ArcaNN: automated enhanced sampling generation of training sets for chemically reactive machine learning interatomic potentials

TL;DR

ArcaNN is a new automated framework that generates high-quality training datasets for reactive machine learning interatomic potentials, improving their accuracy in simulating chemical reactions.

Contribution

It introduces a comprehensive, automated approach combining advanced sampling and iterative training for reactive potential development, addressing a key gap in dataset construction.

Findings

Demonstrated effective sampling of high-energy geometries in a nucleophilic substitution reaction

Achieved uniformly low error of the MLP along the reaction coordinate

Showcased broad applicability for reactive molecular dynamics simulations

Abstract

The emergence of artificial intelligence has profoundly impacted computational chemistry, particularly through machine-learned potentials (MLPs), which offer a balance of accuracy and efficiency in calculating atomic energies and forces to be used in molecular dynamics simulations. These MLPs have significantly advanced molecular dynamics simulations across various applications, including large-scale simulations of materials, interfaces, and chemical reactions. Despite these advances, the construction of training datasets - a critical component for the accuracy of MLPs - has not received proportional attention. This is particularly critical for chemical reactivity which depends on rare barrier-crossing events. Here we address this gap by introducing ArcaNN, a comprehensive framework designed for generating training datasets for reactive MLPs. ArcaNN employs a concurrent learning approach combined with advanced sampling techniques to ensure accurate representation of high-energy geometries. The framework integrates automated processes for iterative training, exploration, new configuration selection, and energy and force labeling, while ensuring reproducibility and documentation. We demonstrate ArcaNN's capabilities through a paradigm nucleophilic substitution reaction in solution, showcasing its effectiveness, the uniformly low error of the resulting MLP everywhere along the chemical reaction coordinate, and its potential for broad applications in reactive molecular dynamics. We also provide guidelines on how to assess the quality of a NNP for a reactive system.