Machine-learning-accelerated simulations to enable automatic surface reconstruction

Abstract

Understanding material surfaces and interfaces is vital in applications like catalysis or electronics. By combining energies from electronic structure with statistical mechanics, ab initio simulations can in principle predict the structure of material surfaces as a function of thermodynamic variables. However, accurate energy simulations are prohibitive when coupled to the vast phase space that must be statistically sampled. Here, we present a bi-faceted computational loop to predict surface phase diagrams of multi-component materials that accelerates both the energy scoring and statistical sampling methods. Fast, scalable, and data-efficient machine learning interatomic potentials are trained on high-throughput density-functional theory calculations through closed-loop active learning. Markov-chain Monte Carlo sampling in the semi-grand canonical ensemble is enabled by using virtual surface sites. The predicted surfaces for GaN(0001), Si(111), and SrTiO3(001) are in agreement with past work and suggest that the proposed strategy can model complex material surfaces and discover previously unreported surface terminations.

arXiv comment30 pages main, 15 figures/tables, 5 pages supplementary

References in corpus (13)

• Global Optimization by Basin-Hopping and the Lowest Energy Structures of Lennard-Jones Clusters Containing up to 110 Atoms
• Composition, structure and stability of RuO_2(110) as a function of oxygen pressure
• Forces are not Enough: Benchmark and Critical Evaluation for Machine Learning Force Fields with Molecular Simulations
• Efficient global structure optimization with a machine learned surrogate model
• Single-model uncertainty quantification in neural network potentials does not consistently outperform model ensembles
• Differentiable sampling of molecular geometries with uncertainty-based adversarial attacks
• Global optimization of atomistic structure enhanced by machine learning
• Predicting interface structures: From SrTiO${}_3$ to graphene
• IrO2 Surface Complexions Identified Through Machine Learning and Surface Investigations
• Deep Ensembles vs. Committees for Uncertainty Estimation in Neural-Network Force Fields: Comparison and Application to Active Learning
• Unexpected Reconstruction of the alpha-Boron (111) Surface
• Atomistic structure search using local surrogate mode
• Prediction of surface reconstructions using MAGUS

Cited by in corpus (7)

• Accelerating the prediction of inorganic surfaces with machine learning interatomic potentials
• Optimal pre-train/fine-tune strategies for accurate material property predictions
• Surface Phase Diagrams from Nested Sampling
• On Boltzmann Averaging in Ab Initio Thermodynamics
• Leveraging transfer learning for accurate estimation of ionic migration barriers in solids
• Exploration of stable atomic configurations in graphene-like BCN systems by Bayesian optimization
• FreeBird.jl: An Extensible Toolbox for Simulating Interfacial Phase Equilibria