Machine Learning Reveals Memory of the Parent Phases in Ferroelectric Relaxors Ba(Ti1−x$_{1-x}$,Zrx)O3.

Machine learning has been establishing its potential in multiple areas of condensed matter physics and materials science. Here an unsupervised machine learning workflow is developed and used within a framework of first‐principles‐based atomistic simulations to investigate phases, phase transitions, and their structural origins in ferroelectric relaxors, Ba(Ti1−x$_{1-x}$,Zrx)O3. The applicability of the workflow is first demonstrated to identify phases and phase transitions in the parent compound, a prototypical ferroelectric BaTiO3. Then the workflow is applied for Ba(Ti1−x$_{1-x}$,Zrx)O3 with x≤0.25$x\le 0.25$ to reveal i) that some of the compounds bear a subtle memory of BaTiO3 phases beyond the point of the pinched phase transition, which could contribute to their enhanced electromechanical response; ii) the existence of peculiar phases with delocalized precursors of nanodomains—likely candidates for the controversial polar nanoregions; and iii) nanodomain phases for the largest concentrations of x. [ABSTRACT FROM AUTHOR]