GPUMD: A package for constructing accurate machine-learned potentials and performing highly efficient atomistic simulations

Abstract

We present our latest advancements of machine-learned potentials (MLPs) based on the neuroevolution potential (NEP) framework introduced in [Fan et al., Phys. Rev. B 104, 104309 (2021)] and their implementation in the open-source package gpumd. We increase the accuracy of NEP models both by improving the radial functions in the atomic-environment descriptor using a linear combination of Chebyshev basis functions and by extending the angular descriptor with some four-body and five-body contributions as in the atomic cluster expansion approach. We also detail our efficient implementation of the NEP approach in graphics processing units as well as our workflow for the construction of NEP models, and we demonstrate their application in large-scale atomistic simulations. By comparing to state-of-the-art MLPs, we show that the NEP approach not only achieves above-average accuracy but also is far more computationally efficient. These results demonstrate that the gpumd package is a promising tool for solving challenging problems requiring highly accurate, large-scale atomistic simulations. To enable the construction of MLPs using a minimal training set, we propose an active-learning scheme based on the latent space of a pre-trained NEP model. Finally, we introduce two separate Python packages, gpyumd and calorine, which enable the integration of gpumd into Python workflows.

Anisotropic mechanical properties of monolayer fullerene network: An interplay between two types of interfullerene bonds

“…Under this circumstance, machine-learning potential (MLP)-based molecular dynamics (MD) simulations were utilized here to conduct these tensile simulations at room temperature (300 K). Specifically, the NEP potential for carbon materials [42] was applied to describe the atomic interactions in qHP C60 membrane. As an MLP fitted from the quantum mechanical calculations using the neural network framework [43,44], the NEP potential for carbon materials could accurately capture the bond nature of both sp 2 and sp 3 hybridization between carbon atoms [42].…”

“…Specifically, the NEP potential for carbon materials [42] was applied to describe the atomic interactions in qHP C60 membrane. As an MLP fitted from the quantum mechanical calculations using the neural network framework [43,44], the NEP potential for carbon materials could accurately capture the bond nature of both sp 2 and sp 3 hybridization between carbon atoms [42]. All the MLP-based MD simulations were performed using the open-source package GPUMD [45] with a time step of 1.0 fs.…”

Quantum-corrected thickness-dependent thermal conductivity in amorphous silicon predicted by machine-learning molecular dynamics simulations

“…However, thermal transport usually involves large length and long time scales and GAP18 is not currently efficient enough for this purpose. The NEP model as implemented in the gpumd package [27,28], on the other hand, can reach a computational speed of about 5 × 10 6 atom-step per second for a-Si by using a single GPU card such as Tesla V100, which is about three orders of magnitude faster than GAP18 using 72 Xeon-Gold 6240 central processing unit (CPU) cores [18].…”