IceCoder: Identification of Ice phases in molecular simulation using variational autoencoder

Abstract: The identification and classification of different phases of ice within molecular simulations is a challenging task due to the complex and varied phase space of ice, which includes numerous crystalline and amorphous forms. Traditional order parameters often struggle to differentiate between these phases, especially under conditions of thermal fluctuations. In this work, we present a novel machine learning-based framework, \textit{IceCoder}, which combines a variational autoencoder (VAE) with the Smooth Overlap of Atomic Positions (SOAP) descriptor to classify a large number of ice phases effectively. Our approach compresses high-dimensional SOAP vectors into a two-dimensional latent space using VAE, facilitating the visualization and distinction of various ice phases. We trained the model on a comprehensive dataset generated through molecular dynamics (MD) simulations and demonstrated its ability to accurately detect various phases of crystalline ice as well as liquid water at the molecular level. IceCoder provides a robust and generalizable tool for tracking ice phase transitions in simulations, overcoming limitations of traditional methods. This approach may be generalized to detect polymorphs in other molecular crystals as well, leading to new insights into the microscopic mechanisms underlying nucleation, growth, and phase transitions, while maintaining computational efficiency.