Jörg Behler

Atom-centered symmetry functions for constructing high-dimensional neural network potentials

Neural networks offer an unbiased and numerically very accurate approach to represent high-dimensional ab initio potential-energy surfaces. Once constructed, neural network potentials can provide the energies and forces many orders of magnitude faster than electronic structure calculations, and thus enable molecular dynamics simulations of large systems. However, Cartesian coordinates are not a good choice to represent the atomic positions, and a transformation to symmetry functions is required. Using simple benchmark systems, the properties of several types of symmetry functions suitable for the construction of high-dimensional neural network potential-energy surfaces are discussed in detail. The symmetry functions are general and can be applied to all types of systems such as molecules, crystalline and amorphous solids, and liquids.

Nucleation mechanism for the direct graphite-to-diamond phase transition.

Graphite and diamond have comparable free energies, yet forming diamond from graphite in the absence of a catalyst requires pressures that are significantly higher than those at equilibrium coexistence. At lower temperatures, the formation of the metastable hexagonal polymorph of diamond is favoured instead of the more stable cubic diamond. These phenomena cannot be explained by the concerted mechanism suggested in previous theoretical studies. Using an ab initio quality neural-network potential, we carried out a large-scale study of the graphite-to-diamond transition assuming that it occurs through nucleation. The nucleation mechanism accounts for the observed phenomenology and reveals its microscopic origins. We demonstrate that the large lattice distortions that accompany the formation of diamond nuclei inhibit the phase transition at low pressure, and direct it towards the hexagonal diamond phase at higher pressure. The proposed nucleation mechanism should improve our understanding of structural transformations in a wide range of carbon-based materials.

Representing potential energy surfaces by high-dimensional neural network potentials

The development of interatomic potentials employing artificial neural networks has seen tremendous progress in recent years. While until recently the applicability of neural network potentials (NNPs) has been restricted to low-dimensional systems, this limitation has now been overcome and high-dimensional NNPs can be used in large-scale molecular dynamics simulations of thousands of atoms. NNPs are constructed by adjusting a set of parameters using data from electronic structure calculations, and in many cases energies and forces can be obtained with very high accuracy. Therefore, NNP-based simulation results are often very close to those gained by a direct application of first-principles methods. In this review, the basic methodology of high-dimensional NNPs will be presented with a special focus on the scope and the remaining limitations of this approach. The development of NNPs requires substantial computational effort as typically thousands of reference calculations are required. Still, if the problem to be studied involves very large systems or long simulation times this overhead is regained quickly. Further, the method is still limited to systems containing about three or four chemical elements due to the rapidly increasing complexity of the configuration space, although many atoms of each species can be present. Due to the ability of NNPs to describe even extremely complex atomic configurations with excellent accuracy irrespective of the nature of the atomic interactions, they represent a general and therefore widely applicable technique, e.g. for addressing problems in materials science, for investigating properties of interfaces, and for studying solvation processes.

Perspective: Machine learning potentials for atomistic simulations

Nowadays, computer simulations have become a standard tool in essentially all fields of chemistry, condensed matter physics, and materials science. In order to keep up with state-of-the-art experiments and the ever growing complexity of the investigated problems, there is a constantly increasing need for simulations of more realistic, i.e., larger, model systems with improved accuracy. In many cases, the availability of sufficiently efficient interatomic potentials providing reliable energies and forces has become a serious bottleneck for performing these simulations. To address this problem, currently a paradigm change is taking place in the development of interatomic potentials. Since the early days of computer simulations simplified potentials have been derived using physical approximations whenever the direct application of electronic structure methods has been too demanding. Recent advances in machine learning (ML) now offer an alternative approach for the representation of potential-energy surfaces by fitting large data sets from electronic structure calculations. In this perspective, the central ideas underlying these ML potentials, solved problems and remaining challenges are reviewed along with a discussion of their current applicability and limitations.

