Domain Switching on the Pareto Front: Multi-Objective Deep Kernel Learning in Automated Piezoresponse Force Microscopy

TL;DR

This paper presents a multi-objective kernel-learning framework that analyzes high-resolution imaging data to uncover microstructural rules governing ferroelectric switching, enabling high-throughput active learning and mechanistic insights.

Contribution

It introduces a novel multi-objective deep kernel learning workflow for analyzing PFM data to understand microstructural influences on polarization switching.

Findings

Identifies key relationships between domain-wall configurations and switching kinetics.

Reveals how defect distributions affect polarization reversal.

Provides a generalizable approach for complex, non-differentiable design spaces.

Abstract

Ferroelectric polarization switching underpins the functional performance of a wide range of materials and devices, yet its dependence on complex local microstructural features renders systematic exploration by manual or grid-based spectroscopic measurements impractical. Here, we introduce a multi-objective kernel-learning workflow that infers the microstructural rules governing switching behavior directly from high-resolution imaging data. Applied to automated piezoresponse force microscopy (PFM) experiments, our framework efficiently identifies the key relationships between domain-wall configurations and local switching kinetics, revealing how specific wall geometries and defect distributions modulate polarization reversal. Post-experiment analysis projects abstract reward functions, such as switching ease and domain symmetry, onto physically interpretable descriptors including domain configuration and proximity to boundaries. This enables not only high-throughput active learning, but also mechanistic insight into the microstructural control of switching phenomena. While demonstrated for ferroelectric domain switching, our approach provides a powerful, generalizable tool for navigating complex, non-differentiable design spaces, from structure-property correlations in molecular discovery to combinatorial optimization across diverse imaging modalities.