Challenges
Datasets
Workspaces
Papers
Discussions
Leaderboard
Log inSign up
Challenges
Datasets
Workspaces
Papers
Discussions
Leaderboard
Blog
Job Board
Q3AS

© 2026 Aqora Quantum S.A.S.

TermsPrivacyLegal Notice

Siberian Journal of Physics

Neural Network Method for Calculation of the Curie Point of the Two-Dimensional Ising Model

Alena Korol, K. V. Nevedev, Vitalii Yu. Kapitan

Published Sep 11, 2022• 0 citations
Publisher

Abstract

The authors describe a method for determining the critical point of a second order phase transitions using a convolutional neural network based on the Ising model on a square lattice. Data for training and analysis were obtained using Monte Carlo simulations. The neural network was trained on the data corresponding to the low-temperature phase, that is a ferromagnetic one and high-temperature phase, that is a paramagnetic one, respectively. After training, the neural network analyzed input data from the entire temperature range: from 0.1 to 5.0 (in dimensionless units J) and determined the Curie point Tc.

DOI
10.25205/2541-9447-2022-17-2-5-15

Related papers

Neural Network for Prediction of Curie Temperature of Two-Dimensional Ising Model

Alena Korol, Vitalii Yu. Kapitan

The authors describe a method for determining the critical point of a second-order phase transitions using a convolutional neural network based on the Ising model on a square lattice. Data for training were obtained using Metropolis algorithm for different temperatures. The neural network was trained on the data corresponding to the low-temperature phase, that is a ferromagnetic one and high-temperature phase, that is a paramagnetic one, respectively. After training, the neural network analyzed input data from the entire temperature range: from 0.1 to 5.0 (in dimensionless units) and determined (the Curie temperature T_c). The accuracy of the obtained results was estimated relative to the Onsager solution for a flat lattice of Ising spins.

Dal nevostochnyi Matematicheskii Zhurnal•Jun 18, 2021•1 citation

Ising Model Phase Transition Calculation for Ferro-Paramagnetic Lattice

Dhia`a K. Khudier, Nabeil Ibrahim Fawaz

The position of the phase transition in the two dimensional Ising model were determined byusing Monte Carlo simulation in a quadratic for area of variable length with external magnetic fieldswitched off (B = 0). The magnetization (M) per site (µ), magnetic susceptibility (x) of aferromagnetic and paramagnetic materials were calculated as a function of temperature T for(20×20,40×40,60×60), (80×80,120×120,200×200) spin lattice interactions. Nearest neighborinteraction is assumed (i.e. each spin has 4 neighbors); uses periodic boundary conditions. The Curietemperature (Tc = 2.27 J/kB ) is determined by measuring the magnetic susceptibility at which theferromagnetic and paramagnetic undergoes a phase change from order to disorder. There is thus aphase transition defined by the Curie temperature. The Monte Carlo method were used to check theseresults and to confirm the phase transition. The data are analyzed using the Curie-Weiss law whichcontains the Curie temperature as a parameter.

International Letters of Chemistry Physics and Astronomy•Jun 29, 2013•0 citations

Machine Learning of Nonequilibrium Phase Transition in an Ising Model on Square Lattice

Dagne Wordofa Tola, Mulugeta Bekele

This paper presents the investigation of convolutional neural network (CNN) prediction successfully recognizing the temperature of the nonequilibrium phase transitions in two-dimensional (2D) Ising spins on a square lattice. The model uses image snapshots of ferromagnetic 2D spin configurations as an input shape to provide the average output predictions. By considering supervised machine learning techniques, we perform Metropolis Monte Carlo (MC) simulations to generate the configurations. In the equilibrium Ising model, the Metropolis algorithm respects detailed balance condition (DBC), while its nonequilibrium version violates DBC. Violating the DBC of the algorithm is characterized by a parameter −8<ε<8. We find the exact result of the transition temperature Tc(ε) in terms of ε. If we set ε=0, the usual single spin-flip algorithm can be restored, and the equilibrium configurations generated with such a set up are used to train our model. For ε≠0, the system attains the nonequilibrium steady states (NESS), and the modified algorithm generates NESS configurations (test dataset). The trained model is successfully tested on the test dataset. Our result shows that CNN can determine Tc(ε≠0) for various ε values, consistent with the exact result.

