A study of the scaling behavior of the two-dimensional Ising model by methods of machine learning

A study of the scaling behavior of the two-dimensional Ising model by methods of machine learning Full article

Journal

Journal of Siberian Federal University. Mathematics & Physics
ISSN: 1997-1397 , E-ISSN: 2313-6022

Output data

Year: 2024, Volume: 17, Number: 2, Pages: 238-245 Pages count : 8

Tags

machine learning, convolutional neural networks, Monte Carlo methods, Ising model, scaling, correlation length, magnetic susceptibility

Authors

Chubarova A.A. ¹ , Mamonova M.V. ¹ , Prudnikov P.V. ²

Affiliations

1	Dostoevsky Omsk State University, Omsk, Russian Federation
2	Center of New Chemical Technologies BIC Boreskov Institute of Catalysis SB RAS, Omsk, Russian Federation

Funding (2)

1	Russian Science Foundation	23-22-00093
2	Ministry of Science and Higher Education of the Russian Federation	FWUR-2024-0039

In the field of condensed matter physics, machine learning methods have become an increasingly important instrument for researching phase transitions. Here we present a method for calculating the universal characteristics of spin models using an Ising model that is exactly solvable in two dimensions. The method is based on a convolutional neural network (CNN) with controlled learning. The scaling functions prove the continuing type of phase transition for the 2D Ising model. As a result of the proposed technique, it has been possible to calculate correlation length directly

Chubarova A.A. , Mamonova M.V. , Prudnikov P.V.
A study of the scaling behavior of the two-dimensional Ising model by methods of machine learning
Journal of Siberian Federal University. Mathematics & Physics. 2024. V.17. N2. P.238-245. WOS РИНЦ

Submitted:	Sep 10, 2023
Accepted:	Jan 27, 2024

Web of science:	WOS:001203106200009
Elibrary:	66229553

DB	Citing
Elibrary	1