Learning microstructure in active matter

TL;DR

This paper introduces a novel approach combining simulations, neural networks, and symbolic regression to predict microstructure in active matter, achieving accurate closed-form expressions that match detailed simulations.

Contribution

It presents a new, efficient method for deriving analytical expressions for microstructure in active matter systems, bridging simulations and theory.

Findings

Closed-form expressions closely match Brownian dynamics simulations.

Method effective at high packing fractions and strong activity.

Broadly applicable to nonequilibrium systems.

Abstract

Understanding microstructure in terms of closed-form expressions is an open challenge in nonequilibrium statistical physics. We propose a simple and generic method that combines particle-resolved simulations, deep neural networks and symbolic regression to predict the pair-correlation function of passive and active particles. Our analytical closed-form results closely agree with Brownian dynamics simulations, even at relatively large packing fractions and for strong activity. The proposed method is broadly applicable, computationally efficient, and can be used to enhance the predictive power of nonequilibrium continuum theories and for designing pattern formation.