Accelerated search for new ferroelectric materials

TL;DR

This paper introduces a combined machine-learning and high-throughput DFT framework to efficiently identify and characterize new ferroelectric materials based solely on elemental composition, significantly speeding up discovery.

Contribution

The novel integrated approach predicts stable ferroelectric compounds and their polarization properties using machine learning and DFT, surpassing traditional trial-and-error methods.

Findings

Successfully identified new candidate ferroelectric materials.

Predicted polarization values with high accuracy.

Accelerated the discovery process compared to conventional methods.

Abstract

We report the development of a combined machine-learning and high-throughput density functional theory (DFT) framework to accelerate the search for new ferroelectric materials. The framework can predict potential ferroelectric compounds using only elemental composition as input. A series of machine-learning algorithms initially predict the possible stable and insulating stoichiometries with a polar crystal structure, necessary for ferroelectricity, within a given chemical composition space. A classification model then predicts the point groups of these stoichiometries. A subsequent series of high-throughput DFT calculations finds the lowest energy crystal structure within the point group. As a final step, non-polar parent structures are identified using group theory considerations, and the values of the spontaneous polarization are calculated using DFT. By predicting the crystal structures and the polarization values, this method provides a powerful tool to explore new ferroelectric materials beyond those in existing databases.