Tin Telluride (SnTe) stands out among semiconductor materials, drawing attention as an environmentally friendly alternative to conventional Lead Telluride (PbTe). This study explores the novel incorporation of titanium (Ti) and zirconium (Zr) as dopant elements in SnTe-based materials, an approach that has never been previously investigated. Leveraging mathematical modeling and machine learning methodologies, we use Response Surface Methodology (RSM) and Artificial Neural Network-Genetic Algorithm (ANN-GA) to predict thermoelectric properties of SnTe-based materials and find the optimum dopant element addition and operating temperature. Eleven samples featuring varying Ti and Zr concentrations are employed in experimental investigations, with dopant amounts ranging from 0 to 0.05 M. Characterization of each sample is conducted across a temperature spectrum from 50 to 450 °C, yielding a comprehensive dataset of 99 entries for neural network model construction. The generated RSM and ANN models demonstrate remarkable predictive accuracy for the thermoelectric properties of SnTe-based materials, showcasing coefficient of determination (R2) values spanning from 0.986 to 0.998. This study uses RSM and ANN-GA to predict an optimized zT value of 0.558. This value surpasses the highest zT value from the experiment by 3.33 %. In conclusion, this investigation underscores the potency of RSM and ANN as valuable tools for advancing research on SnTe-based thermoelectric materials, exemplifying their capacity to hasten the exhausting process of finding the optimum dopant addition and operating temperature.
Read full abstract