Massive Monte Carlo simulations-guided interpretable learning of two-dimensional Curie temperature.
basic_science · Level V
Where this comes from
- Record sourced from PubMed, PMID 36569550.
- Also identified by DOI 10.1016/j.patter.2022.100625 and PMC identifier 9782261.
- Licence recorded as CC BY-NC-ND.
- Because redistribution is not established, this page shows the abstract only. Follow the links below for the full text.
Abstract
Monte Carlo (MC) simulation of the classical Heisenberg model has become the de facto tool to estimate the Curie temperature (<i>T</i> <sub>C</sub>) of two-dimensional (2D) magnets. As an alternative, here we develop data-driven models for the five most common crystal types, considering the isotropic and anisotropic exchange of up to four nearest neighbors and the single-ion anisotropy. We sample the 20-dimensional Heisenberg spin Hamiltonian and conceive a bisection-based MC technique to simulate a quarter of a million materials for training deep neural networks, which yield testing <i>R</i> <sup>2</sup> scores of nearly 0.99. Since 2D magnetism has a natural tendency toward low <i>T</i> <sub>C</sub>, learning-from-data is combined with data-from-learning to ensure a nearly uniform final data distribution over a wide range of <i>T</i> <sub>C</sub> (10-1,000 K). Global and local analysis of the features confirms the models' interpretability. We also demonstrate that the <i>T</i> <sub>C</sub> can be accurately estimated by a purely first-principles-based approach, free from any empirical corrections.