Score: 0

Machine learning magnetism from simple global descriptors

Published: September 7, 2025 | arXiv ID: 2509.05909v1

By: Ahmed E. Fahmy

Potential Business Impact:

Finds better magnetic materials for science.

Business Areas:
Machine Learning Artificial Intelligence, Data and Analytics, Software

The reliable identification of magnetic ground states remains a major challenge in high-throughput materials databases, where density functional theory (DFT) workflows often converge to ferromagnetic (FM) solutions. Here, we partially address this challenge by developing machine learning classifiers trained on experimentally validated MAGNDATA magnetic materials leveraging a limited number of simple compositional, structural, and electronic descriptors sourced from the Materials Project database. Our propagation vector classifiers achieve accuracies above 92%, outperforming recent studies in reliably distinguishing zero from nonzero propagation vector structures, and exposing a systematic ferromagnetic bias inherent to the Materials Project database for more than 7,843 materials. In parallel, LightGBM and XGBoost models trained directly on the Materials Project labels achieve accuracies of 84-86% (with macro F1 average scores of 63-66%), which proves useful for large-scale screening for magnetic classes, if refined by MAGNDATA-trained classifiers. These results underscore the role of machine learning techniques as corrective and exploratory tools, enabling more trustworthy databases and accelerating progress toward the identification of materials with various properties.

Country of Origin
🇺🇸 United States

Page Count
211 pages

Category
Condensed Matter:
Materials Science