Machine learning identified materials descriptors for ferroelectricity

With aid of good materials descriptors, machine learning algorithms are able to accelerate the design of new materials and uncover underlying mechanisms. In the present study, we adopt machine learning methods to discover the most important materials descriptors for properties of ferroelectric materials. A regression study, in typical BaTiO3-based and K1/2Na1/2NbO3-based lead-free ceramics and lead-contained PbMg1/3Nb2/3TiO3-PbTiO3 ceramics, screens out three important materials descriptors determining ferroelectricity from 46 potential descriptors. The three descriptors of Matyonov-Batsanov electronegativity, ratio of valence electron number to nominal charge and core electron distance (Schubert) are confirmed to be dominant as well in classification of perovskite compounds into antiferroelectrics or not. The classification based on these descriptors exhibit an excellent accuracy of 96%, much higher than that of traditional criterion (89%) using tolerance factor and Pauling electronegativity. Furthermore, we propose a machine learning strategy based on our descriptors to predict the phase coexistence. The prediction probability after bootstrapping provides an effective approach to distinguish the phase boundaries and predict the phase ratio of coexisted phases. In all, we identified materials descriptors for ferroelectric materials, which is helpful to reveal the structure-property relationship of ferroelectric materials and guide the design of better ferroelectricity and piezoelectricity. (C) 2021 Acta Materialia Inc. Published by Elsevier Ltd. All rights reserved.

Automated summary

By utilizing machine learning methods, this study identified important materials descriptors for ferroelectric materials and selected key descriptors in different materials. These descriptors can accurately classify perovskite compounds and provide an effective strategy for predicting phase coexistence.