AENET-LAMMPS and AENET-TINKER: Interfaces for Accurate and Efficient Molecular Dynamics Simulations with Machine Learning Potentials

TL;DR

This paper introduces two open-source interfaces connecting the Atomic Energy Network machine learning potentials with TINKER and LAMMPS, enabling accurate, efficient, and scalable molecular simulations of complex systems.

Contribution

The development of two novel interfaces that integrate AENET MLPs with TINKER and LAMMPS for improved molecular dynamics simulations.

Findings

The AENET-TINKER interface has nearly optimal shared-memory parallel efficiency.

The AENET-LAMMPS interface performs well on distributed memory systems.

Applications include diffusion in water and amorphous battery materials.

Abstract

Machine learning potentials (MLPs) trained on data from quantum-mechanics based first-principles methods can approach the accuracy of the reference method at a fraction of the computational cost. To facilitate efficient MLP-based molecular dynamics (MD) and Monte Carlo (MC) simulations, an integration of the MLPs with sampling software is needed. Here we develop two interfaces that link the Atomic Energy Network ({\ae}net) MLP package with the popular sampling packages TINKER and LAMMPS. The three packages, {\ae}net, TINKER, and LAMMPS, are free and open-source software that enable, in combination, accurate simulations of large and complex systems with low computational cost that scales linearly with the number of atoms. Scaling tests show that the parallel efficiency of the {\ae}net-TINKER interface is nearly optimal but is limited to shared-memory systems. The {\ae}net-LAMMPS interface achieves excellent parallel efficiency on highly parallel distributed memory systems and benefits from the highly optimized neighbor list implemented in LAMMPS. We demonstrate the utility of the two MLP interfaces for two relevant example applications, the investigation of diffusion phenomena in liquid water and the equilibration of nanostructured amorphous battery materials.