Machine learning short-ranged many-body interactions in colloidal systems using descriptors based on Voronoi cells

TL;DR

This paper introduces a Voronoi-based machine learning approach to efficiently model local many-body interactions in colloidal systems, demonstrated on a 2D colloid-polymer mixture, highlighting the importance of comprehensive metrics for model validation.

Contribution

The paper presents a novel Voronoi descriptor-based neural network method for capturing local many-body interactions in colloids, improving simulation accuracy.

Findings

Voronoi descriptors effectively capture many-body interactions.

Pearson correlation alone is insufficient for model validation.

Method accurately models a 2D colloid-polymer system.

Abstract

Machine learning (ML) strategies are opening the door to faster computer simulations, allowing us to simulate more realistic colloidal systems. Since the interactions in colloidal systems are often highly many-body, stemming from e.g. depletion and steric interactions, one of the challenges for these algorithms is capturing the many-body nature of these interactions. In this paper, we introduce a new ML-based strategy for fitting many-body interactions in colloidal systems where the many-body interaction is highly local. To this end, we develop Voronoi-based descriptors for capturing the local environment and fit the effective potential using a simple neural network. To test this algorithm, we consider a simple two-dimensional model for a colloid-polymer mixture, where the colloid-colloid interactions and colloid-polymer interactions are hard-disk like, while the polymers themselves interact as ideal gas particles. We find that a Voronoi-based description is sufficient to accurately capture the many-body nature of this system. Moreover, we find that the Pearson correlation function alone is insufficient to determine the predictive power of the network emphasizing the importance of additional metrics when assessing the quality of ML-based potentials.