Surface reconstructions and premelting of the (100) CaF2 surface

Data-Driven Machine Learning for Understanding Surface Structures of Heterogeneous Catalysts

The design of heterogeneous catalysts is necessarily surface-focused, generally achieved via optimization of adsorption energy and microkinetic modelling. A prerequisite is to ensure the adsorption energy is physically meaningful is the stable existence of the conceived active-site structure on the surface. The development of improved understanding of the catalyst surface, however, is challenging practically because of the complex nature of dynamic surface formation and evolution under in-situ reactions. We propose therefore data-driven machine-learning (ML) approaches as a solution. In this Minireview we summarize recent progress in using machine-learning to search and predict (meta)stable structures, assist operando simulation under reaction conditions and micro-environments, and critically analyze experimental characterization data. We conclude that ML will become the new norm to lower costs associated with discovery and design of optimal heterogeneous catalysts.

A fourth-generation high-dimensional neural network potential with accurate electrostatics including non-local charge transfer

Machine learning potentials have become an important tool for atomistic simulations in many fields, from chemistry via molecular biology to materials science. Most of the established methods, however, rely on local properties and are thus unable to take global changes in the electronic structure into account, which result from long-range charge transfer or different charge states. In this work we overcome this limitation by introducing a fourth-generation high-dimensional neural network potential that combines a charge equilibration scheme employing environment-dependent atomic electronegativities with accurate atomic energies. The method, which is able to correctly describe global charge distributions in arbitrary systems, yields much improved energies and substantially extends the applicability of modern machine learning potentials. This is demonstrated for a series of systems representing typical scenarios in chemistry and materials science that are incorrectly described by current methods, while the fourth-generation neural network potential is in excellent agreement with electronic structure calculations.

Machine learning potentials do not account for long-range charge transfer. Here the authors introduce a fourth-generation high-dimensional neural network potential including non-local information of charge populations that is able to provide forces, charges and energies in excellent agreement with DFT data.

Combining Machine Learning Potential and Structure Prediction for Accelerated Materials Design and Discovery

The theoretical structure prediction method via quantum mechanical atomistic simulations such as density functional theory (DFT), based solely on chemical composition, has already become a routine tool to determine the structures of physical and chemical systems, e.g., solids and clusters. However, the application of DFT to more realistic simulations, to a large extent, is impeded because of the unfavorable scaling of the computational cost with respect to the system size. During recent years, the machine learning potential (MLP) method has been rapidly rising as an accurate and efficient tool for atomistic simulations. In this Perspective, we provide an introduction to the basic principles and advantages of the combination of structure prediction and MLP, as well as the challenges and opportunities associated with this promising approach.

Hierarchically Structured Allotropes of Phosphorus from Data-Driven Exploration

The discovery of materials is increasingly guided by quantum-mechanical crystal-structure prediction, but the structural complexity in bulk and nanoscale materials remains a bottleneck. Here we demonstrate how data-driven approaches can vastly accelerate the search for complex structures, combining a machine-learning (ML) model for the potential-energy surface with efficient, fragment-based searching. We use the characteristic building units observed in Hittorf's and fibrous phosphorus to seed stochastic ("random") structure searches over hundreds of thousands of runs. Our study identifies a family of hierarchically structured allotropes based on a P8 cage as principal building unit, including one-dimensional (1D) single and double helix structures, nanowires, and two-dimensional (2D) phosphorene allotropes with square-lattice and kagome topologies. These findings yield new insight into the intriguingly diverse structural chemistry of phosphorus, and they provide an example for how ML methods may, in the long run, be expected to accelerate the discovery of hierarchical nanostructures.

Guidelines for creating artificial neural network empirical interatomic potential from first-principles molecular dynamics data under specific conditions and its application to α-Ag2Se

First-principles molecular dynamics (FPMD) simulations are highly accurate, but due to their high calculation cost, the computational scale is often limited to hundreds of atoms and few picoseconds under specific temperature and pressure conditions. We present here the guidelines for creating artificial neural network empirical interatomic potential (ANN potential) trained with such a limited FPMD data, which can perform long time scale MD simulations at least under the same conditions. The FPMD data for training are prepared on the basis of the convergence of radial distribution function [g(r)]. While training the ANN using total energy and atomic forces of the FPMD data, the error of pressure is also monitored and minimized. To create further robust potential, we add a small amount of FPMD data to reproduce the interaction between two atoms that are close to each other. ANN potentials for α-Ag₂Se were created as an application example, and it has been confirmed that not only g(r) and mean square displacements but also the specific heat requiring a long time scale simulation matched the FPMD and the experimental values. In addition, the MD simulation using the ANN potential achieved over 10⁴ acceleration over the FPMD one. The guidelines proposed here mitigate the creation difficulty of the ANN potential, and a lot of FPMD data sleeping on the hard disk after the research may be put on the front stage again.