Search

Machine learning (ML) methods are of rapidly growing interest for materials modeling, and yet, the use of ML interatomic potentials for new systems is often more demanding than that of established density-functional theory (DFT) packages. Here, we describe computational methodology to combine the CASTEP first-principles simulation software with the on-the-fly fitting and evaluation of ML interatomic potential models. Our approach is based on regular checking against DFT reference data, which provides a direct measure of the accuracy of the evolving ML model. We discuss the general framework and the specific solutions implemented, and we present an example application to high-temperature molecular-dynamics simulations of carbon nanostructures. The code is freely available for academic research. [ABSTRACT FROM AUTHOR]

Studies of supercooled liquid phase‐change materials are important for the development of phase‐change memory and neuromorphic computing devices. Herein, a machine‐learning (ML)‐based interatomic potential for Ge2Sb2Te5 (GST) to conduct large‐scale molecular dynamics simulations of liquid and supercooled liquid GST is used. A pronounced effect of the thermostat parameters on the simulation results is demonstrated, and it is shown how using a Langevin thermostat with optimized damping values can lead to excellent agreement with reference ab initio molecular dynamics (AIMD) simulations. Structural and dynamical analyses are presented, including the studies of radial and angular distributions, homopolar bonds, and the temperature‐dependent diffusivity. Herein, the usefulness of ML‐driven molecular dynamics for further studies of supercooled liquid GST, with length and timescales far exceeding those that are accessible to AIMD is demonstrated. [ABSTRACT FROM AUTHOR]

Understanding the thermal properties of disordered systems is of fundamental importance for condensed matter physics - and for practical applications as well. While quantities such as the thermal conductivity are usually well characterised experimentally, their microscopic origin is often largely unknown - hence the pressing need for molecular simulations. However, the time and length scales involved with thermal transport phenomena are typically well beyond the reach of ab initio calculations. On the other hand, many amorphous materials are characterised by a complex structure, which prevents the construction of classical interatomic potentials. One way to get past this deadlock is to harness machine-learning (ML) algorithms to build interatomic potentials: these can be nearly as computationally efficient as classical force fields while retaining much of the accuracy of first-principles calculations. Here, we discuss neural network potentials (NNPs) and Gaussian approximation potentials (GAPs), two popular ML frameworks. We review the work that has been devoted to investigate, via NNPs, the thermal properties of phase-change materials, systems widely used in non-volatile memories. In addition, we present recent results on the vibrational properties of amorphous carbon, studied via GAPs. In light of these results, we argue that ML-based potentials are among the best options available to further our understanding of the vibrational and thermal properties of complex amorphous solids. [ABSTRACT FROM AUTHOR]