Deep Learning of Accurate Force Field of Ferroelectric HfO${}_2$

Abstract

The discovery of ferroelectricity in HfO${}_2$-based thin films opens up new opportunities for using this silicon-compatible ferroelectric to realize low-power logic circuits and high-density non-volatile memories. The functional performances of ferroelectrics are intimately related to their dynamic responses to external stimuli such as electric fields at finite temperatures. Molecular dynamics is an ideal technique for investigating dynamical processes on large length and time scales, though its applications to new materials is often hindered by the limited availability and accuracy of classical force fields. Here we present a deep neural network-based interatomic force field of HfO${}_2$ learned from {\em ab initio} data using a concurrent learning procedure. The model potential is able to predict structural properties such as elastic constants, equation of states, phonon dispersion relationships, and phase transition barriers of various hafnia polymorphs with accuracy comparable with density functional theory calculations. The validity of this model potential is further confirmed by the reproduction of experimental sequences of temperature-driven ferroelectric-paraelectric phase transitions of HfO${}_2$ with isobaric-isothermal ensemble molecular dynamics simulations. We suggest a general approach to extend the model potential of HfO${}_2$ to related material systems including dopants and defects.

References in corpus (23)

• On representing chemical environments
• Deep Potential Molecular Dynamics: a scalable model with the accuracy of quantum mechanics
• DeePMD-kit: A deep learning package for many-body potential energy representation and molecular dynamics
• ANI-1: An extensible neural network potential with DFT accuracy at force field computational cost
• DP-GEN: A concurrent learning platform for the generation of reliable deep learning based potential energy models
• The Origin of Ferroelectricity in Hf${}_x$ Zr${}_{1-x}$ O${}_2$: A Computational Investigation and a Surface Energy Model
• Pathways Towards Ferroelectricity in Hafnia
• Active Learning of Uniformly Accurate Inter-atomic Potentials for Materials Simulation
• How van der Waals interactions determine the unique properties of water
• Machine learning a general purpose interatomic potential for silicon
• Neural Network Based in Silico Simulation of Combustion Reactions
• Antiferroelectricity in thin film ZrO2 from first principles
• A neural network interatomic potential for the phase change material GeTe
• A learning scheme to predict atomic forces and accelerate materials simulations
• Machine Learning Inter-Atomic Potentials Generation Driven by Active Learning: A Case Study for Amorphous and Liquid Hafnium dioxide
• Ab initio quality neural-network potential for sodium
• Effects of Growth Orientations and Epitaxial Strains on Phase Stability of HfO${}_2$ Thin Films
• Isotope Effects in Liquid Water via Deep Potential Molecular Dynamics
• Machine-learning based interatomic potential for phonon transport in perfect crystalline Si and crystalline Si with vacancies
• Reinterpretation of bond-valence model with bond-order formalism: an improved bond-valence based interatomic potential for PbTiO${}_3$
• A computational study of hafnia-based ferroelectric memories: from ab initio via physical modeling to circuit models of ferroelectric device
• Optimization and Validation of a Deep Learning CuZr Atomistic Potential: Robust Applications for Crystalline and Amorphous Phases with near-DFT Accuracy
• Machine learning the DFT potential energy surface for inorganic halide perovskite CsPbBr${}_3$

Cited by in corpus (20)

• Deep Potentials for Materials Science
• Structural Phase Transitions in SrTiO3 from Deep Potential Molecular Dynamics
• Heat transport in liquid water from first-principles and deep-neural-network simulations
• Progress in Computational Understanding of Ferroelectric Mechanisms in HfO${}_2$
• Ultrahigh oxygen ion mobility in ferroelectric hafnia
• Viscosity in water from first-principles and deep-neural-network simulations
• Phonons in magic-angle twisted bilayer graphene
• Modular development of deep potential for complex solid solutions
• Universal interatomic potential for perovskite oxides
• Theoretical approach to ferroelectricity in hafnia and related materials
• Machine-learning interatomic potential for molecular dynamics simulation of ferroelectric KNbO3 perovskite
• Finite-temperature properties of antiferroelectric perovskite $\mathrm{PbZr}{\mathrm{O}}_3$ from deep learning interatomic potential
• Origin of Interstitial Doping Induced Coercive Field Reduction in Ferroelectric Hafnia
• Recent Advances in Unconventional Ferroelectrics and Multiferroics
• Theoretical lower limit of coercive field in ferroelectric hafnia
• A neural-network-backed effective harmonic potential study of the ambient pressure phases of hafnia
• Self-healing mechanism of lithium in lithium metal batteries
• Considerations in the use of ML interaction potentials for free energy calculations
• Accurate force field of two-dimensional ferroelectrics from deep learning
• The ground state of CuInP${}_2$S${}_6$ thin films: A study of the deep potential method