https://doi.org/10.1140/epjp/s13360-026-07371-8
Regular Article
An experimental/theoretical investigation of optical absorption properties for chalcogenide composition in thin-film form: prediction study using an artificial neural network model
Faculty of Education, Physics Department, Ain Shams University, 11771, Cairo, Roxy, Egypt
a
This email address is being protected from spambots. You need JavaScript enabled to view it.
Received:
17
September
2025
Accepted:
28
January
2026
Published online:
26
February
2026
Abstract
The compositional dependency of the optical characteristics of binary 
(SB) and ternary 
(SB–Te) chalcogenide compositions, prepared by melt-quenching technique, was investigated. The thermal evaporation approach was used to form these thin films on heated glass substrates under high vacuum conditions (~ 10−5 Torr). The X-ray diffraction technique was used to test the amorphous nature of the studied films chick the pattern (XRD). Energy-dispersive X-ray (EDX) analysis was employed to investigate the chemical composition of the samples that were prepared.The optical characteristics of the produced thin films through using a spectrophotometer to collect observational spectrum data for transmittance and reflectance ranging from 500 to 2500 nm wavelength. The transmission and absorption measurements were used to calculate the optical absorption coefficient (α) and the extinction coefficient (
). By analyzing the spectrum change in the dispersion properties, the optical energy gap 
and Urbach tail (
) were recently identified. This computation offers vital information on the material's electrical structure and disorder. The transition power factor n confirms that the indirect optical transition with 
decreases with the Te addition, which is in conjunction with the increase in (Eu) and the increase in the randomness of the films studied. The analysis of optical absorption constants (α), and () was used to determine some important optical factors, including the steepness parameter, optical density, skin depth, and metallization parameters, and study their composition dependence as well. Using experimental data, artificial neural networks (ANNs) were used to model the optical energy gap (
, and the extinction coefficient () for chalcogenide thin films. One of the soft computing methods that is important for modeling is ANNS. The mean squared error (MSE) values for various ANN configurations will be compared to determine the best ANN model configuration. In most cases, the 3-hidden layers ANN architecture produced the best results. The optical parameters in the range wavelengths that were not experimentally measured were also predicted using this method.
© The Author(s) 2026
Open Access This article is licensed under a Creative Commons Attribution 4.0 International License, which permits use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons licence, and indicate if changes were made. The images or other third party material in this article are included in the article's Creative Commons licence, unless indicated otherwise in a credit line to the material. If material is not included in the article's Creative Commons licence and your intended use is not permitted by statutory regulation or exceeds the permitted use, you will need to obtain permission directly from the copyright holder. To view a copy of this licence, visit http://creativecommons.org/licenses/by/4.0/.
