Machine-learning-accelerated simulations to enable automatic surface reconstruction
This work addresses the challenge of computationally expensive surface simulations for materials science applications like catalysis or electronics, representing an incremental improvement through acceleration methods.
The authors tackled the problem of predicting material surface structures by accelerating both energy scoring and statistical sampling in simulations, achieving results that match past work for GaN(0001), Si(111), and SrTiO3(001) and suggesting the ability to discover new surface terminations.
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.