Ukrainian Journal of Physical Optics


2026 Volume 27, Issue 4


ISSN 1816-2002 (Online), ISSN 1609-1833 (Print)

MACHINE LEARNING APPROACH FOR OPTICAL NON-DESTRUCTIVE NANOMETROLOGY OF NANO (MICRO) SCALE ROUGH SURFACES

C. Zenkova, O. Angelsky, D. Ivanskyi, V. Tkachuk, P. Ryabyi, A. Koniakhin, Yu. Ursuliak, and S. Hanson

Author Information
1Zenkova, C. ORCID logo, 1Angelsky, O. ORCID logo, 1Ivanskyi, D. ORCID logo, 1Tkachuk, V. ORCID logo, 1Ryabyi, P. ORCID logo, 1Koniakhin, A. ORCID logo, 2Ursuliak, Yu. ORCID logo, 3Hanson, S. ORCID logo

1Chernivtsi National University, 2 Kotsiubynskoho Street, Chernivtsi, Ukraine, 58002
2Municipal Enterprise Chernivtsi Regional Clinical Cardiological Center, 230 Heroiv Maidanu, Chernivtsi, Ukraine, 58006
3DTU Fotonik, Department of Photonics Engineering, Frederiksborgvej 399, Building 128, 4000 Roskilde, Denmark
*Corresponding author: k.zenkova@chnu.edu.ua

ABSTRACT

A comprehensive approach for non-contact, non-destructive, and high-precision analysis of surface inhomogeneity distributions has been proposed, enabling reconstruction of the surface height distribution with coefficients of determination (R2) ranging from 0.86 to 0.90, based on the photoluminescence intensity distribution of surface-deposited perovskite nanoparticles. Perovskite nanoparticles of about 5 nm were employed as functional markers, reproducing the surface topographic profile after deposition. A machine learning model based on graph convolutional networks (GCN) was developed to analyze and reconstruct the height distribution of surfaces with nano- and micro-inhomogeneities. The model was trained using experimental data obtained by atomic force microscopy to determine the surface height profile, together with measurements of the luminescence intensity of the deposited nanoparticles

Keywords: perovskite nanoparticles, graph convolutional networks, height distribution, nano- and micro-inhomogeneities

