EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Neural Estimation of Crystallographic Orientation from Rotating-Substrate RHEED with Limited Training Data: Application to CdTe Thin Films

Bartłomiej Turowski iD, Jakub J Meixner, Róża Dziewiątkowska, Wojciech Zaleszczyk, Tomasz Wojciechowski, Valentine V Volobuev, Marcin M Wysokiński, Tomasz Wojtowicz

ACS Applied Materials & Interfaces · 18.11.2026

DOI: 10.1021/acsami.6c15520 ↗

Kurz gefasst

Fachartikel in der Zeitschrift ACS Applied Materials & Interfaces, online erschienen am 18.11.2026. Verfasst von Bartłomiej Turowski und 7 weiteren Autor:innen. Beteiligte Einrichtung: International Research Centre MagTop, Institute of Physics, Polish Academy of Sciences, Aleja Lotników 32/46, WarsawPL-02668, Poland. Die Arbeit nennt 59 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Fundacja na rzecz Nauki Polskiej, Minister Nauki, Ministerstwo Nauki i Szkolnictwa Wyzszego.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

We introduce a data-efficient neural-vision method to estimate the crystallographic orientation of a rotating substrate from reflection high-energy electron diffraction (RHEED) patterns during molecular beam epitaxy (MBE) growth. We combine single-frame azimuth predictions of a neural network with the known rotation kinematics in a physics-aware postprocessing step. This step detects the rotation direction and recovers a robust reference azimuth, replacing manual frame-by-frame inspection. Trained on RHEED patterns from only 15 independently grown CdTe samples, the model infers the crystallographic directions to within the 0.5° target for 95% of rotations. Under leave-one-structure-out evaluation on all 20 samples, the mean error is 0.18°. High accuracy stems from the postprocessing rather than from the network architecture. A 2D ResNet reaches the accuracy of a 3D ResNet benchmark trained on the same number of samples at approximately one tenth of the training cost. Our work delivers (i) a physics-constrained estimation procedure for rotating-substrate RHEED, applicable to any azimuth regressor that is unbiased over a rotation, (ii) an analysis of why few independently grown samples suffice, and (iii) a trained system validated for online orientation estimation during CdTe growth.

Schlagwörter

Stichwörter der Autor:innen

CdTe substrateRHEEDcomputer visionmachine learningmolecular beam epitaxy

Autor:innen und Institutionen

  • International Research Centre MagTop, Institute of Physics, Polish Academy of Sciences, Aleja Lotników 32/46, WarsawPL-02668, Poland.
  • Institute of Physics, Polish Academy of Sciences, Aleja Lotników 32/46, WarsawPL-02668, Poland.
  • National Technical University "KhPI" , Kyrpychova Str. 2, Kharkiv61002, Ukraine.

ORCID-Profile: Bartłomiej Turowski

Förderung

  • Fundacja na rzecz Nauki Polskiej
  • Minister Nauki
  • Ministerstwo Nauki i Szkolnictwa Wyzszego

Zitieren

APA

Turowski, B., Meixner, J. J., Dziewiątkowska, R., Zaleszczyk, W., Wojciechowski, T., Volobuev, V. V., Wysokiński, M. M., & Wojtowicz, T. (2026). Neural Estimation of Crystallographic Orientation from Rotating-Substrate RHEED with Limited Training Data: Application to CdTe Thin Films. ACS Applied Materials & Interfaces. https://doi.org/10.1021/acsami.6c15520

Vancouver

Turowski B, Meixner JJ, Dziewiątkowska R, Zaleszczyk W, Wojciechowski T, Volobuev VV, et al. Neural Estimation of Crystallographic Orientation from Rotating-Substrate RHEED with Limited Training Data: Application to CdTe Thin Films. ACS Applied Materials & Interfaces. 2026. doi:10.1021/acsami.6c15520

BibTeX
@article{Turowski2026,
  author = {Turowski, Bartłomiej and Meixner, Jakub J and Dziewiątkowska, Róża and Zaleszczyk, Wojciech and Wojciechowski, Tomasz and Volobuev, Valentine V and Wysokiński, Marcin M and Wojtowicz, Tomasz},
  title = {Neural Estimation of Crystallographic Orientation from Rotating-Substrate RHEED with Limited Training Data: Application to CdTe Thin Films},
  journal = {ACS Applied Materials & Interfaces},
  year = {2026},
  doi = {10.1021/acsami.6c15520}
}
Kostenlos starten →