Library-Based LAMMPS Implementation of High-Dimensional Neural Network Potentials

A Singraber and J Behler and C Dellago, JOURNAL OF CHEMICAL THEORY AND COMPUTATION, 15, 1827-1840 (2019).

DOI: 10.1021/acs.jctc.8b00770

Neural networks and other machine learning approaches have been successfully used to accurately represent atomic interaction potentials derived from computationally demanding electronic structure calculations. Due to their low computational cost, such representations open the possibility for large scale reactive molecular dynamics simulations of processes with bonding situations that cannot be described accurately with traditional empirical force fields. Here, we present a library of functions developed for the implementation of neural network potentials. Written in C++, this library incorporates several strategies resulting in a very high efficiency of neural network potential-energy and force evaluations. Based on this library, we have developed an implementation of the neural network potential within the molecular dynamics package LAMMPS and demonstrate its performance using liquid water as a test system.

Return to Publications page