Machine learning approaches to point defects in non-metallic materials: a review of methods
Applied Physics Express · 01.06.2026 · 19 (6) · 060101
DOI: 10.35848/1882-0786/ae6eb7 ↗Kurz gefasst
Fachartikel in der Zeitschrift Applied Physics Express, online erschienen am 03.06.2026. Verfasst von Yu Kumagai und 1 weiteren Autor:innen. Die Arbeit wurde bisher 2-mal zitiert (Crossref) und nennt 195 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Japan Society for the Promotion of Science, Asahi Glass Foundation, JST FOREST Program.
Abstract (Originalsprache)
We review recent machine learning (ML) approaches for point defects in non-metallic materials, with an emphasis on defect formation energies. Existing studies largely fall into two categories: direct ML models that predict defect energies from local structural representations, and ML potentials that approximate the defect-containing potential energy surface. We summarize key achievements as well as persistent bottlenecks, emphasizing that dataset quality often dominates practical model performance. We further identify charged-defect formation energies as a central frontier, where Fermi-level alignment, finite-size corrections, and long-range electrostatics must be handled carefully and consistently to enable meaningful comparisons and transferable predictions across different materials.
Förderung
- Japan Society for the Promotion of Science
- Asahi Glass Foundation
- JST FOREST Program
Zitieren
APA
Kumagai, Y., & Kiyohara, S. (2026). Machine learning approaches to point defects in non-metallic materials: a review of methods. Applied Physics Express, 19(6), 060101. https://doi.org/10.35848/1882-0786/ae6eb7
Vancouver
Kumagai Y, Kiyohara S. Machine learning approaches to point defects in non-metallic materials: a review of methods. Applied Physics Express. 2026;19(6):060101. doi:10.35848/1882-0786/ae6eb7
BibTeX
@article{Kumagai2026,
author = {Kumagai, Yu and Kiyohara, Shin},
title = {Machine learning approaches to point defects in non-metallic materials: a review of methods},
journal = {Applied Physics Express},
year = {2026},
volume = {19},
number = {6},
pages = {060101},
doi = {10.35848/1882-0786/ae6eb7}
}
EUVIMED