Machine learning assisted predictions of multi-component phase diagrams and fine boundary information

A phase diagram is a critical tool in materials science, but establishing it often requires a large num-ber of experiments, especially for multi-component systems. In this work, we propose a machine learning strategy to accurately predict the phase diagram for the multi-component ferroelectric sys-tem (Ba1 -x -yCaxSry)(Ti1 -u -v -wZru SnvHfw)O3 by combining classification and regression methods. Based on literature data, we construct by classification a diagram that maps composition and temperature to the phase, and identify octahedral factor, Matyonov-Batsanov electronegativity, the ratio of valence electron number to nuclear charge and core electron distance (Schubert) for the A site and B site cations as the dominant physical descriptors. A neural network (NN) regression model is adopted to accurately predict phase transition temperatures, i.e. the phase boundaries, so that a phase dia-gram can be established in composition space. In the region of phase boundaries, the relative propor-tions of coexisting phases are also estimated by their prediction probability. The predicted phase la-bels, location boundaries and coexisting phase proportions are experimentally validated for the ceramic (Ba0.96Ca0.02Sr0.02)(Ti0.98 -xZr0.02Hfx)O3. Our work provides an effective approach to establish phase dia-grams for multi-component systems and also predict fine boundary information.(c) 2022 Acta Materialia Inc. Published by Elsevier Ltd. All rights reserved.

Automated summary

This study proposes a machine learning strategy to accurately predict the phase diagram of a multi-component ferroelectric system. By combining classification and regression methods, the composition and temperature are mapped to the phase. The neural network regression model accurately predicts the phase transition temperatures and establishes the phase diagram. The predicted results are experimentally validated.