journal article·2025-04-09

Deep Learning with Reflection High-Energy Electron Diffraction Images to Predict Cation Ratio in Sr2xTi2(1–x)O3 Thin Films

Sumner B. Harris, Patrick T. Gemperline, Christopher M. Rouleau, Rama K. Vasudevan, Ryan B. Comes

Nano Letters· Volume 25· Issue 14
Publisher page

Abstract

Machine learning (ML) with in-situ diagnostics offers a transformative approach to accelerate, understand, and control thin film synthesis by uncovering relationships between synthesis conditions and material properties. In this study, we demonstrate the application of deep learning to predict the stoichiometry of Sr 2 x Ti 2(1– x ) O 3 thin films using reflection high-energy electron diffraction images acquired during pulsed laser deposition. A gated convolutional neural network trained for regression of the Sr atomic fraction achieved accurate predictions with a small dataset of 31 samples. Explainable AI techniques revealed a previously unknown correlation between diffraction streak features and cation stoichiometry in Sr 2 x Ti 2(1– x ) O 3 thin films. Our results demonstrate how ML can be used to transform a ubiquitous in-situ diagnostic tool, that is usually limited to qualitative assessments, into a quantitative surrogate measurement of continuously valued thin film properties. Such methods are critically needed to enable real-time control, autonomous workflows, and accelerate traditional synthesis approaches.
Source: openalex_inverted_index · Quality: baseline

Research context

OpenAlex topics: Electronic and Structural Properties of Oxides · Ferroelectric and Piezoelectric Materials · Advanced X-ray and CT Imaging

SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.

Affiliations

Center for Nanophase Materials Sciences

Oak Ridge National Laboratory

Department of Physics, Auburn University, 315 Roosevelt Concourse, Auburn, Alabama 36849, United States

Department of Materials Science and Engineering, University of Delaware, 201 DuPont Hall, Newark, Delaware 19716, United States

Funding

U.S. Department of Energy · National Science Foundation

References (38)

Show source-provided references
1. 10.1038/s41586-023-06734-w10.1038/s41586-023-06734-w ↗
2. 10.1038/s41467-020-19597-w10.1038/s41467-020-19597-w ↗
3. 10.1126/sciadv.aaz886710.1126/sciadv.aaz8867 ↗
4. 10.1038/s41467-024-48534-410.1038/s41467-024-48534-4 ↗
5. 10.1038/s41467-023-37139-y10.1038/s41467-023-37139-y ↗
6. 10.1038/s41598-020-64397-310.1038/s41598-020-64397-3 ↗
7. 10.1038/s41586-020-2442-210.1038/s41586-020-2442-2 ↗
8. 10.1088/1361-6463/ad256910.1088/1361-6463/ad2569 ↗
9. 10.1126/science.273.5277.89810.1126/science.273.5277.898 ↗
10. 10.1063/5.002037010.1063/5.0020370 ↗
11. 10.1002/smtd.20230176310.1002/smtd.202301763 ↗
12. Ichimiya A. · 200410.1017/CBO9780511735097 ↗
13. Braun W. · 1999 · 154
14. 10.1023/A:100994751771010.1023/A:1009947517710 ↗
15. 10.1063/1.282799210.1063/1.2827992 ↗
16. 10.1063/1.490172610.1063/1.4901726 ↗
17. 10.1021/nn504730n10.1021/nn504730n ↗
18. 10.1103/PhysRevMaterials.4.08380710.1103/PhysRevMaterials.4.083807 ↗
19. 10.1186/s40580-023-00359-510.1186/s40580-023-00359-5 ↗
20. 10.1063/5.005965510.1063/5.0059655 ↗
21. 10.1109/66.82733810.1109/66.827338 ↗
22. 10.1021/acs.cgd.2c0113210.1021/acs.cgd.2c01132 ↗
23. 10.1021/acs.cgd.0c0050610.1021/acs.cgd.0c00506 ↗
24. 10.1016/j.jcrysgro.2022.12678010.1016/j.jcrysgro.2022.126780 ↗
25. 10.1038/s41467-024-47087-w10.1038/s41467-024-47087-w ↗
26. 10.1103/PhysRevMaterials.6.06380510.1103/PhysRevMaterials.6.063805 ↗
27. 10.1116/6.000449310.1116/6.0004493 ↗
28. 10.1021/acs.nanolett.4c0450010.1021/acs.nanolett.4c04500 ↗
29. 10.1063/1.491694810.1063/1.4916948 ↗
30. 10.1088/0022-3727/47/3/03400910.1088/0022-3727/47/3/034009 ↗
31. 10.1038/srep1994110.1038/srep19941 ↗
32. 10.1038/s41467-018-04903-410.1038/s41467-018-04903-4 ↗
33. 10.1557/s43578-020-00070-910.1557/s43578-020-00070-9 ↗
34. van den Oord A. · 2016 · 29
35. Zhou J. · 2021 · 6647
36. Chattopadhay, A.; Sarkar, A.; Howlader, P.; Balasubramanian, V. N. IEEE Winter Conference on Applications of Computer Vision (WACV); IEEE, 2018; pp 839–847.
37. 10.1002/admi.20200147710.1002/admi.202001477 ↗
38. 10.1038/srep1182910.1038/srep11829 ↗