LeaPP: Learning Pathways to Polymorphs through machine learning analysis of atomic trajectories

TL;DR

This paper introduces a machine learning-based methodology to analyze atomic trajectories, capturing diverse nucleation pathways and predicting resulting polymorphs, thus providing a detailed understanding of crystal formation mechanisms.

Contribution

The study presents a novel deep learning approach to classify nucleation pathways and predict polymorphs from atomic trajectory data, addressing limitations of static snapshot analysis.

Findings

Effectively captures diverse structural pathways in crystallization.

Enables prediction of polymorphs from nucleation trajectories.

Provides a nuanced view of crystal nucleation mechanisms.

Abstract

Understanding the mechanisms underlying crystal formation is crucial. For most systems, crystallization typically goes through a nucleation process that involves dynamics that happen at short time and length scales. Due to this, molecular dynamics serves as a powerful tool to study this phenomenon. Existing approaches to study the mechanism often focus analysis on static snapshots of the global configuration, potentially overlooking subtle local fluctuations and history of the atoms involved in the formation of solid nuclei. To address this limitation, we propose a methodology that categorizes nucleation pathways into reactive pathways based on the time evolution of constituent atoms. Our approach effectively captures the diverse structural pathways explored by crystallizing Lennard-Jones-like particles and solidifying Ni$_3$Al, providing a more nuanced understanding of nucleating pathways. Moreover, our methodology enables the prediction of the resulting polymorph from each reactive trajectory. This deep learning-assisted comprehensive analysis offers an alternative view of crystal nucleation mechanisms and pathways.