# Classification of magnetic order from electronic structure by using machine learning

## TL;DR

This paper presents a machine learning approach using decision trees to classify magnetic order from electronic spectral data, demonstrating high accuracy even across different data generation methods.

## Contribution

The study introduces a novel machine learning framework that effectively classifies magnetic states from electronic spectra, improving robustness and accuracy over traditional methods.

## Key findings

- Decision-tree models accurately classify magnetic order from spectral data.
- Excitation energy features enhance model performance and robustness.
- Model generalizes well across different data generation methods.

## Abstract

Identifying the magnetic state of materials is of great interest in a wide range of applications, but direct identification is not always straightforward due to limitations in neutron scattering experiments. In this work, we present a machine-learning approach using decision-tree algorithms to identify magnetism from the spin-integrated excitation spectrum, such as the density of states. The dataset was generated by Hartree-Fock mean-field calculations of candidate antiferromagnetic orders on a Wannier Hamiltonian, extracted from first-principle calculations targeting BaOsO$_3$. Our machine learning model was trained using various types of spectral data, including local density of states, momentum-resolved density of states at high-symmetry points, and the lowest excitation energies from the Fermi level. Although the density of states shows good performance for machine learning, the broadening method had a significant impact on the model's performance. We improved the model's performance by designing the excitation energy as a feature for machine learning, resulting in excellent classification of antiferromagnetic order, even for test samples generated by different methods from the training samples used for machine learning.