# Disentangling autoencoders and spherical harmonics for efficient shape classification in crystal growth simulations

## TL;DR

The paper introduces a machine learning framework combining autoencoders and spherical harmonics to efficiently analyze and design crystal shapes in simulations.

## Contribution

The novel approach uses disentangled autoencoders and spherical harmonics to map crystal morphology transformations while preserving crystallographic principles.

## Key findings

- The method reduces data analysis burdens in crystal growth simulations.
- It enables continuous transformation pathways between crystal morphologies.
- The framework improves the design of crystalline materials with desired properties.

## Abstract

Controlling crystal growth is a challenge across numerous industries, as the functional properties of crystalline materials are determined during formation and often depend on particle shape. Current approaches rely on expensive, time-consuming experimental studies complemented by exhaustive parameter space simulations, creating significant computational and analytical burdens. Despite machine learning advances in crystal growth for structure-property relationships, applications targeting morphological control remain underdeveloped. Here, we demonstrate how disentangling autoencoders combined with particle aspect ratio and spherical harmonics descriptors can enhance simulation workflows for crystal growth. This approach reveals continuous transformation pathways between different crystal morphologies whilst preserving underlying crystallographic principles. Our method significantly reduces data analytics burdens, shortens design study timelines, and deepens understanding of crystal shape control. This framework enables more efficient exploration of possible crystal morphologies, facilitating the targeted design of crystalline materials with specific functional properties.

Crystal growth simulations generate vast datasets that are difficult to analyse using traditional methods alone. By combining disentangling autoencoders with spherical harmonic descriptors, the authors create an interpretable system that maps continuous transformations between crystal morphologies while preserving underlying crystallographic principles.