Advancing Magnetic Materials Discovery -- A structure-based machine learning approach for magnetic ordering and magnetic moment prediction

TL;DR

This paper introduces a structure-based machine learning model that accurately predicts magnetic ordering and magnetic moments in a diverse set of materials, aiding the discovery of new magnetic materials.

Contribution

It presents a generalized, efficient ML approach using structural data to predict magnetic properties across a broad range of compounds, surpassing previous models.

Findings

Achieves 82.4% accuracy in magnetic ordering classification.

Predicts magnetic moments with a correlation coefficient of 0.93.

Accurately estimates formation energy for stability assessment.

Abstract

Accurately predicting magnetic behavior across diverse materials systems remains a longstanding challenge due to the complex interplay of structural and electronic factors and is pivotal for the accelerated discovery and design of next-generation magnetic materials. In this work, a refined descriptor is proposed that significantly improves the prediction of two critical magnetic properties -- magnetic ordering (Ferromagnetic vs. Ferrimagnetic) and magnetic moment per atom -- using only the structural information of materials. Unlike previous models limited to Mn-based or lanthanide-transition metal compounds, the present approach generalizes across a diverse dataset of 5741 stable, binary and ternary, ferromagnetic and ferrimagnetic compounds sourced from the Materials Project. Leveraging an enriched elemental vector representation and advanced feature engineering, including nonlinear terms and reduced matrix sparsity, the LightGBM-based model achieves an accuracy of 82.4% for magnetic ordering classification and balanced recall across FM and FiM classes, addressing a key limitation in prior studies. The model predicts magnetic moment per atom with a correlation coefficient of 0.93, surpassing the Hund's matrix and orbital field matrix descriptors. Additionally, it accurately estimates formation energy per atom, enabling assessment of both magnetic behavior and material stability. This generalized and computationally efficient framework offers a robust tool for high-throughput screening of magnetic materials with tailored properties.