查看更多>>摘要：By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News Daily News – Investigators publish new report on Ma chine Learning. According to news reporting originating from Chennai, India, by NewsRx correspondents, research stated, “Thermoelectric materials play a pivotal role in harnessing waste heat and converting it into valuable electrical energy , addressing energy sustainability challenges. This study introduces an innovati ve methodology to predict essential thermoelectric properties-thermal conductivi ty (kappa), electrical conductivity (sigma), Seebeck coefficient (S), and the fi gure of merit (ZT)-solely from the chemical formula of materials.” Our news editors obtained a quote from the research from the Indian Institute of Technology (IIT) Madras, “Employing advanced machine learning (ML) techniques, including random forest, gradient boosting regression, XGBRegressor, and Neural Network, we developed a robust predictive model utilizing a diverse dataset of t hermoelectric compounds. Notably, random forest exhibits outstanding predictive performance, boasting R-2 values of 0.91, 0.95, 0.95, and 0.90 for kappa, sigma, S and ZT, respectively. While testing the prediction competency of thermoelectr ic parameters of Bi2Te1-xSex using a random forest model, the model provides a v ery consistent quantitative prediction with experimental kappa, sigma, S and ZT. Furthermore, the kappa, sigma, S and ZT of Bi2Te2Se were calculated using the f irst principles density functional theory and Boltzmann transport equation to co mpare the corresponding ML-predicted thermoelectric properties. Although the ord er of theoretical values of kappa, sigma, S and ZT of Bi2Te2Se is consistent wit h the room temperature ML prediction, the temperature-dependent theoretical valu e of kappa, sigma, S and ZT of Bi2Te2Se shows a deviation from the ML-prediction values as the model is trained with the experimental data. The findings highlig ht the superiority of classification-based models in capturing complex patterns. By leveraging chemical composition as the exclusive input, our streamlined appr oach eliminates the need for extensive laboratory experiments. This research sig nificantly propels the advancement of high-performance thermoelectric materials, offering an efficient pathway for exploration and optimization, thus revolution izing the field of materials science.”
NETL
NSTL