Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Machine learning assisted High-Throughput study of M$_4$X$_3$T$_x$ MXenes

Sakshi Goel, Arti Kashyap

Abstract

In this work, we employ a machine-learning-assisted high-throughput density functional theory framework to systematically investigate the stability, electronic structure, and magnetic ground states of 234 M$_4$X$_3$T$_x$ MXenes. The machine learning model predicts lattice parameters with up to 94% accuracy using a relatively small training dataset and significantly reduces structural optimization time in high-throughput calculations. Based on total energy and density-of-states analyses, we classify the magnetic nature of MXenes across different transition- metal compositions and surface terminations. Ti-, Zr-, Hf-, Nb-, and Ta-based MXenes are found to be non-magnetic metals for all functional groups considered, while Sc- and Y-based systems exhibit a range of behaviors including weak ferromagnetism and semiconducting character. V- and Fe-based MXenes are identified as antiferromagnetic metals, whereas Cr- and Mn-based MXenes yield 16 ferromagnetic systems with spin polarization ranging from 50% to 100%.

Machine learning assisted High-Throughput study of M$_4$X$_3$T$_x$ MXenes

Abstract

In this work, we employ a machine-learning-assisted high-throughput density functional theory framework to systematically investigate the stability, electronic structure, and magnetic ground states of 234 MXT MXenes. The machine learning model predicts lattice parameters with up to 94% accuracy using a relatively small training dataset and significantly reduces structural optimization time in high-throughput calculations. Based on total energy and density-of-states analyses, we classify the magnetic nature of MXenes across different transition- metal compositions and surface terminations. Ti-, Zr-, Hf-, Nb-, and Ta-based MXenes are found to be non-magnetic metals for all functional groups considered, while Sc- and Y-based systems exhibit a range of behaviors including weak ferromagnetism and semiconducting character. V- and Fe-based MXenes are identified as antiferromagnetic metals, whereas Cr- and Mn-based MXenes yield 16 ferromagnetic systems with spin polarization ranging from 50% to 100%.
Paper Structure (14 sections, 3 equations, 7 figures, 1 table)

This paper contains 14 sections, 3 equations, 7 figures, 1 table.

Table of Contents

  1. Introduction
  2. Methodology
  3. Machine Learning
  4. Density functional theory
  5. Results and Discussion
  6. ML predicted and DFT calculated Lattice parameter Comparison
  7. Lowest Energy Configurations for functionalized MXenes
  8. Magnetic ground state study
  9. Stability analysis
  10. Electronic Properties
  11. Conclusion
  12. Conflicts of interest
  13. Acknowledgment
  14. Data Availability

Figures (7)

  • Figure 1: An overview of the workflow: (a) Lattice constant (L) prediction of 234 MXenes using ML, (b) lattice constant optimization for M$_4$X$_3$ and six M$_4$X$_3$T$_x$ configurations using ML predicted L as a starting point, (c) magnetic ground state calculation, (d) data analysis.
  • Figure 2: Geometrical structures of the bare and functionalized MXenes (at different positions): Side view of (a) Bare MXene, (b--d) functional group attached at the top and bottom site of M, (e) at the site of X, and (f--g) at M and X sites
  • Figure 3: Side view of different magnetic configurations. (a) FM, (b) AFM1, (c) AFM2, (d) AFM3, the Up arrow represents spin up and down to spin down.
  • Figure 4: Projected Density of States for weak ferromagnetic materials (a) Y$_4$N$_3$O$_2$ (b) Y$_4$N$_3$S$_2$
  • Figure 5: A schematic summary of stability results (a) variation in cohesive energy (eV/atom) and, (b) formation energy (eV/unit cell) with different functional groups for carbide MXenes. (colored lines indicate transition metals)
  • ...and 2 more figures