Artificial neural networks represent an accurate and efficient tool to construct high-dimensional potential-energy surfaces based on first-principles data. However, so far the main drawback of this method has been the limitation to a single atomic species. We present a generalization to compounds of arbitrary chemical composition, which now enables simulations of a wide range of systems containing large numbers of atoms. The required incorporation of long-range interactions is achieved by combining the numerical accuracy of neural networks with an electrostatic term based on environment-dependent charges. Using zinc oxide as a benchmark system we show that the neural network potential-energy surface is in excellent agreement with density-functional theory reference calculations, while the evaluation is many orders of magnitude faster.
Machine-learning potentials (MLPs) for atomistic simulations are a promising alternative to conventional classical potentials. Current approaches rely on descriptors of the local atomic environment with dimensions that increase quadratically with the number of chemical species. In this paper, we demonstrate that such a scaling can be avoided in practice. We show that a mathematically simple and computationally efficient descriptor with constant complexity is sufficient to represent transition-metal oxide compositions and biomolecules containing 11 chemical species with a precision of around 3 meV/atom. This insight removes a perceived bound on the utility of MLPs and paves the way to investigate the physics of previously inaccessible materials with more than ten chemical species.
The atomic environments at metal surfaces differ strongly from the bulk, and, in particular, in case of reconstructions or imperfections at ``real surfaces,'' very complicated atomic configurations can be present. This structural complexity poses a significant challenge for the development of accurate interatomic potentials suitable for large-scale molecular dynamics simulations. In recent years, artificial neural networks (NN) have become a promising new method for the construction of potential-energy surfaces for difficult systems. In the present work, we explore the applicability of such high-dimensional NN potentials to metal surfaces using copper as a benchmark system. A detailed analysis of the properties of bulk copper and of a wide range of surface structures shows that NN potentials can provide results of almost density functional theory (DFT) quality at a small fraction of the computational costs.
Structure plays a vital role in determining materials properties. In lithium ion cathode materials, the crystal structure defines the dimensionality and connectivity of interstitial sites, thus determining lithium ion diffusion kinetics. In most conventional cathode materials that are well-ordered, the average structure as seen in diffraction dictates the lithium ion diffusion pathways. Here, we show that this is not the case in a class of recently discovered high-capacity lithium-excess rocksalts. An average structure picture is no longer satisfactory to understand the performance of such disordered materials. Cation short-range order, hidden in diffraction, is not only ubiquitous in these long-range disordered materials, but fully controls the local and macroscopic environments for lithium ion transport. Our discovery identifies a crucial property that has previously been overlooked and provides guidelines for designing and engineering cation-disordered cathode materials.