| Autor: |
Panfilova, E. V., Ibragimov, A. R., Shramko, D. Y. |
| Předmět: |
|
| Zdroj: |
AIP Conference Proceedings; 2022, Vol. 2383/2470 Issue 1, p1-5, 5p |
| Abstrakt: |
The amplitude modulation or tapping mode of atomic force microscopy is often used in the study of a variety of nanostructures, thin films and nanoparticles. This mode is characterized by the complexity and duration of the settings for scanning samples. In the present work, it is proposed to use an artificial neural network model to determine the settings of the main parameters during intralaboratory studies of similar samples. When studying photonic crystal self-assembled colloidal films, the best results were obtained using a multilayer perceptron with one inner layer. The input was supplied with the values of eleven input parameters describing the properties of the colloidal suspension and substrate and film deposition methods and modes. The output parameters were three main custom scan options. It was revealed that the use of such a model significantly improves the quality of the obtained images and the accuracy of determining the main parameters of the geometry of photonic crystal films. [ABSTRACT FROM AUTHOR] |
| Databáze: |
Complementary Index |
| Externí odkaz: |
|
