DFT-aided machine learning-based discovery of magnetism in Fe-based bimetallic chalcogenides
Abstract With the technological advancement in recent years and the widespread use of magnetism in every sector of the current technology, a search for a low-cost magnetic material has been more important than ever. The discovery of magnetism in alternate materials such as metal chalcogenides with a...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Nature Portfolio
2023-02-01
|
| Series: | Scientific Reports |
| Online Access: | https://doi.org/10.1038/s41598-023-30438-w |
| _version_ | 1797864830887002112 |
|---|---|
| author | Dharmendra Pant Suresh Pokharel Subhasish Mandal Dukka B. KC Ranjit Pati |
| author_facet | Dharmendra Pant Suresh Pokharel Subhasish Mandal Dukka B. KC Ranjit Pati |
| author_sort | Dharmendra Pant |
| collection | DOAJ |
| description | Abstract With the technological advancement in recent years and the widespread use of magnetism in every sector of the current technology, a search for a low-cost magnetic material has been more important than ever. The discovery of magnetism in alternate materials such as metal chalcogenides with abundant atomic constituents would be a milestone in such a scenario. However, considering the multitude of possible chalcogenide configurations, predictive computational modeling or experimental synthesis is an open challenge. Here, we recourse to a stacked generalization machine learning model to predict magnetic moment (µB) in hexagonal Fe-based bimetallic chalcogenides, FexAyB; A represents Ni, Co, Cr, or Mn, and B represents S, Se, or Te, and x and y represent the concentration of respective atoms. The stacked generalization model is trained on the dataset obtained using first-principles density functional theory. The model achieves MSE, MAE, and R2 values of 1.655 (µB)2, 0.546 (µB), and 0.922 respectively on an independent test set, indicating that our model predicts the compositional dependent magnetism in bimetallic chalcogenides with a high degree of accuracy. A generalized algorithm is also developed to test the universality of our proposed model for any concentration of Ni, Co, Cr, or Mn up to 62.5% in bimetallic chalcogenides. |
| first_indexed | 2024-04-09T22:58:21Z |
| format | Article |
| id | doaj.art-5bcc573242f2407f8f5c5accd787e5f7 |
| institution | Directory Open Access Journal |
| issn | 2045-2322 |
| language | English |
| last_indexed | 2024-04-09T22:58:21Z |
| publishDate | 2023-02-01 |
| publisher | Nature Portfolio |
| record_format | Article |
| series | Scientific Reports |
| spelling | doaj.art-5bcc573242f2407f8f5c5accd787e5f72023-03-22T11:06:26ZengNature PortfolioScientific Reports2045-23222023-02-0113111010.1038/s41598-023-30438-wDFT-aided machine learning-based discovery of magnetism in Fe-based bimetallic chalcogenidesDharmendra Pant0Suresh Pokharel1Subhasish Mandal2Dukka B. KC3Ranjit Pati4Department of Physics, Michigan Technological UniversityDepartment of Computer Science, Michigan Technological UniversityDepartment of Physics and Astronomy, West Virginia UniversityDepartment of Computer Science, Michigan Technological UniversityDepartment of Physics, Michigan Technological UniversityAbstract With the technological advancement in recent years and the widespread use of magnetism in every sector of the current technology, a search for a low-cost magnetic material has been more important than ever. The discovery of magnetism in alternate materials such as metal chalcogenides with abundant atomic constituents would be a milestone in such a scenario. However, considering the multitude of possible chalcogenide configurations, predictive computational modeling or experimental synthesis is an open challenge. Here, we recourse to a stacked generalization machine learning model to predict magnetic moment (µB) in hexagonal Fe-based bimetallic chalcogenides, FexAyB; A represents Ni, Co, Cr, or Mn, and B represents S, Se, or Te, and x and y represent the concentration of respective atoms. The stacked generalization model is trained on the dataset obtained using first-principles density functional theory. The model achieves MSE, MAE, and R2 values of 1.655 (µB)2, 0.546 (µB), and 0.922 respectively on an independent test set, indicating that our model predicts the compositional dependent magnetism in bimetallic chalcogenides with a high degree of accuracy. A generalized algorithm is also developed to test the universality of our proposed model for any concentration of Ni, Co, Cr, or Mn up to 62.5% in bimetallic chalcogenides.https://doi.org/10.1038/s41598-023-30438-w |
| spellingShingle | Dharmendra Pant Suresh Pokharel Subhasish Mandal Dukka B. KC Ranjit Pati DFT-aided machine learning-based discovery of magnetism in Fe-based bimetallic chalcogenides Scientific Reports |
| title | DFT-aided machine learning-based discovery of magnetism in Fe-based bimetallic chalcogenides |
| title_full | DFT-aided machine learning-based discovery of magnetism in Fe-based bimetallic chalcogenides |
| title_fullStr | DFT-aided machine learning-based discovery of magnetism in Fe-based bimetallic chalcogenides |
| title_full_unstemmed | DFT-aided machine learning-based discovery of magnetism in Fe-based bimetallic chalcogenides |
| title_short | DFT-aided machine learning-based discovery of magnetism in Fe-based bimetallic chalcogenides |
| title_sort | dft aided machine learning based discovery of magnetism in fe based bimetallic chalcogenides |
| url | https://doi.org/10.1038/s41598-023-30438-w |
| work_keys_str_mv | AT dharmendrapant dftaidedmachinelearningbaseddiscoveryofmagnetisminfebasedbimetallicchalcogenides AT sureshpokharel dftaidedmachinelearningbaseddiscoveryofmagnetisminfebasedbimetallicchalcogenides AT subhasishmandal dftaidedmachinelearningbaseddiscoveryofmagnetisminfebasedbimetallicchalcogenides AT dukkabkc dftaidedmachinelearningbaseddiscoveryofmagnetisminfebasedbimetallicchalcogenides AT ranjitpati dftaidedmachinelearningbaseddiscoveryofmagnetisminfebasedbimetallicchalcogenides |