovered by trial-and-error aided by the knowledge and intuition of individual researchers. In this work, using materials informatics aided by machine learning (ML), we build an ML model of superconductors, which is based on several material descriptors with apparent physical meanings to efficiently predict critical superconducting temperature TC. The descriptors include the average atomic mass of a compound, the average number of electrons in an unfilled shell, the average ground state atomic magnetic moments, the maximum difference of electronegativity, etc. To fully optimize the ML model, we develop a multi-step learning and multi-algorithm cross-verification approach. For known high TC superconductors, our ML model predicts excellent TC values with over 92% confidence. When the ML model is applied to about 2500 layered materials in the inorganic crystal structure database, 25 of them are predicted to be superconductors not known before, including 12 cuprates, 7 iron-based crystals, and 6 others, with TC ranging from ∼32 K to ∼138 K. The findings shed considerable light on the mapping between the material descriptors and TC for layered superconductors. The ML calculates that in our descriptors, the maximum difference of electronegativity is the most important one. |
| first_indexed | 2024-12-13T11:49:09Z |
| format | Article |
| id | doaj.art-09996485c5a849918c44adf018d2565c |
| institution | Directory Open Access Journal |
| issn | 2166-532X |
| language | English |
| last_indexed | 2024-12-13T11:49:09Z |
| publishDate | 2020-06-01 |
| publisher | AIP Publishing LLC |
| record_format | Article |
| series | APL Materials |
| spelling | doaj.art-09996485c5a849918c44adf018d2565c2022-12-21T23:47:25ZengAIP Publishing LLCAPL Materials2166-532X2020-06-0186061104061104-810.1063/5.0004641Material informatics for layered high-TC superconductorsZhong-Li Liu0Peng Kang1Yu Zhu2Lei Liu3Hong Guo4College of Physics and Electric Information, Luoyang Normal University, Luoyang 471934, ChinaCentre for the Physics of Materials and Department of Physics, McGill University, Montreal, Quebec H3A 2T8, CanadaNanoacademic Technologies, Inc., Brossard, Quebec J4Z 1A7, CanadaNanoacademic Technologies, Inc., Brossard, Quebec J4Z 1A7, CanadaCentre for the Physics of Materials and Department of Physics, McGill University, Montreal, Quebec H3A 2T8, CanadaSuperconductors were typically discovered by trial-and-error aided by the knowledge and intuition of individual researchers. In this work, using materials informatics aided by machine learning (ML), we build an ML model of superconductors, which is based on several material descriptors with apparent physical meanings to efficiently predict critical superconducting temperature TC. The descriptors include the average atomic mass of a compound, the average number of electrons in an unfilled shell, the average ground state atomic magnetic moments, the maximum difference of electronegativity, etc. To fully optimize the ML model, we develop a multi-step learning and multi-algorithm cross-verification approach. For known high TC superconductors, our ML model predicts excellent TC values with over 92% confidence. When the ML model is applied to about 2500 layered materials in the inorganic crystal structure database, 25 of them are predicted to be superconductors not known before, including 12 cuprates, 7 iron-based crystals, and 6 others, with TC ranging from ∼32 K to ∼138 K. The findings shed considerable light on the mapping between the material descriptors and TC for layered superconductors. The ML calculates that in our descriptors, the maximum difference of electronegativity is the most important one.http://dx.doi.org/10.1063/5.0004641 |
| spellingShingle | Zhong-Li Liu Peng Kang Yu Zhu Lei Liu Hong Guo Material informatics for layered high-TC superconductors APL Materials |
| title | Material informatics for layered high-TC superconductors |
| title_full | Material informatics for layered high-TC superconductors |
| title_fullStr | Material informatics for layered high-TC superconductors |
| title_full_unstemmed | Material informatics for layered high-TC superconductors |
| title_short | Material informatics for layered high-TC superconductors |
| title_sort | material informatics for layered high tc superconductors |
| url | http://dx.doi.org/10.1063/5.0004641 |
| work_keys_str_mv | AT zhongliliu materialinformaticsforlayeredhightcsuperconductors AT pengkang materialinformaticsforlayeredhightcsuperconductors AT yuzhu materialinformaticsforlayeredhightcsuperconductors AT leiliu materialinformaticsforlayeredhightcsuperconductors AT hongguo materialinformaticsforlayeredhightcsuperconductors |