Integrating machine learning and experimental data in modeling optical behaviors of neodymium oxide nanoparticle-doped glasses

Nazrin, S. N. and Liyana Adilla, Burhanuddin and Halimah Badioze, Zaman and Faznny, Mohd Fudzi and Ibrahim, A. Shaaban (2025) Integrating machine learning and experimental data in modeling optical behaviors of neodymium oxide nanoparticle-doped glasses. THE EUROPEAN PHYSICAL JOURNAL. pp. 1-24. ISSN 1951-6401

PDF Integrating machine.pdf Download (2MB)

Abstract

Zinc tellurite doped with neodymium oxide nanoparticles (Nd2O3 NPs) glass series has been fabricated using conventional melt-quenching technique to explore the respective optical, structural, and physical properties of the glass material. Fourier-transform infra-red (FTIR) spectra and the respective deconvolution revealed changes in the amount of TeO3 and TeO4 structural units related to the concentration of neodymium oxide nanoparticles, which directly influences the amount of bridging oxygen and non-bridging oxygen in the glass system. The density of the prepared glasses possesses increasing trend with values that rose from 5346 to 5606 kg m−3 as more Nd2O3 NPs are incorporated in the glass matrix. The parameters for optical properties have also been determined, assisted and trained the chosen model in order to predict the data for optical properties of glass material with different chemical compositions via the machine learning approach. To enhance the experimental results, machine learning models were developed using linear regression (LR) and artificial neural networks (ANN). ANN model with its ability to capture both linear as well as non-linear interactions has outperformed the simulation and LR model as the ANN model had managed to accurately predict the values for the optical properties of glass material based on the compositional parameters. This underscores the effectiveness of ANN in modeling having intricate relationships between dopant concentrations and optical behaviors while at the same time providing critical insights for future advancements in doped glass technology.

Actions (For repository members only: login required)

View Item