Dead or alive: Distinguishing active from passive particles using supervised learning ^(a)

Abstract

A longstanding open question in the field of dense disordered matter is how precisely structure and dynamics are related to each other. With the advent of machine learning, it has become possible to agnostically predict the dynamic propensity of a particle in a dense liquid based on its local structural environment. Thus far, however, these machine-learning studies have focused almost exclusively on simple liquids composed of passive particles. Here we consider a mixture of both passive and active (i.e.\ self-propelled) Brownian particles, with the aim to identify the active particles from minimal local structural information. We compare a state-of-the-art machine learning approach for passive systems with a new method we develop based on Voronoi tessellation. Both methods accurately identify the active particles based on their structural properties at high activity and low concentrations of active particles. Our Voronoi method is, however, substantially faster to train and deploy because it requires fewer, and easy to compute, input features. Notably, both become ineffective when the activity is low, suggesting a fundamentally different structural signature for dynamic propensity and non-equilibrium activity. Ultimately, these efforts might also find relevance in the context of biological active glasses such as confluent cell layers, where subtle changes in the microstructure can hint at pathological changes in cell dynamics.

Voronoi spatial pattern construction through bacterial colony simulation

“…More along the lines of machine learning, Voronoi diagrams can also be used to extract characteristic in images, and then achieve classification tasks. 30 An essential consideration is that gene expression decreases as distance increases due to the Hill function 8 (sigmoid shaped). The simulations work with cells in a two-dimensional environment (2D), where quorum sensing exhibits a sigmoidal function.…”

Classifying the age of a glass based on structural properties: A machine learning approach

“…Cubuk et al introduced a machine learning microscopic structural quantity, the socalled softness, which characterizes the local structure around each particle. Based on this approach, several recent works [30][31][32][33][34][35][36][37][38][39][40][41] extended our conceptual understanding of glassy liquids by convincingly demonstrating that machine learning is able to accurately connect structural properties with the corresponding dynamics. In particular, standard machine learning tools like support vector machines have been able to compute the relaxation time through softness [42] and collective effects like fragility [36] and low-temperature defects [43].…”