Machine Learning Vortices in the XY Model

Jintao Yang, Junpeng Cao

Donald D. Betts, F. C. Salevsky, Jos Rogiers

Wanzhou Zhang, Jiayu Liu, Tzu-Chieh Wei

In this paper, we apply machine learning methods to study phase transitions in certain statistical mechanical models on the two-dimensional lattices, whose transitions involve nonlocal or topological properties, including site and bond percolations, the XY model, and the generalized XY model. We find that using just one hidden layer in a fully connected neural network, the percolation transition can be learned and the data collapse by using the average output layer gives correct estimate of the critical exponent ν. We also study the Berezinskii-Kosterlitz-Thouless transition, which involves binding and unbinding of topological defects, vortices and antivortices, in the classical XY model. The generalized XY model contains richer phases, such as the nematic phase, the paramagnetic and the quasi-long-range ferromagnetic phases, and we also apply machine learning method to it. We obtain a consistent phase diagram from the network trained with only data along the temperature axis at two particular parameter Δ values, where Δ is the relative weight of pure XY coupling. Aside from using the spin configurations (either angles or spin components) as the input information in a convolutional neural network, we devise a feature engineering approach using the histograms of the spin orientations in order to train the network to learn the three phases in the generalized XY model and demonstrate that it indeed works. The trained network by using system size L×L can be used to the phase diagram for other sizes (L^{'}×L^{'}, where L^{'}≠L) without any further training.

Chikao Kawabata, Masaki Takeuchi, A. R. Bishop +1 more

Chen-Hui Song, Qu-Cheng Gao, Xu-Yang Hou +5 more

The XY model on a spherical surface, inspired by recently realized atomic gases trapped in a spherical shell, is analyzed here. Instead of a traditional latitude-longitude lattice, we introduce the much more homogeneous Fibonacci lattice and use classical Monte Carlo (MC) simulations to generate spin configurations. The results clearly show that topological defects, in the form of vortices, must exist in the stable configuration on a sphere but vanish in a plane due to a mathematical theorem. Using these spin configurations as training samples, a graph-convolutional network-based method is implemented to recognize different phases and successfully predict the phase-transition temperature. We also apply the density-based spatial clustering of applications with noise, a powerful machine-learning algorithm, to monitor the path of two vortices with topological charges on the sphere during MC simulations. Our results provide reliable predictions for quantum simulators using polaritons or future space-based experiments on ultracold atoms in microgravity.

Wenjian Hu, Rajiv R. P. Singh, Richard T. Scalettar

We apply unsupervised machine learning techniques, mainly principal component analysis (PCA), to compare and contrast the phase behavior and phase transitions in several classical spin models-the square- and triangular-lattice Ising models, the Blume-Capel model, a highly degenerate biquadratic-exchange spin-1 Ising (BSI) model, and the two-dimensional XY model-and we examine critically what machine learning is teaching us. We find that quantified principal components from PCA not only allow the exploration of different phases and symmetry-breaking, but they can distinguish phase-transition types and locate critical points. We show that the corresponding weight vectors have a clear physical interpretation, which is particularly interesting in the frustrated models such as the triangular antiferromagnet, where they can point to incipient orders. Unlike the other well-studied models, the properties of the BSI model are less well known. Using both PCA and conventional Monte Carlo analysis, we demonstrate that the BSI model shows an absence of phase transition and macroscopic ground-state degeneracy. The failure to capture the "charge" correlations (vorticity) in the BSI model (XY model) from raw spin configurations points to some of the limitations of PCA. Finally, we employ a nonlinear unsupervised machine learning procedure, the "autoencoder method," and we demonstrate that it too can be trained to capture phase transitions and critical points.