Machine learning-assisted high-entropy alloy discovery: a perspective
Journal of Materials Informatics · 13.04.2026 · 6 (2)
DOI: 10.20517/jmi.2025.79 ↗Kurz gefasst
Fachartikel in der Zeitschrift Journal of Materials Informatics, online erschienen am 13.04.2026. Verfasst von Ning Yang und 3 weiteren Autor:innen. Die Arbeit nennt 56 Literaturangaben.
Abstract (Originalsprache)
High-entropy alloys (HEAs) have attracted extensive attention due to their exceptional mechanical, physical, and chemical properties, making them promising candidates for extreme environments. Understanding the complex structure-property relationships in these multi-principal element systems is crucial for discovering and designing high-performance HEAs. However, their vast compositional space and high-dimensional chemical complexity pose major challenges to traditional trial-and-error design. Machine learning (ML) offers a transformative strategy to overcome these barriers by enabling data-driven exploration. This perspective first reviews the critical challenges currently limiting HEA development, then summarizes recent ML breakthroughs in phase formation prediction, multi-objective optimization, and accelerated atomistic simulations. Finally, we discuss ongoing challenges and propose future opportunities for integrating ML with experimental and computational methods to create more interpretable, data-efficient, and autonomous ML-driven HEA design frameworks.
Zitieren
APA
Yang, N., Zhou, J., Huang, H., & Sun, Z. (2026). Machine learning-assisted high-entropy alloy discovery: a perspective. Journal of Materials Informatics, 6(2). https://doi.org/10.20517/jmi.2025.79
Vancouver
Yang N, Zhou J, Huang H, Sun Z. Machine learning-assisted high-entropy alloy discovery: a perspective. Journal of Materials Informatics. 2026;6(2). doi:10.20517/jmi.2025.79
BibTeX
@article{Yang2026,
author = {Yang, Ning and Zhou, Jian and Huang, Hongfu and Sun, Zhimei},
title = {Machine learning-assisted high-entropy alloy discovery: a perspective},
journal = {Journal of Materials Informatics},
year = {2026},
volume = {6},
number = {2},
doi = {10.20517/jmi.2025.79}
}
EUVIMED