Recent advances in describing and driving crystal nucleation using machine learning and artificial intelligence

TL;DR

This review discusses how machine learning and AI techniques have advanced the understanding and modeling of crystal nucleation, addressing key challenges like reaction coordinate discovery, force field development, phase identification, and coarse-grained modeling.

Contribution

It provides a comprehensive overview of recent ML and AI applications in crystal nucleation, highlighting new methods for reaction coordinates, force fields, phase detection, and modeling.

Findings

ML improves reaction coordinate discovery

AI enhances force field accuracy for polymorphs

Advanced methods enable better phase identification

Abstract

With the advent of faster computer processors and especially graphics processing units (GPUs) over the last few decades, the use of data-intensive machine learning (ML) and artificial intelligence (AI) has increased greatly, and the study of crystal nucleation has been one of the beneficiaries. In this review, we outline how ML and AI have been applied to address four outstanding difficulties of crystal nucleation: how to discover better reaction coordinates (RCs) for describing accurately non-classical nucleation situations; the development of more accurate force fields for describing the nucleation of multiple polymorphs or phases for a single system; more robust identification methods for determining crystal phases and structures; and as a method to yield improved course-grained models for studying nucleation.