Neural network model for adjusting the process of studying colloidal nano- and microstructures using atomic force microscopy

Cover Page

Cite item

Full Text

Open Access Open Access
Restricted Access Access granted
Restricted Access Subscription or Fee Access

Abstract

An important stage in the process of formation of micro- and nanosystems is control operations. For operational monitoring of colloidal nano- and microstructured films, atomic force microscopy is used, implemented by the method of amplitude modulation semi-contact scanning. This method is characterized by the complexity and duration of setting the sample scanning parameters. In this project, a neural network has been developed to automatically optimize process parameters during scanning, which can significantly speed up the process and improve image quality and measurement accuracy.

Full Text

Restricted Access

About the authors

E. V. Panfilova

Bauman Moscow State Technical University (National Research university)

Author for correspondence.
Email: panfilova.e.v@bmstu.ru
ORCID iD: 0000-0001-7944-2765

Cand. of Sci. (Tech), Assistant Professor

Russian Federation, Moscow

A. R. Ibragimov

Bauman Moscow State Technical University (National Research university)

Email: panfilova.e.v@bmstu.ru
ORCID iD: 0000-0001-9689-1837

Assistant

Russian Federation, Moscow

D. V. Frantsisin

Bauman Moscow State Technical University (National Research university); Ostek-EK LLC

Email: panfilova.e.v@bmstu.ru
ORCID iD: 0009-0007-7493-8199

Student, Еengineer

Russian Federation, Moscow; Moscow

References

  1. Панфилова Е.В. Перспективные методы формирования планарных наноструктур // Наноинженерия. Машиностроение. 2014. № 8. C. 29–33.
  2. Liu Y. et al. Bioinspired reflective display based on photonic crystals // Interdisciplinary Materials. 2024. Vol. 3. No. 1. PP. 54–73.
  3. Snapp P. et al. Colloidal photonic crystal strain sensor integrated with deformable graphene phototransducer // Advanced Functional Materials. 2019. Vol. 29. No. 33. P. 1902216.
  4. Wang Y. et al. All-optical logic gates based on hierarchical photonic crystal modulated photoluminescence of perovskite nanocrystals // Science China Technological Sciences. 2023. Vol. 66. No. 9. PP. 2735–2742.
  5. Быков В.А. и др. Зондовая микроскопия и спектроскопия: приборы, техника и технология измерений // Взаимодействие сверхвысокочастотного, терагерцового и оптического излучения с полупроводниковыми микро- и наноструктурами, метаматериалами и биообъектами. 2019. С. 29–32.
  6. Giessibl F.J. et al. Calculation of the optimal imaging parameters for frequency modulation atomic force microscopy // Applied Surface Science. 1999. Vol. 140. No. 3–4. PP. 352–357.
  7. Xue B. et al. Study on effects of scan parameters on the image quality and tip wear in AFM tapping mode // Scanning: The Journal of Scanning Microscopies. 2014. Vol. 36. No. 2. PP. 263–269.
  8. Wang Y. et al. Improving the scanning speed of atomic force microscopy at the scanning range of several tens of micrometers // Ultramicroscopy. 2013. Vol. 124. PP. 102–107.
  9. Giergiel M. et al. AFM image analysis of porous structures by means of neural networks // Biomedical Signal Processing and Control. 2022. Vol. 71. P. 103097.
  10. Vekinis A.A., Constantoudis V. Neural network evaluation of geometric tip-sample effects in AFM measurements // Micro and Nano Engineering. 2020. Vol. 8. P. 100057.
  11. Kocur V. et al. Correction of AFM data artifacts using a convolutional neural network trained with synthetically generated data // Ultramicroscopy. 2023. Vol. 246. P. 113666.
  12. Sun M. et al. Fast AFM Imaging Based on Neural Network Compressed Sensing // 2022 IEEE 24th International Workshop on Multimedia Signal Processing (MMSP). IEEE. 2022. PP. 1–5.
  13. Panfilova E.V., Ibragimov A.R., Mozer K.V. Neural network module for tuning an atomic force microscope in the study of photonic crystal films // Journal of Physics: Conference Series. IOP Publishing. 2020. Vol. 1571. No. 1. P. 012004.
  14. Yablon D. et al. Deep learning to establish structure property relationships of impact copolymers from AFM phase images // Mrs Communications. 2021. Vol. 11. PP. 962–968.
  15. Панфилова Е.В., Дюбанов В.А., Ибрагимов А.Р., Шрамко Д.Ю. Лабораторный комплекс для получения коллоидных фотонно-кристаллических структур. Ч. 1 // НАНОИНДУСТРИЯ. 2024. Т. 17. № 3–4. C. 190–199. https://doi.org/10.22184/1993-8578.2024.17.3-4.190.198

Supplementary files

Supplementary Files
Action
1. JATS XML
Download
2. Fig.1. Image given to the neural network input: a – original image; b – image after processing

Download (2MB)
Indexing metadata
3. Fig.2. Neural network structure

Download (349KB)
Indexing metadata
4. Fig.3. Neural network architecture

Download (664KB)
Indexing metadata
5. Fig.4. Dependence of the error of an algorithmic neural network on the number of periods

Download (234KB)
Indexing metadata
6. Fig.5. Image transformation when passing through NN layers (a – initial image, i – final image)

Download (643KB)
Indexing metadata

Copyright (c) 2024 Panfilova E.V., Ibragimov A.R., Frantsisin D.V.