EUVIMEDEUVIMED entdecken
Crossref

Peak Sequence Transformer: A Real-Time AI RHEED Monitoring Framework for Ferroelectric Nitride MBE Growth

Dalei Jiang, Yuyang Chen, Danhao Wang, Jiayu Chen, Peisen Gao, Tianju Wang, Jiangnan Liu, Md Mehedi Hasan Tanim, Elena Sung, Yu Zheng, Rui Xu, Yucheng Wei und 1 weitere

Crystal Growth & Design · 05.08.2026 · 26 (15) · 5744-5752

DOI: 10.1021/acs.cgd.5c01379 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Crystal Growth & Design, online erschienen am 21.07.2026. Verfasst von Dalei Jiang und 12 weiteren Autor:innen. Die Arbeit nennt 43 Literaturangaben. Gefördert von: Army Research Office, University of Michigan.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Reflection high-energy electron diffraction (RHEED) is a cornerstone technique for in situ monitoring of surface crystallography, reconstruction transitions, thin-film roughness, and growth mode during materials growth by molecular beam epitaxy (MBE). However, current analysis workflows rely heavily on manual interpretation and often neglect the temporal continuity feature of material growth. Here, we present the Peak Sequence Transformer (PS-Transformer), a lightweight temporal modeling framework that combines a physics-inspired peak-aware encoder, which achieves a 2490:1 reduction in input dimensionality, with Transformer-based attention to capture temporal evolution. Initial frame-level labels are generated from manually assigned start and end scores with linear interpolation and subsequently refined through pseudolabel self-training, enabling robust performance with minimal manual effort. When evaluated on ferroelectric nitride RHEED data sets, PS-Transformer achieves 99.87% classification accuracy, 105.3 frames per second inference speed, and 75.51% lower power consumption compared to three-dimensional (3D) convolutional neural network (CNN) baselines, while requiring substantially fewer parameters and floating-point operations. This physics-guided framework provides a practical and generalizable solution for real-time RHEED video analysis in semiconductor manufacturing and high-throughput research.

Förderung

  • Army Research Office
  • University of Michigan

Zitieren

APA

Jiang, D., Chen, Y., Wang, D., Chen, J., Gao, P., Wang, T., Liu, J., Tanim, M. M. H., Sung, E., Zheng, Y., Xu, R., Wei, Y., & Mi, Z. (2026). Peak Sequence Transformer: A Real-Time AI RHEED Monitoring Framework for Ferroelectric Nitride MBE Growth. Crystal Growth & Design, 26(15), 5744-5752. https://doi.org/10.1021/acs.cgd.5c01379

Vancouver

Jiang D, Chen Y, Wang D, Chen J, Gao P, Wang T, et al. Peak Sequence Transformer: A Real-Time AI RHEED Monitoring Framework for Ferroelectric Nitride MBE Growth. Crystal Growth & Design. 2026;26(15):5744-5752. doi:10.1021/acs.cgd.5c01379

BibTeX
@article{Jiang2026,
  author = {Jiang, Dalei and Chen, Yuyang and Wang, Danhao and Chen, Jiayu and Gao, Peisen and Wang, Tianju and Liu, Jiangnan and Tanim, Md Mehedi Hasan and Sung, Elena and Zheng, Yu and Xu, Rui and Wei, Yucheng and Mi, Zetian},
  title = {Peak Sequence Transformer: A Real-Time AI RHEED Monitoring Framework for Ferroelectric Nitride MBE Growth},
  journal = {Crystal Growth & Design},
  year = {2026},
  volume = {26},
  number = {15},
  pages = {5744--5752},
  doi = {10.1021/acs.cgd.5c01379}
}
Kostenlos starten →