Neural Estimation of Crystallographic Orientation from Rotating-Substrate RHEED with Limited Training Data: Application to CdTe Thin Films
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.
Authors
- W. Zaleszczyk (ORCID: https://orcid.org/0000-0002-0051-7267)
- Bartłomiej Turowski (ORCID: https://orcid.org/0000-0003-1229-4416)
- Valentine V. Volobuev (ORCID: https://orcid.org/0000-0002-8474-7392)
- Marcin M. Wysokiński (ORCID: https://orcid.org/0000-0002-7881-5168)
- J. Meixner (ORCID: https://orcid.org/0009-0009-5293-8731)
- Róża Dziewiątkowska (ORCID: https://orcid.org/0009-0004-9325-9843)
- Tomasz Wojtowicz (ORCID: https://orcid.org/0000-0003-4498-4622)
- Tomasz Wojciechowski (ORCID: https://orcid.org/0000-0002-6424-988X)
Institutions
- National Technical University "Kharkiv Polytechnic Institute" (UA)
- Polish Academy of Sciences (PL)
Publication Details
- Journal
- ACS Applied Materials & Interfaces
- Published
- 2026-11-18
- DOI
- https://doi.org/10.1021/acsami.6c15520
- Citations
- 1
- Primary Topic
- Machine Learning in Materials Science
- Type
- article
- Field-Weighted Citation Impact
- 0.84
Funders
- European Commission
- Fundacja na rzecz Nauki Polskiej