Predicting thermoelectric transport properties from composition with attention-based deep learning

Abstract

Thermoelectric materials can be used to construct devices which recycle waste heat into electricity. However, the best known thermoelectrics are based on rare, expensive or even toxic elements, which limits their widespread adoption. To enable deployment on global scales, new classes of effective thermoelectrics are thus required. Ab initio models of transport properties can help in the design of new thermoelectrics, but they are still too computationally expensive to be solely relied upon for high-throughput screening in the vast chemical space of all possible candidates. Here, we use models constructed with modern machine learning techniques to scan very large areas of inorganic materials space for novel thermoelectrics, using composition as an input. We employ an attention-based deep learning model, trained on data derived from ab initio calculations, to predict a material’s Seebeck coefficient, electrical conductivity, and power factor over a range of temperatures and n- or p-type doping levels, with surprisingly good performance given the simplicity of the input, and with significantly lower computational cost. The results of applying the model to a space of known and hypothetical binary and ternary selenides reveal several materials that may represent promising thermoelectrics. Our study establishes a protocol for composition-based prediction of thermoelectric behaviour that can be easily enhanced as more accurate theoretical or experimental databases become available.

Regression-Based Machine Learning for Predicting Lifting Movement Pattern Change in People with Low Back Pain

“…For instance, regression machine learning has been used to predict stock prices [ 12 ], diagnose diseases [ 13 ], forecast weather patterns [ 14 , 15 ], and assess molecular similarity [ 16 ]. In addition, regression machine learning has been used to optimise processes and improve decision making in industries such as manufacturing and transportation [ 17 , 18 , 19 , 20 ]. Some studies have suggested that machine learning algorithms, particularly regression models, may have the potential to predict treatment outcomes based on patient characteristics and movement patterns [ 21 ].…”