Unsupervised machine learning for detection of phase transitions in off-lattice systems I. Foundations

Abstract

We demonstrate the utility of an unsupervised machine learning tool for the detection of phase transitions in off-lattice systems. We focus on the application of principal component analysis (PCA) to detect the freezing transitions of two-dimensional hard-disk and three-dimensional hard-sphere systems as well as liquid-gas phase separation in a patchy colloid model. As we demonstrate, PCA autonomously discovers order-parameter-like quantities that report on phase transitions, mitigating the need for a priori construction or identification of a suitable order parameter--thus streamlining the routine analysis of phase behavior. In a companion paper, we further develop the method established here to explore the detection of phase transitions in various model systems controlled by compositional demixing, liquid crystalline ordering, and non-equilibrium active forces.

References in corpus (30)

• Scikit-learn: Machine Learning in Python
• Active Particles in Complex and Crowded Environments
• A Tutorial on Principal Component Analysis
• Machine learning phases of matter
• Robust Structural Identification via Polyhedral Template Matching
• Learning phase transitions by confusion
• Strong scaling of general-purpose molecular dynamics simulations on GPUs
• Two-step melting in two dimensions: First-order liquid-hexatic transition
• Discovering Phase Transitions with Unsupervised Learning
• Unsupervised learning of phase transitions: from principal component analysis to variational autoencoders
• Optimal whitening and decorrelation
• Discovering Phases, Phase Transitions and Crossovers through Unsupervised Machine Learning: A critical examination
• Hard-disk equation of state: First-order liquid-hexatic transition in two dimensions with three simulation methods
• Model for reversible colloidal gelation
• Large-Scale Simulations of the Two-Dimensional Melting of Hard Disks
• Kernel methods for interpretable machine learning of order parameters
• Unsupervised Learning of Frustrated Classical Spin Models I: Principle Component Analysis
• A Topological Framework for Local Structure Analysis in Condensed Matter
• Scalable Metropolis Monte Carlo for simulation of hard shapes
• Dynamic Phases of Active Matter Systems with Quenched Disorder
• Effect of controlled corrugation on capillary condensation of colloid-polymer mixtures
• Equilibrium phase behavior of the square-well linear microphase-forming model
• Machine Learning of Frustrated Classical Spin Models. II. Kernel Principal Component Analysis
• Unsupervised machine learning for detection of phase transitions in off-lattice systems II. Applications
• On the Formation of Equilibrium Gels via a Macroscopic Bond Limitation
• Phase behaviour of polydisperse spheres: simulation strategies and an application to the freezing transition
• Computing the phase diagram of binary mixtures: a patchy particle case study
• Wertheim perturbation theory: thermodynamics and structure of patchy colloids
• Dynamic Phases, Clustering, and Lane Formation for Driven Disk Systems in the Presence of Quenched Disorder
• Nonequilibrium Structure of Colloidal Dumbbells under Oscillatory Shear

Cited by in corpus (19)

• Topological quantum phase transitions retrieved through unsupervised machine learning
• Inverse methods for design of soft materials
• Machine Learning for Condensed Matter Physics
• Machine learning-assisted design of material properties
• Extensive deep neural networks for transferring small scale learning to large scale systems
• The critical temperature of the 2D-Ising model through Deep Learning Autoencoders
• Drawing Phase Diagrams of Random Quantum Systems by Deep Learning the Wave Functions
• dPOLY: Deep Learning of Polymer Phases and Phase Transition
• Unsupervised machine learning for detection of phase transitions in off-lattice systems II. Applications
• Soft Metamaterials: Adaptation and Intelligence
• Recent advances in describing and driving crystal nucleation using machine learning and artificial intelligence
• Unsupervised Learning Eigenstate Phases of Matter
• Characterizing Different Motility Induced Regimes in Active Matter with Machine Learning and Noise
• Detecting Depinning and Nonequilibrium Transitions with Unsupervised Machine Learning
• Detecting composite orders in layered models via machine learning
• Unsupervised Machine Learning of Quenched Gauge Symmetries: A Proof-of-Concept Demonstration
• Unsupervised Learning of Rydberg Atom Array Phase Diagram with Siamese Neural Networks
• Ordered ground state configurations of the asymmetric Wigner bilayer system -- revisited: an unsupervised clustering algorithm analysis
• Orthogonal projections of hypercubes