Bayesian Force Fields from Active Learning for Simulation of Inter-Dimensional Transformation of Stanene

Abstract

We present a way to dramatically accelerate Gaussian process models for interatomic force fields based on many-body kernels by mapping both forces and uncertainties onto functions of low-dimensional features. This allows for automated active learning of models combining near-quantum accuracy, built-in uncertainty, and constant cost of evaluation that is comparable to classical analytical models, capable of simulating millions of atoms. Using this approach, we perform large scale molecular dynamics simulations of the stability of the stanene monolayer. We discover an unusual phase transformation mechanism of 2D stanene, where ripples lead to nucleation of bilayer defects, densification into a disordered multilayer structure, followed by formation of bulk liquid at high temperature or nucleation and growth of the 3D bcc crystal at low temperature. The presented method opens possibilities for rapid development of fast accurate uncertainty-aware models for simulating long-time large-scale dynamics of complex materials.

arXiv comment30 pages of main text, 14 pages of supplementary materials, 9 figures in total

References in corpus (29)

• Gaussian Approximation Potentials: the accuracy of quantum mechanics, without the electrons
• On representing chemical environments
• Deep Potential Molecular Dynamics: a scalable model with the accuracy of quantum mechanics
• SchNet - a deep learning architecture for molecules and materials
• 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
• Epitaxial Growth of Two-Dimensional Stanene
• Moment Tensor Potentials: a class of systematically improvable interatomic potentials
• Optimized Tersoff and Brenner empirical potential parameters for lattice dynamics and phonon thermal transport in carbon nanotubes and graphene
• A Spectral Analysis Method for Automated Generation of Quantum-Accurate Interatomic Potentials
• A Performance and Cost Assessment of Machine Learning Interatomic Potentials
• Less is more: sampling chemical space with active learning
• Active learning of linearly parametrized interatomic potentials
• Towards Exact Molecular Dynamics Simulations with Machine-Learned Force Fields
• On-the-fly machine learning force field generation: Application to melting points
• Phase transitions of hybrid perovskites simulated by machine-learning force fields trained on-the-fly with Bayesian inference
• SchNet: A continuous-filter convolutional neural network for modeling quantum interactions
• SchNetPack: A Deep Learning Toolbox For Atomistic Systems
• Materials Cloud, a platform for open computational science
• Nucleation mechanism for the direct graphite-to-diamond phase transition
• Deep Potential: a general representation of a many-body potential energy surface
• Superconductivity in Few-Layer Stanene
• Accurate Interatomic Force Fields via Machine Learning with Covariant Kernels
• Melting temperature of graphene
• Fast and Accurate Uncertainty Estimation in Chemical Machine Learning
• Melting of graphene: from two to one dimension
• Efficient nonparametric $n$-body force fields from machine learning
• Fast Neural Network Approach for Direct Covariant Forces Prediction in Complex Multi-Element Extended Systems
• Building nonparametric $n$-body force fields using Gaussian process regression

Cited by in corpus (8)

• Active learning of reactive Bayesian force fields: Application to heterogeneous hydrogen-platinum catalysis dynamics
• Fast Uncertainty Estimates in Deep Learning Interatomic Potentials
• Data-driven simulation and characterisation of gold nanoparticle melting
• CIDER: An Expressive, Nonlocal Feature Set for Machine Learning Density Functionals with Exact Constraints
• Nonlocal Machine-Learned Exchange Functional for Molecules and Solids
• A machine learning potential for simulating infrared spectra of nanosilicate clusters
• Modeling refractory high-entropy alloys with efficient machine-learned interatomic potentials: defects and segregation
• Comparing the latent features of universal machine-learning interatomic potentials