UDC: 004.85:535.8, 620.179.16, 681.7

    1. Mellor, L. (2025). Tribology in Mechanical Engineering: Navigating the Science of Friction Wear, and Lubrication. J Appl Mech Eng, 14, 530.
    2. Ahmadi, A. (2025). Study in Tribology Science and its Importance in Mechanical Engineering. International Journal for Multidisciplinary Research (IJFMR).
    3. Dai, Z.X., Ono, T., Dai, C.L. (2026). Editorial for the Special Issue on MEMS/NEMS Devices and Applications, 3rd Edition. Micromachines (Basel), 17(2), 205.
      doi:10.3390/mi17020205
    4. Daniyal, W. M. E. M. M., Fen, Y.W., Abdullah, J., Sadrolhosseini, A.R., Mahdi, M.A. (2021). Design and Optimization of Surface Plasmon Resonance Spectroscopy for Optical Constant Characterization and Potential Sensing Application: Theoretical and Experimental Approaches. Photonics, 8, 361.
      doi:10.3390/photonics8090361
    5. Angelsky, O. V., Zenkova, C. Yu., Hanson, S. G., Ivansky, D.I., Tkachuk, V.M., and Jun Zheng (2021). Random object optical field diagnostics by using carbon nanoparticles, Optics Express, 29(2), 916-928.
      doi:10.1364/OE.411118
    6. Angelsky, O. V., Zenkova, C. Yu., Ivansky, D. I., Tkachuk, V. M., Jun Zheng. (2021) Carbon nanoparticles for study complex optical fields, Journal of Optoelectronics and Advanced Materials, 23(5-6), 2021.
    7. Angelsky, O. V., Bekshaev, A. Y., Zenkova, C. Yu., Ivansky, D. I., Zheng, J., Tkachuk, V. M. (2022). Fluorescence Record Diagnostics of 3D Rough-Surface Landscapes With Nano-Scale Inhomogeneities, Front. Phys,
      doi:10.3389/fphy.2021.787821
    8. Zenkova, C. Yu., Ivansky, D. I., Tkachuk, V. M., and Jun Zheng. (2022). Structured Light in Applications Related to the Reconstruction of Three-Dimensional Landscape of Nanorough Surfaces, Optical Memory and Neural Networks, 31(1), 22-35.
      doi:10.3103/S1060992X22010118
    9. Angelsky, O., Bekshaev, A., Zenkova, C., Ivanskyi, D., Maksymyak, P., Kryvetsky, V., Zhebo Chen. (2023). Application of the Luminescent Carbon Nanoparticles for Optical Diagnostics of Structure-Inhomogeneous Objects at the Micro- and Nanoscales, Optical Memory and Neural Networks, 32(4), 258-274.
      doi:10.3103/S1060992X23040069
    10. Angelsky, O., Maksymyak, P., Zenkova, C., Ushenko, O., & Zheng, J. (2021). New Trends of Optical Measurements. In (Ed.), Applied Aspects of Modern Metrology, IntechOpen.
      doi:10.5772/intechopen.100589
    11. Angelsky, O.V., Maksymyak, P.P., Zenkova, C.Yu., Hanson, S.G., Jun Zheng. (2020). Current Trends in Development of Optical Metrology. Optical Memory & Neural Networks (Information Optics), 29(4), 269-292.
      doi:10.3103/S1060992X20040025
    12. Angelsky, O.V., Bekshaev, A.Y., Maksimyak, P.P, Mokhun, I.I., Zenkova, C.Y., Gotsulskiy, V.Y, Ivanskyi, D.I., Zheng, J. (2024). Correlation and singular optics for diagnostics of structured light and condensed matter: time-stationary and spatio-temporal approaches. Front. Phys. 12, 1383256.
      doi:10.3389/fphy.2024.1383256
    13. Zenkova, C. Yu., Gorsky, M. P., Ryabiy, P. A., Angelskaya, A O. (2016). Additional approaches to solving the phase problem in optics. Applied Optics , 55(12), B78-B84.
      doi:10.1364/AO.55.000B78
    14. Zenkova, C. Yu. (2014). Interconnection of polarization properties and coherence of optical fields. Applied Optics, 10, B43-B52.
      doi:10.1364/AO.53.000B43
    15. Zenkova, C. Yu., Yermolenko, S. B., Angelskaya, A. O., Soltys, I. V. (2011). The polarization peculiarities of the correlation (Intrinsic Coherence) of optical fields. Optical Memory and Neural Networks (Information Optics), 20(4), 247-254.
      doi:10.3103/S1060992X11040072
    16. Zenkova, C. Yu., Gorsky, M. P., Soltys, I. V., Angelsky, P. O. (2012). Influence of the Brownian movement on the motion of nano and micro-particles in the inhomogeneous optical field. Opto-Electronics Review, 20(3), 247-254.
      doi:10.2478/s11772-012-0030-1
    17. Angelsky, O. V., Bekshaev, A. Y., Zenkova, C. Yu., Ivansky, D. I., Zheng, J. (2022). Correlation Optics, Coherence and Optical Singularities: Basic Concepts and Practical Applications, Front. Phys.
      doi:10.3389/fphy.2022.924508
