Machine learning for percolation utilizing auxiliary Ising variables

Abstract

Machine learning for phase transition has received intensive research interest in recent years. However, its application in percolation still remains challenging. We propose an auxiliary Ising mapping method for machine learning study of the standard percolation as well as a variety of statistical mechanical systems in correlated percolation representations. We demonstrate that unsupervised machine learning is able to accurately locate the percolation threshold, independent of the spatial dimension of system or the type of phase transition, which can be first order or continuous. Moreover, we show that, by neural network machine learning, auxiliary Ising configurations for different universalities can be classified with high confidence level. Our results indicate that the auxiliary Ising mapping method, despite of it simplicity, can advance the application of machine learning in statistical and condensed-matter physics.

10 pages, 8 figures

References in corpus (7)

• Learning phase transitions by confusion
• Percolation on complex networks: Theory and application
• Discovering Phases, Phase Transitions and Crossovers through Unsupervised Machine Learning: A critical examination
• Unsupervised machine learning account of magnetic transitions in the Hubbard model
• Square lattice site percolation at increasing ranges of neighbor interactions
• Machine-Learning Studies on Spin Models
• Berezinskii-Kosterlitz-Thouless-like percolation transitions in the two-dimensional XY model

Cited by in corpus (6)

• Study of phase transition of Potts model with Domain Adversarial Neural Network
• Minimalist Neural Networks training for phase classification in diluted-Ising models
• Machine Learning Domain Adaptation in Spin Models with Continuous Phase Transitions
• Transport through Quantum Anomalous Hall Bilayers with Lattice Mismatch
• Exploring percolation phase transition in the three-dimensional Ising model with machine learning
• Phase probabilities in first-order transitions using machine learning