Machine learning metadynamics simulation of reconstructive phase transition

AbstractDespite decades of theoretical research, the nature of the self-driven collective motion remains indigestible and controversial, while the phase transition process of its dynamic is a major research issue. Recent methods propose to infer the phase transition process from various artificially extracted features using machine learning. In this thesis, we propose a new order parameter by using machine learning to quantify the synchronization degree of the self-driven collective system from the perspective of the number of clusters. Furthermore, we construct a powerful model based on the graph network to determine the long-term evolution of the self-driven collective system from the initial position of the particles, without any manual features. Results show that this method has strong predictive power, and is suitable for various noises. Our method can provide reference for the research of other physical systems with local interactions.

Download Full-text

Determining the nonequilibrium criticality of a Gardner transition via a hybrid study of molecular simulations and machine learning

Proceedings of the National Academy of Sciences ◽

10.1073/pnas.2017392118 ◽

2021 ◽

Vol 118 (11) ◽

pp. e2017392118

Author(s):

Huaping Li ◽

Yuliang Jin ◽

Ying Jiang ◽

Jeff Z. Y. Chen

Keyword(s):

Machine Learning ◽

Phase Transition ◽

Critical Exponents ◽

Spin Glasses ◽

Scaling Laws ◽

Finite Size ◽

Three Dimensions ◽

Aging Effects ◽

Correlation Lengths ◽

Nonequilibrium Phase

Apparent critical phenomena, typically indicated by growing correlation lengths and dynamical slowing down, are ubiquitous in nonequilibrium systems such as supercooled liquids, amorphous solids, active matter, and spin glasses. It is often challenging to determine if such observations are related to a true second-order phase transition as in the equilibrium case or simply a crossover and even more so to measure the associated critical exponents. Here we show that the simulation results of a hard-sphere glass in three dimensions are consistent with the recent theoretical prediction of a Gardner transition, a continuous nonequilibrium phase transition. Using a hybrid molecular simulation–machine learning approach, we obtain scaling laws for both finite-size and aging effects and determine the critical exponents that traditional methods fail to estimate. Our study provides an approach that is useful to understand the nature of glass transitions and can be generalized to analyze other nonequilibrium phase transitions.

Download Full-text

Scanning-probe and information-concealing machine learning intermediate hexatic phase and critical scaling of solid-hexatic phase transition in deformable particles

EPL (Europhysics Letters) ◽

10.1209/0295-5075/ac49d4 ◽

2022 ◽

Author(s):

Weichen Guo ◽

Bao-Quan Ai ◽

Liang He

Keyword(s):

Machine Learning ◽

Phase Transition ◽

Correlation Length ◽

Continuous Phase ◽

Scanning Probe ◽

Learning Approaches ◽

Two Dimensional ◽

Critical Scaling ◽

Hexatic Phase ◽

Deformable Particles

Abstract We investigate the two-dimensional melting of deformable polymeric particles with multi-body interactions described by the Voronoi model. We report machine learning evidence for the existence of the intermediate hexatic phase in this system, and extract the critical exponent $\nu\approx0.65$ for the divergence of the correlation length of the associated solid-hexatic phase transition. Moreover, we clarify the discontinuous nature of the hexatic-liquid phase transition in this system. These findings are achieved by directly analyzing system's spatial configurations with two generic machine learning approaches developed in this work, dubbed ``scanning-probe'' via which the possible existence of intermediate phases can be efficiently detected, and ``information-concealing'' via which the critical scaling of the correlation length in the vicinity of generic continuous phase transition can be extracted. Our work provides new physical insights into the fundamental nature of the two-dimensional melting of deformable particles, and establishes a new type of generic toolbox to investigate fundamental properties of phase transitions in various complex systems.

Download Full-text