    18. Angelsky, O. V., Bekshaev, A. Y., Vasnetsov, M. V., Zenkova, C. Yu., Maksimyak, P. P., Zheng J. (2022). Optical phase singularities: Physical nature, manifestations and applications, Front. Phys.
      doi:10.3389/fphy.2022.1060787
    19. Nitsowich, B. M., Zenkova, C. Yu. (1995). Theory of optical bistability in the region of exciton resonances, Optical Engineering, 34(4), 1072-1078.
      doi:10.1117/12.197095
    20. Reza, M.H., Sibly, M.N.B., Rabbani, S.G. et al. (2026). A comprehensive review of convolutional neural networks: foundations, enhancements and applications, Neural Comput & Applic, 38, 56.
      doi:10.1007/s00521-025-11827-w
    21. Zhou, J., Cui, G., Hu, Sh., Zhang, Zh., Yang, Ch., Liu, Zh., Wang ,L., Li, Ch., Sun, M. (2020). Graph neural networks: A review of methods and applications, AI Open, 1, 57-81.
      doi:10.1016/j.aiopen.2021.01.001
    22. Sharma, A. and Sharma, A. (2025). Graph Neural Network (GNN) and its Application: A State-of-the-Art Survey, 2025 IEEE International Conference on Big Data (BigData), Macau, China, 6763-6772.
      doi:10.1109/BigData66926.2025.11401619
    23. Hussaine, S.M. (2025). Graph Neural Networks (GNNs) Applications. In: Chelliah, P.R., Whig, P., Nagarajan, S., Sakthivel, U., Yathiraju, N. (eds) Graph Neural Networks: Essentials and Use Cases. Springer, Cham.
      doi:10.1007/978-3-031-88538-9_7
    24. Zhang, S, Tong, H, Xu, J, Maciejewski, R.(2019). Graph convolutional networks: a comprehensive review. Comput Soc Netw., 6(1), 11.
      doi:10.1186/s40649-019-0069-y
    25. Wei, Yu., Wu, D. (2023). Model-based real-time prediction of surface roughness in fused deposition modeling with graph convolutional network-based error correction, Journal of Manufacturing Systems,71, 286-297.
      doi:10.1016/j.jmsy.2023.09.001
    26. Sourish, Gh., Knoblauch, R., Mansori, M.El., Corleto, Ci. (2024). Towards AI driven surface roughness evaluation in manufacturing: a prospective study, Journal of Intelligent Manufacturing, 36 (7), 4519-4548.
      doi:10.1007/s10845-024-02493-1
    27. Steege, T., Bernard, G., Darm, P., Kunze, T., Lasagni, A.F. (2023). Prediction of Surface Roughness in Functional Laser Surface Texturing Utilizing Machine Learning, Photonics, 10, 361.
      doi:10.3390/photonics10040361
    28. Sharma, A., Saini, R. S., Kaushik, A., Okshah, A., Kuruniyan, M.S., Gurumurthy, V., Vyas, R.,. Binduhayyim, R.I.H., Heboyan, A. (2025). Machine learning based approach for surface roughness prediction in precision dental prototyping, Scientific Reports, 15(1).
      doi:10.1038/s41598-025-17487-z
    29. Aglikov, A.S., Aliev, T.A., Zhukov, M.V., Nikitina, A.A., Smirnov, E., Kozodaev, D.A., Nosonovsky, M.I., Skorb, E.V. (2023). Topological Data Analysis of Nanoscale Roughness of Layer-by-Layer Polyelectrolyte Samples Using Machine Learning, ACS Appl. Electron. Mater.,5 (12), 6955-6963.
      doi:10.1021/acsaelm.3c01358
    30. Pylypko, V. G., Ivanitska, V. G., Khalavka, Y. B., and Krupko, O. V. (2025). Effect of oleylamine content on the optical properties of CsPbBr3 nanoparticles synthesized in the presence of various antisolvents, Proc. SPIE, 13813, 138132Z.
      doi:10.1117/12.3093136

    Запропоновано комплексний підхід до безконтактного, неруйнівного та високоточного аналізу розподілу неоднорідностей поверхні, який дозволяє прогнозувати реконструйований розподіл висоти поверхні з коефіцієнтами детермінації R² у діапазоні від 0,86 до 0,90 на основі розподілу інтенсивності фотолюмінесценції поверхнево осаджених перовськітних наночастинок. Наночастинки перовскіту розміром приблизно 5 нм використовувалися як функціональні маркери, що відтворюють топографічний профіль поверхні після осадження. Для аналізу та реконструкції розподілу висоти поверхонь з нано- та мікронеоднорідностями було розроблено модель машинного навчання на основі графових згорткових мереж (GCN). Модель була навчена на основі експериментальних даних, отриманих за допомогою атомно-силової мікроскопії, для визначення профілю висоти поверхні, а також вимірювань інтенсивності люмінесценції осаджених наночастинок.

    Ключові слова: наночастинки перовскіту, графові згорткові мережі, розподіл висоти, нано- та мікронеоднорідності

Free download this article 

This work is licensed under CC BY 4.0