Atom-Density Representations for Machine Learning

TL;DR

This paper introduces a unified, basis set independent framework for atomic environment representations in machine learning, leveraging smoothed atomic densities and inner products to improve efficiency and systematic tuning.

Contribution

It formalizes a basis set independent, density-based representation of atomic environments, connecting existing methods and enabling systematic optimization for materials and molecules.

Findings

Provides a formalism connecting SOAP and real-space correlations.

Lays groundwork for systematic tuning of representations.

Unifies recent developments in atomic environment representations.

Abstract

The applications of machine learning techniques to chemistry and materials science become more numerous by the day. The main challenge is to devise representations of atomic systems that are at the same time complete and concise, so as to reduce the number of reference calculations that are needed to predict the properties of different types of materials reliably. This has led to a proliferation of alternative ways to convert an atomic structure into an input for a machine-learning model. We introduce an abstract definition of chemical environments that is based on a smoothed atomic density, using a bra-ket notation to emphasize basis set independence and to highlight the connections with some popular choices of representations for describing atomic systems. The correlations between the spatial distribution of atoms and their chemical identities are computed as inner products between these feature kets, which can be given an explicit representation in terms of the expansion of the atom density on orthogonal basis functions, that is equivalent to the smooth overlap of atomic positions (SOAP) power spectrum, but also in real space, corresponding to $n$-body correlations of the atom density. This formalism lays the foundations for a more systematic tuning of the behavior of the representations, by introducing operators that represent the correlations between structure, composition, and the target properties. It provides a unifying picture of recent developments in the field and indicates a way forward towards more effective and computationally affordable machine-learning schemes for molecules and materials.