Detecting Depinning and Nonequilibrium Transitions with Unsupervised Machine Learning

TL;DR

This paper demonstrates that machine learning can generate an order parameter capable of detecting depinning transitions and various dynamic phases in driven particle systems far from equilibrium, surpassing traditional measures.

Contribution

The study introduces a machine learning derived order parameter that effectively identifies depinning and nonequilibrium phase transitions in particle systems, including complex regimes like jamming.

Findings

Machine learning order parameter detects depinning transition.

It distinguishes different dynamical regimes beyond traditional methods.

Behavior of the order parameter varies with density and jamming effects.

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.