Analyzing Collective Motion with Machine Learning and Topology

Abstract

We use topological data analysis and machine learning to study a seminal model of collective motion in biology [D'Orsogna et al., Phys. Rev. Lett. 96 (2006)]. This model describes agents interacting nonlinearly via attractive-repulsive social forces and gives rise to collective behaviors such as flocking and milling. To classify the emergent collective motion in a large library of numerical simulations and to recover model parameters from the simulation data, we apply machine learning techniques to two different types of input. First, we input time series of order parameters traditionally used in studies of collective motion. Second, we input measures based in topology that summarize the time-varying persistent homology of simulation data over multiple scales. This topological approach does not require prior knowledge of the expected patterns. For both unsupervised and supervised machine learning methods, the topological approach outperforms the one that is based on traditional order parameters.

Published in Chaos 29, 123125 (2019), DOI: 10.1063/1.5125493

References in corpus (11)

• Collective motion
• A roadmap for the computation of persistent homology
• Self-organization in systems of self-propelled particles
• Clique topology reveals intrinsic geometric structure in neural correlations
• State Transitions and the Continuum Limit for a 2D Interacting, Self-Propelled Particle System
• Confidence sets for persistence diagrams
• Topological Data Analysis of Biological Aggregation Models
• Topological data analysis of contagion maps for examining spreading processes on networks
• Nonparametric inference of interaction laws in systems of agents from trajectory data
• Robust Topological Inference: Distance To a Measure and Kernel Distance
• Swarming in viscous fluids: three-dimensional patterns in swimmer- and force-induced flows

Cited by in corpus (10)

• Bridging from single to collective cell migration: A review of models and links to experiments
• Topological data analysis distinguishes parameter regimes in the Anderson-Chaplain model of angiogenesis
• Topological data analysis and machine learning
• Minimal Cycle Representatives in Persistent Homology using Linear Programming: an Empirical Study with User's Guide
• Learning Anisotropic Interaction Rules from Individual Trajectories in a Heterogeneous Cellular Population
• Detecting bifurcations in dynamical systems with CROCKER plots
• Dark soliton detection using persistent homology
• Vicsek Model Meets DBSCAN: Cluster Phases in the Vicsek Model
• Intrinsic statistical separation of subpopulations in heterogeneous collective motion via dimensionality reduction
• SSRCA: a novel machine learning pipeline to perform sensitivity analysis for agent-based models