Understanding chemical reactions via variational autoencoder and atomic representations

TL;DR

This paper introduces an unsupervised variational autoencoder approach that automatically generates robust collective variables from atomic representations, improving the sampling of rare chemical reactions in atomistic simulations.

Contribution

The method automatically derives collective variables from atomic representations using VAEs, applicable to complex reactions and unseen structure prediction, without manual variable selection.

Findings

Successfully applied to three different chemical reactions.

Demonstrated effectiveness in complex hydrolysis of aluminosilicate.

Enabled efficient generation of structures for various collective variable values.

Abstract

On the time scales accessible to atomistic numerical modelling, chemical reactions are considered rare events. Atomistic simulations are typically biased along a low-dimensional representation of a chemical reaction in an atomic structure space, i.e., along the collective variable, to accelerate sampling of these improbable events. However, suitable collective variables are often complicated to guess due to the complexity of the transitions. Therefore, we present an automatic method of generating robust collective variables from atomic representation vectors, using either fixed Behler-Parrinello functions or representations extracted from pre-trained machine learning potentials. Variational autoencoder with these representations as inputs is trained while its latent space with arbitrary dimension gives us the set of collective variables. The resulting collective variables inherit all necessary invariances from the atomic representations and can be trained entirely unsupervised. The method's effectiveness is demonstrated using three different chemical reactions, one being the complex hydrolysis of a heterogeneous aluminosilicate catalyst. Lastly, we consider the method in the context of unseen atomic structure prediction, efficiently creating structures for different values of collective variables in a generative model fashion.