Topology-based Phase Identification of Bulk, Interface, and Confined Water using Edge-Conditioned Convolutional Graph Neural Network

TL;DR

This paper introduces a graph neural network approach to identify water phases in various systems, learning features directly from data, improving upon traditional order parameter methods.

Contribution

It develops a GNN-based methodology for water phase identification that generalizes better to heterogeneous systems compared to conventional order parameters.

Findings

GNN outperforms baseline methods in phase classification.

The approach effectively captures phase transitions in diverse water systems.

Learned features improve phase detection accuracy.

Abstract

Water plays a significant role in various physicochemical and biological processes. Understanding and identifying water phases in various systems such as bulk, interface, and confined water is crucial in improving and engineering state-of-the-art nano-devices. Various order parameters have been developed to distinguish water phases, including bond-order parameters, local structure index, and tetrahedral order parameters. These order parameters are often developed with the assumption of homogenous bulk systems, while most applications involve heterogeneous and non-bulk systems, thus, limiting their generalizability. Our study develops a methodology based on the graph neural network to distinguish water phases directly from data and to learn features instead of predefining them. We provide comparisons between baseline methods trained using conventional order-parameters as features, and a graph neural network model trained using radial distance and hydrogen-bonding information for phase classification and phase transition of water in bulk, interface, and confined systems with continuous and discontinuous phase transitions.