Physics-inspired structural representations for molecules and materials

TL;DR

This review discusses how physics-inspired structural representations of molecules and materials are crucial for machine learning models, emphasizing their development, connections, and applications in chemistry and materials science.

Contribution

It provides a comprehensive overview of current structural representations, highlighting their physical and mathematical foundations, and discusses future research directions in the field.

Findings

Deep connections between different structural frameworks

Examples of applications in diverse chemical problems

Identification of open questions and promising research areas

Abstract

The first step in the construction of a regression model or a data-driven analysis, aiming to predict or elucidate the relationship between the atomic scale structure of matter and its properties, involves transforming the Cartesian coordinates of the atoms into a suitable representation. The development of atomic-scale representations has played, and continues to play, a central role in the success of machine-learning methods for chemistry and materials science. This review summarizes the current understanding of the nature and characteristics of the most commonly used structural and chemical descriptions of atomistic structures, highlighting the deep underlying connections between different frameworks, and the ideas that lead to computationally efficient and universally applicable models. It emphasizes the link between properties, structures, their physical chemistry and their mathematical description, provides examples of recent applications to a diverse set of chemical and materials science problems, and outlines the open questions and the most promising research directions in the field.