Analyzing collective motion with machine learning and topology
Open Access
- 1 December 2019
- journal article
- conference paper
- Published by AIP Publishing in Chaos: An Interdisciplinary Journal of Nonlinear Science
- Vol. 29 (12) , 123125
Abstract
We use topological data analysis and machine learning to study a seminal model of collective motion in biology [M. R. D’Orsogna et al., Phys. Rev. Lett. 96, 104302 (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 on 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.Keywords
All Related Versions
Funding Information
- National Science Foundation (DMS-1641020)
- National Science Foundation (CDS&E-MSS-1854703)
- National Science Foundation (DMS-1638521)
- National Science Foundation (DMS-1813752)
- National Cancer Institute (R21CA212932)
This publication has 39 references indexed in Scilit:
- Topology based data analysis identifies a subgroup of breast cancers with a unique mutational profile and excellent survivalProceedings of the National Academy of Sciences, 2011
- Inferring individual rules from collective behaviorProceedings of the National Academy of Sciences, 2010
- Particle, kinetic and fluid models for phototaxisDiscrete and Continuous Dynamical Systems-Series B, 2009
- Collective behavior in animal groups: Theoretical models and empirical studiesHFSP Journal, 2008
- Stability of Persistence DiagramsDiscrete & Computational Geometry, 2006
- Biomimetics: its practice and theoryJournal of The Royal Society Interface, 2006
- Effective leadership and decision-making in animal groups on the moveNature, 2005
- Collective Memory and Spatial Sorting in Animal GroupsJournal of Theoretical Biology, 2002
- Support-vector networksMachine Learning, 1995
- On the determination of molecular fields.—I. From the variation of the viscosity of a gas with temperatureProceedings of the Royal Society of London. Series A, Containing Papers of a Mathematical and Physical Character, 1924