Comparative analysis of machine learning techniques in predicting dielectric behavior of ternary chalcogenide thin films

Abstract

The current research introduces a comparative analysis of the dielectric behavior exhibited by ternary chalcogenide thin films, including both experimental data and machine learning techniques. The study of temperature and frequency dependencies of dielectric parameters is crucial for assessing material losses, particularly focusing on the low-frequency range where dielectric dispersion occurs. The experimental results on the frequency (100–1000000 Hz)and the temperature(303 –393 K) influences on the dielectric (constant (ε1) and loss (ε2)) of As4Ge24Te72 composition in thin film form have been discussed. Results demonstrate that ε₁ exhibits an increasing trend with temperature, attributed to heightened orientation polarization as dipoles gain mobility with elevated thermal energy. Conversely, ε₁ declines with rising frequency, reflecting diverse different polarization mechanisms. Understanding these behaviors is important for material characterization and applications in fields like electronics and solar cells. A comparative analysis of the dielectric behavior exhibited by ternary chalcogenide thin films, including both experimental data and machine learning techniques. Through the experimental approach, the dielectric properties of the films are investigated. Additionally, the study employs a range of machine learning algorithms, including Artificial Neural Networks (ANN), Adaptive Neuro-Fuzzy Inference Systems (ANFIS), Genetic Programming (GP), hybrid techniques ANFIS-GA, and ANFIS-PSO, to model and predict the dielectric behavior with remarkable accuracy. The paper presents a comparison between the performance of the proposed machine learning models, highlighting their strengths and limitations in capturing the complex dielectric phenomena observed in the ternary chalcogenide thin films. This comparative study not only provides valuable insights into the dielectric properties of these materials but also demonstrates the efficacy of machine learning in understanding and predicting their behavior, paving the way for further advancements in materials science and device development.