Ultrafast Sliding Ferroelectric Switching in Bilayer Hexagonal Boron Nitride Revealed by Deep Learning Molecular Dynamics

TL;DR

This study employs a novel deep learning-based atomistic simulation framework to demonstrate ultrafast, 5 picosecond ferroelectric switching in bilayer hexagonal boron nitride, aligning with experimental hysteresis observations.

Contribution

It introduces a data-driven, coupled machine learning and neural network approach for large-scale molecular dynamics simulations of ferroelectric switching.

Findings

Ultrafast 5 ps coherent single-domain sliding observed.

Simulated hysteresis loops match experimental shapes.

New atomistic insights into electric-field-driven polarization dynamics.

Abstract

Sliding ferroelectricity in bilayer hexagonal boron nitride (h-BN) offers compelling prospects for next-generation non-volatile memory, yet the atomistic dynamics of electric-field-driven polarization switching remain poorly understood. Here, we present a fully data-driven, coupled atomistic framework that integrates a fine-tuned MACE machine learning potential (MLP) with an equivariant graph convolutional neural network (EGCNN) for real-time Born effective charge (BEC) prediction, enabling large-scale non-equilibrium molecular dynamics simulations of AB-stacked bilayer h-BN under applied electric fields. By implementing a rigorous real-space path-integral polarization formalism combined with a state-constrained Gaussian convolution background extraction procedure, we successfully isolate the intrinsic spontaneous polarization from the dominant dielectric background. Our simulations reveal that coherent single-domain rigid sliding, completing within 5 ps, constitutes a physically viable ultrafast switching mechanism, and reproduces clean ferroelectric hysteresis loops whose shape is qualitatively consistent with experimental observations.