Generator of Neural Network Potential for Molecular Dynamics: Constructing Robust and Accurate Potentials with Active Learning for Nanosecond-scale Simulations

TL;DR

This paper introduces an active learning-based generator for neural network potentials that enhances the stability and accuracy of long-duration molecular dynamics simulations of large organic systems, achieving nanosecond-scale durations.

Contribution

The authors developed an integrated active learning framework to automatically generate robust neural network potentials capable of stable long-duration MD simulations.

Findings

Enables stable 20 ns MD simulations of >10,000 atoms

Achieves physical property predictions in excellent agreement with experiments

Improves stability by focusing on unstable structures with short interatomic distances

Abstract

Neural network potentials (NNPs) enable large-scale molecular dynamics (MD) simulations of systems containing >10,000 atoms with the accuracy comparable to ab initio methods and play a crucial role in material studies. Although NNPs are valuable for short-duration MD simulations, maintaining the stability of long-duration MD simulations remains challenging due to the uncharted regions of the potential energy surface (PES). Currently, there is no effective methodology to address this issue. To overcome this challenge, we developed an automatic generator of robust and accurate NNPs based on an active learning (AL) framework. This generator provides a fully integrated solution encompassing initial dataset creation, NNP training, evaluation, sampling of additional structures, screening, and labeling. Crucially, our approach uses a sampling strategy that focuses on generating unstable structures with short interatomic distances, combined with a screening strategy that efficiently samples these configurations based on interatomic distances and structural features. This approach greatly enhances the MD simulation stability, enabling nanosecond-scale simulations. We evaluated the performance of our NNP generator in terms of its MD simulation stability and physical properties by applying it to liquid propylene glycol (PG) and polyethylene glycol (PEG). The generated NNPs enable stable MD simulations of systems with >10,000 atoms for 20 ns. The predicted physical properties, such as the density and self-diffusion coefficient, show excellent agreement with the experimental values. This work represents a remarkable advance in the generation of robust and accurate NNPs for organic materials, paving the way for long-duration MD simulations of complex systems.