Machine learning interatomic potentials (IPs) can provide accuracy close to that of first-principles methods, such as density functional theory (DFT), at a fraction of the computational cost. This greatly extends the scope of accurate molecular simulations, providing opportunities for quantitative design of materials and devices on scales hitherto unreachable by DFT methods. However, machine learning IPs have a basic limitation in that they lack a physical model for the phenomena being predicted and therefore have unknown accuracy when extrapolating outside their training set. In this paper, we propose a class of Dropout Uncertainty Neural Network (DUNN) potentials that provide rigorous uncertainty estimates that can be understood from both Bayesian and frequentist statistics perspectives. As an example, we develop a DUNN potential for carbon and show how it can be used to predict uncertainty for static and dynamical properties, including stress and phonon dispersion in graphene. We demonstrate two approaches to propagate uncertainty in the potential energy and atomic forces to predicted properties. In addition, we show that DUNN uncertainty estimates can be used to detect configurations outside the training set, and in some cases, can serve as a predictor for the accuracy of a calculation.
Monolayer and multilayer graphene are promising materials for applications such as electronic devices, sensors, energy generation and storage, and medicine. In order to perform large-scale atomistic simulations of the mechanical and thermal behavior of graphene-based devices, accurate interatomic potentials are required. Here, we present an interatomic potential for multilayer graphene structures referred to as “.” This hybrid potential employs a neural network to describe short-range interactions and a theoretically motivated analytical term to model long-range dispersion. The potential is trained against a large dataset of monolayer graphene, bilayer graphene, and graphite configurations obtained from ab initio total-energy calculations based on density functional theory (DFT). The potential provides accurate energy and forces for both intralayer and interlayer interactions, correctly reproducing DFT results for structural, energetic, and elastic properties such as the equilibrium layer spacing, interlayer binding energy, elastic moduli, and phonon dispersions to which it was not fit. The potential is used to study the effect of vacancies on thermal conductivity in monolayer graphene and interlayer friction in bilayer graphene. The potential is available through the openkim interatomic potential repository at https://openkim.org.
20 March 2024 in The Journal of Physical Chemistry B
Two-dimensional molybdenum disulfide (MoS2) is a promising material for the next generation of switchable transistors and photodetectors. In order to perform large-scale molecular simulations of the mechanical and thermal behavior of MoS2-based devices, an accurate interatomic potential is required. To this end, we have developed a Stillinger-Weber potential for monolayer MoS2. The potential parameters are optimized to reproduce the geometry (bond lengths and bond angles) of MoS2 in its equilibrium state and to match as closely as possible the forces acting on the atoms along a dynamical trajectory obtained from ab initio molecular dynamics. Verification calculations indicate that the new potential accurately predicts important material properties including the strain dependence of the cohesive energy, the elastic constants, and the linear thermal expansion coefficient. The uncertainty in the potential parameters is determined using a Fisher information theory analysis. It is found that the parameters are fully identified, and none are redundant. In addition, the Fisher information matrix provides uncertainty bounds for predictions of the potential for new properties. As an example, bounds on the average vibrational thickness of a MoS2 monolayer at finite temperature are computed and found to be consistent with the results from a molecular dynamics simulation. The new potential is available through the OpenKIM interatomic potential repository at https://openkim.org/cite/MO_201919462778_000.
14 November 2023 in Journal of Chemical Theory and Computation