Nonadiabatic effects in the dissociation of oxygen molecules at the Al(111) surface

The measured low initial sticking probability of oxygen molecules at the Al(111) surface that had puzzled the field for many years was recently explained in a nonadiabatic picture invoking spin-selection rules [J. Behler et al., Phys. Rev. Lett. 94, 036104 (2005)]. These selection rules tend to conserve the initial spin-triplet character of the free

How van der Waals interactions determine the unique properties of water

{\mathrm{O}}_{2}

Representing molecule-surface interactions with symmetry-adapted neural networks

molecule during the molecules approach to the surface. A locally constrained density-functional theory approach gave access to the corresponding potential-energy surface (PES) seen by such an impinging spin-triplet molecule and indicated barriers to dissociation which reduce the sticking probability. Here, we further substantiate this nonadiabatic picture by providing a detailed account of the employed approach. Building on the previous work, we focus, in particular, on inaccuracies in present-day exchange-correlation functionals. Our analysis shows that small quantitative differences in the spin-triplet constrained PES obtained with different gradient-corrected functionals have a noticeable effect on the lowest kinetic energy part of the resulting sticking curve.

A Density-Functional Theory-Based Neural Network Potential for Water Clusters Including van der Waals Corrections

Significance Despite its simple chemical formula, H2O, water is a complex substance with a variety of unusual properties resulting from its ability to form hydrogen bonds. A famous example for the anomalous behavior of water is the fact that it exhibits a density maximum at 4 °C. Here, we unravel the density anomaly of water on the molecular level using a powerful ab initio-based simulation technique. We show that weak van der Waals forces crucially modulate the flexibility of the hydrogen bond network, giving rise to the density maximum in water and causing ice to be less dense than the liquid. Whereas the interactions between water molecules are dominated by strongly directional hydrogen bonds (HBs), it was recently proposed that relatively weak, isotropic van der Waals (vdW) forces are essential for understanding the properties of liquid water and ice. This insight was derived from ab initio computer simulations, which provide an unbiased description of water at the atomic level and yield information on the underlying molecular forces. However, the high computational cost of such simulations prevents the systematic investigation of the influence of vdW forces on the thermodynamic anomalies of water. Here, we develop efficient ab initio-quality neural network potentials and use them to demonstrate that vdW interactions are crucial for the formation of water’s density maximum and its negative volume of melting. Both phenomena can be explained by the flexibility of the HB network, which is the result of a delicate balance of weak vdW forces, causing, e.g., a pronounced expansion of the second solvation shell upon cooling that induces the density maximum.

Structure determination of small vanadium clusters by density-functional theory in comparison with experimental far-infrared spectra

The accurate description of molecule-surface interactions requires a detailed knowledge of the underlying potential-energy surface (PES). Recently, neural networks (NNs) have been shown to be an efficient technique to accurately interpolate the PES information provided for a set of molecular configurations, e.g., by first-principles calculations. Here, we further develop this approach by building the NN on a new type of symmetry functions, which allows to take the symmetry of the surface exactly into account. The accuracy and efficiency of such symmetry-adapted NNs is illustrated by the application to a six-dimensional PES describing the interaction of oxygen molecules with the Al(111) surface.

Neural network interatomic potential for the phase change material GeTe

The fundamental importance of water for many chemical processes has motivated the development of countless efficient but approximate water potentials for large-scale molecular dynamics simulations, from simple empirical force fields to very sophisticated flexible water models. Accurate and generally applicable water potentials should fulfill a number of requirements. They should have a quality close to quantum chemical methods, they should explicitly depend on all degrees of freedom including all relevant many-body interactions, and they should be able to describe molecular dissociation and recombination. In this work, we present a high-dimensional neural network (NN) potential for water clusters based on density-functional theory (DFT) calculations, which is constructed using clusters containing up to 10 monomers and is in principle able to meet all these requirements. We investigate the reliability of specific parametrizations employing two frequently used generalized gradient approximation (GGA) exchange-correlation functionals, PBE and RPBE, as reference methods. We find that the binding energy errors of the NN potentials with respect to DFT are significantly lower than the typical uncertainties of DFT calculations arising from the choice of the exchange-correlation functional. Further, we examine the role of van der Waals interactions, which are not properly described by GGA functionals. Specifically, we incorporate the D3 scheme suggested by Grimme (J. Chem. Phys. 2010, 132, 154104) in our potentials and demonstrate that it can be applied to GGA-based NN potentials in the same way as to DFT calculations without modification. Our results show that the description of small water clusters provided by the RPBE functional is significantly improved if van der Waals interactions are included, while in case of the PBE functional, which is well-known to yield stronger binding than RPBE, van der Waals corrections lead to overestimated binding energies.