DFT-aided machine learning-based discovery of magnetism in Fe-based bimetallic chalcogenides

Dharmendra Pant; Suresh Pokharel; Subhasish Mandal; Dukka B Kc; Ranjit Pati

doi:10.1038/s41598-023-30438-w

DFT-aided machine learning-based discovery of magnetism in Fe-based bimetallic chalcogenides

Sci Rep. 2023 Feb 25;13(1):3277. doi: 10.1038/s41598-023-30438-w.

Authors

Dharmendra Pant¹, Suresh Pokharel², Subhasish Mandal³, Dukka B Kc², Ranjit Pati^{4

5}

Affiliations

¹ Department of Physics, Michigan Technological University, Houghton, MI, 49931, USA.
² Department of Computer Science, Michigan Technological University, Houghton, MI, 49931, USA.
³ Department of Physics and Astronomy, West Virginia University, Morgantown, WV, 26506, USA.
⁴ Department of Physics, Michigan Technological University, Houghton, MI, 49931, USA. patir@mtu.edu.
⁵ Henes Center for Quantum Phenomena, Michigan Technological University, Houghton, MI, 49931, USA. patir@mtu.edu.

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, Fe_xA_yB; 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.