Dead or alive: Distinguishing active from passive particles using supervised learning

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.

References in corpus (21)

• Active Particles in Complex and Crowded Environments
• Active Brownian Particles. From Individual to Collective Stochastic Dynamics
• Scaling behavior in the $\beta$-relaxation regime of a supercooled Lennard-Jones mixture
• Identifying structural flow defects in disordered solids using machine learning methods
• Active matter
• Inertial effects of self-propelled particles: from active Brownian to active Langevin motion
• Convolutional neural networks automate detection for tracking of submicron scale particles in 2D and 3D
• Measurement of Anomalous Diffusion Using Recurrent Neural Networks
• On the Study of Collective Dynamics in Supercooled Liquids through the Statistics of the Iso-Configurational Ensemble
• Unsupervised learning for local structure detection in colloidal systems
• Nonequilibrium dynamics of mixtures of active and passive colloidal particles
• Mode-Coupling Theory for Active Brownian Particles
• Averaging local structure to predict the dynamic propensity in supercooled liquids
• Anomalous glassy dynamics in simple models of dense biological tissue
• Assessing the structural heterogeneity of supercooled liquids through community inference
• Bias- and bath-mediated pairing of particles driven through a quiescent medium
• Attractive versus truncated repulsive supercooled liquids: The dynamics is encoded in the pair correlation function
• Dimensionality reduction of local structure in glassy binary mixtures
• Improving the prediction of glassy dynamics by pinpointing the local cage
• Correlation of plastic events with local structure in jammed packings across spatial dimensions
• Quantifying the link between local structure and cellular rearrangements using information in models of biological tissues

Cited by in corpus (6)

• Roadmap on machine learning glassy dynamics
• Classifying the age of a glass based on structural properties: A machine learning approach
• Selecting Relevant Structural Features for Glassy Dynamics by Information Imbalance
• Shape matters: Inferring the motility of confluent cells from static images
• Active Matter as a framework for living systems-inspired Robophysics
• Interpretability of linear regression models of glassy dynamics