Detecting Depinning and Nonequilibrium Transitions with Unsupervised Machine Learning
arXiv:1909.01430 · doi:10.1103/PhysRevE.101.042101
Abstract
Using numerical simulations of a model disk system, we demonstrate that a machine learning generated order parameter can detect depinning transitions and different dynamic flow phases in systems driven far from equilibrium. We specifically consider monodisperse passive disks with short range interactions undergoing a depinning phase transition when driven over quenched disorder. The machine learning derived order parameter identifies the depinning transition as well as different dynamical regimes, such as the transition from a flowing liquid to a phase separated liquid-solid state that is not readily distinguished with traditional measures such as velocity-force curves or Voronoi tessellation. The order parameter also shows markedly distinct behavior in the limit of high density where jamming effects occur. Our results should be general to the broad class of particle-based systems that exhibit depinning transitions and nonequilibrium phase transitions.
arXiv comment10 pages, 10 figures
References in corpus (35)
- Scikit-learn: Machine Learning in Python
- Machine learning phases of matter
- Direct Observation of the Skyrmion Hall Effect
- Emergent electrodynamics of skyrmions in a chiral magnet
- Discovering Phase Transitions with Unsupervised Learning
- Modeling friction: From nanoscale to mesoscale
- Unsupervised learning of phase transitions: from principal component analysis to variational autoencoders
- Room-temperature current-induced generation and motion of sub-100nm skyrmions
- Discovering Phases, Phase Transitions and Crossovers through Unsupervised Machine Learning: A critical examination
- Nonequilibrium Dynamic Phase Diagram for Vortex Lattices
- Depinning and nonequilibrium dynamic phases of particle assemblies driven over random and ordered substrates: a review
- Dynamic Phases of Vortices in Superconductors with Periodic Pinning
- Moving glass theory of driven lattices with disorder
- Nonequilibrium Steady States of Driven Periodic Media
- Distortion and destruction of colloidal flocks in disordered environments
- Hall noise and transverse freezing in driven vortex lattices
- Colloidal Dynamics on Disordered Substrates
- Moving Wigner Glasses and Smectics: Dynamics of Disordered Wigner Crystals
- Static and dynamic friction in sliding colloidal monolayers
- Dynamical Ordering of Driven Stripe Phases in Quenched Disorder
- Dynamic Phases of Active Matter Systems with Quenched Disorder
- The Tribology of Sliding Elastic Media
- Unsupervised machine learning for detection of phase transitions in off-lattice systems I. Foundations
- Fluctuations and Noise Signatures of Driven Magnetic Skyrmions
- Topological Defects, Orientational Order, and Depinning of the Electron Solid in a Random Potential
- Unsupervised machine learning for detection of phase transitions in off-lattice systems II. Applications
- Transport evidence for a sliding two-dimensional quantum electron solid
- Dynamic Regimes for Driven Colloidal Particles on a Periodic Substrate at Commensurate and Incommensurate Fillings
- Jamming in Systems With Quenched Disorder
- Observation of narrow-band noise accompanying the breakdown of insulating states in high Landau levels
- Dynamics of self-organized driven particles with competing range interaction
- Driven Disordered Polymorphic Solids: Phases and Phase Transitions, Dynamical Coexistence and Peak Effect Anomalies
- Pinning Susceptibility: The effect of dilute, quenched disorder on jamming
- De-Pinning Transition of Bubble Phases in a High Landau Level
- Dynamic Phases, Clustering, and Lane Formation for Driven Disk Systems in the Presence of Quenched Disorder