Metadynamics sampling in atomic environment space for collecting training data for machine learning potentials

TL;DR

This paper introduces a semi-automatic metadynamics sampling method using local atomic environment descriptors to efficiently generate diverse training data for machine learning potentials, reducing manual effort and redundancy.

Contribution

The novel sampling approach leverages metadynamics with atomic environment descriptors to automatically explore diverse configurations for training MLPs.

Findings

Efficiently generates diverse training data with fewer trajectories.

Applicable to various systems like H:Pt(111), GeTe, and Si.

Enables high-fidelity MLP training with minimal manual intervention.

Abstract

The universal mathematical form of machine-learning potentials (MLPs) shifts the core of development of interatomic potentials to collecting proper training data. Ideally, the training set should encompass diverse local atomic environments but the conventional approach is prone to sampling similar configurations repeatedly, mainly due to the Boltzmann statistics. As such, practitioners handpick a large pool of distinct configurations manually, stretching the development period significantly. Herein, we suggest a novel sampling method optimized for gathering diverse yet relevant configurations semi-automatically. This is achieved by applying the metadynamics with the descriptor for the local atomic environment as a collective variable. As a result, the simulation is automatically steered toward unvisited local environment space such that each atom experiences diverse chemical environments without redundancy. We apply the proposed metadynamics sampling to H:Pt(111), GeTe, and Si systems. Throughout the examples, a small number of metadynamics trajectories can provide reference structures necessary for training high-fidelity MLPs. By proposing a semi-automatic sampling method tuned for MLPs, the present work paves the way to wider applications of MLPs to many challenging applications.