EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Wafer-Scale Learning of Epitaxial Defect Propagation in Thick 4H-SiC Layers

Karim Chaabane, Salma Z. Abid

International Journal of Business and Social Science Studies · 05.09.2026 · 6 (2) · 133-141

DOI: 10.66795/ijbsss66 ↗

Kurz gefasst

Fachartikel in der Zeitschrift International Journal of Business and Social Science Studies, online erschienen am 05.09.2026. Verfasst von Karim Chaabane und 1 weiteren Autor:innen. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

The rapid expansion of the power electronics market, driven by electric vehicles and renewable energy systems, relies heavily on the superior material properties of silicon carbide. Specifically, the 4H polytype of silicon carbide has emerged as the semiconductor of choice for high-voltage applications. However, the commercial viability and operational reliability of these devices are strictly limited by crystallographic defects that form during the growth of thick epitaxial layers. This paper presents a comprehensive methodology for the wafer-scale learning of epitaxial defect propagation in thick silicon carbide layers using advanced machine learning techniques. By leveraging high-resolution multi-modal imaging, including photoluminescence and X-ray topography, a massive dataset of spatially resolved defect structures was assembled. We propose a deep convolutional neural network architecture designed to automatically classify, map, and trace the propagation of basal plane dislocations, threading edge dislocations, and other extended defects across entire wafers. The spatial correlation analysis provides profound insights into the morphological evolution of defects as the epitaxial layer thickness increases. The model achieves exceptional classification accuracy and reveals previously undetected patterns in defect clustering and conversion mechanisms. The implications of these findings are substantial for optimizing chemical vapor deposition processes, ultimately enabling the production of thicker, higher-quality epitaxial layers required for next-generation power grid components.

Zitieren

APA

Chaabane, K., & Abid, S. Z. (2026). Wafer-Scale Learning of Epitaxial Defect Propagation in Thick 4H-SiC Layers. International Journal of Business and Social Science Studies, 6(2), 133-141. https://doi.org/10.66795/ijbsss66

Vancouver

Chaabane K, Abid SZ. Wafer-Scale Learning of Epitaxial Defect Propagation in Thick 4H-SiC Layers. International Journal of Business and Social Science Studies. 2026;6(2):133-141. doi:10.66795/ijbsss66

BibTeX
@article{Chaabane2026,
  author = {Chaabane, Karim and Abid, Salma Z.},
  title = {Wafer-Scale Learning of Epitaxial Defect Propagation in Thick 4H-SiC Layers},
  journal = {International Journal of Business and Social Science Studies},
  year = {2026},
  volume = {6},
  number = {2},
  pages = {133--141},
  doi = {10.66795/ijbsss66}
}
Kostenlos starten →