Prediction of the Curie temperatures of ferroelectric solid solutions using machine learning methods

Evan M. Askanazi, Suhas Yadav, Ilya Grinberg

Research output: Contribution to journalArticlepeer-review

10 Scopus citations

Abstract

In this work, we studied the application of machine learning for the prediction of the Curie temperature (Tc) of ferroelectric BiMe′Me′′O3-PbTiO3 systems (where Me′ and Me′′ are metal cations). We found that among the studied K-nearest neighbor (KNN), support vector regression (SVR) and random forest (RF) methods, RF obtains the best performance and is insensitive to the choice of hyperparameters. SVR results show a strong sensitivity to the choice of hyperparameters and obtained Tc predictions with significantly lower accuracy than RF even after hyperparameter optimization. KNN results show poor accuracy and are essentially unusable with an incomplete feature set and are only qualitatively accurate with a complete feature set. With regard to the choice of features for accurate prediction of the Ferroelectric (FE) systems, we find that Bi content and B-cation valence, ionic radius and ionic displacements form the irreducible set of features such that these features or their equivalents must be used to obtain quantitatively accurate Tc predictions. We also find that homovalent and heterovalent BiMe′Me′′O3-PbTiO3 solid solutions form distinct classes of compounds with different behaviors so that both types must be included in the input data set to obtain high predictive accuracy. Our work confirms that for the small data sets typically available in materials science, careful selection of the input system, features and ML methods is required to enable accurate model construction and discovery of previously unknown relationships, but can be achieved in a systematic manner.

Original languageEnglish
Article number110730
JournalComputational Materials Science
Volume199
DOIs
StatePublished - Nov 2021

Bibliographical note

Publisher Copyright:
© 2021 Elsevier B.V.

Funding

This work was supported by the Israel Science Foundation.

FundersFunder number
Israel Science Foundation

    Keywords

    • Computational materials
    • Ferroelectrics
    • Machine learning
    • Solid Solutions

    Fingerprint

    Dive into the research topics of 'Prediction of the Curie temperatures of ferroelectric solid solutions using machine learning methods'. Together they form a unique fingerprint.

    Cite this