arXiv:2307.11901•Condensed Matter•Sep 15, 2023•10 citations

The Phase Transition of the 2D-Ising Model By Using Monte Carlo Method

Dhia'a Kudeer, Saad. Abood

In this project, the location of the phase transition in the two dimensional Ising model will be determined using Monte Carlo simulation with importance sampling. the magnetization per site [m ], energy per site [J ], magnetic susceptibility, specific heat of a Ferromagnetic materials are Calculated as a function of temperature T for 10´10, 20´ 20, 40´ 40 , 50´50 spin lattice interaction by using Monte Carlo Simulation of the 2D Ising Model for some experimental values of ferromagnetic materials such as Gadolinium Chloride ( ) 3 GdCl at Curie temperature c T B = 2.2 J k , and ferromagnetic thin film from Nickel ( ) i N growth on cooper (Cu)at Curie temperature c B T = 2.772 J k , in zero and nonzero magnetic field. It was noticed that above a certain temperature ( ) c T the material will be in a paramagnetic state, this will lead to that the average magnetization will be decrease and the average energy increase, while below that temperature ,it will be in a ferromagnetic state, and the average magnetization will increase and the average energy decrease. Moreover, above a certain temperature spontaneous magnetization will be zero

Engineering and Technology Journal•Jan 1, 2011•0 citations

Two-Dimensional Ising Ferromagnet with Second-Neighbor Interaction. II. Monte Carlo Method

Sei-ichi Takase

The static properties are investigated by computer simulation for the square Ising ferromagnet in which the nearest-neighbor interactions are ferromagnetic and the second interactions antiferromagnetic. Energy and magnetization at various temperatures are obtained by Monte Carlo calculations performed on the lattice with 20×20 spins. The Curie point determined as the inflection point of the energy-vs-temperature curve agrees with the result by Fan and Wu rather than other analytical approximations. The behavior of the spontaneous magnetization M 0 ( T ) for T → T c -0 as characterized by the critical exponent β is shown by comparing the data with an analytical equation for the magnetization. The exponent β remains probably unchanged from the original value 1/8.

Journal of the Physical Society of Japan•May 15, 1976•5 citations

Two-Dimensional Ising Ferromagnet with Second-Neighbor Interaction. III. Series-Expansion Method

Sei-ichi Takase

The square Ising ferromagnet is investigated by computer simulation in the region of competing interactions (nearest-neighbor interaction K >0 and second-neighbor one K '<0). Spontaneous magnetization M 0 and energy E are calculated from advanced Monte Carlo calculations. The estimates of M 0 and of the Curie point T c ( K '/ K ) determined by analyzing the data on E are compared with the results from analysis of low-temperature series based on the assumption β=1/8. The values of T c ( K '/ K ) are obtained from padé-approximant method for low-temperature series. The value of β does not vary from the Onsager's value 1/8.

Journal of the Physical Society of Japan•Jun 1, 1977•7 citations
The authors describe a method for determining the critical point of a second order phase transitions using a convolutional neural network based on the Ising model on a square lattice. Data for training and analysis were obtained using Monte Carlo simulations. The neural network was trained on the data corresponding to the low-temperature phase, that is a ferromagnetic one and high-temperature phase, that is a paramagnetic one, respectively. After training, the neural network analyzed input data from the entire temperature range: from 0.1 to 5.0 (in dimensionless units J) and determined the Curie point Tc.
The authors describe a method for determining the critical point of a second-order phase transitions using a convolutional neural network based on the Ising model on a square lattice. Data for training were obtained using Metropolis algorithm for different temperatures. The neural network was trained on the data corresponding to the low-temperature phase, that is a ferromagnetic one and high-temperature phase, that is a paramagnetic one, respectively. After training, the neural network analyzed input data from the entire temperature range: from 0.1 to 5.0 (in dimensionless units) and determined (the Curie temperature T_c). The accuracy of the obtained results was estimated relative to the Onsager solution for a flat lattice of Ising spins.
The position of the phase transition in the two dimensional Ising model were determined byusing Monte Carlo simulation in a quadratic for area of variable length with external magnetic fieldswitched off (B = 0). The magnetization (M) per site (µ), magnetic susceptibility (x) of aferromagnetic and paramagnetic materials were calculated as a function of temperature T for(20×20,40×40,60×60), (80×80,120×120,200×200) spin lattice interactions. Nearest neighborinteraction is assumed (i.e. each spin has 4 neighbors); uses periodic boundary conditions. The Curietemperature (Tc = 2.27 J/kB ) is determined by measuring the magnetic susceptibility at which theferromagnetic and paramagnetic undergoes a phase change from order to disorder. There is thus aphase transition defined by the Curie temperature. The Monte Carlo method were used to check theseresults and to confirm the phase transition. The data are analyzed using the Curie-Weiss law whichcontains the Curie temperature as a parameter.
This paper presents the investigation of convolutional neural network (CNN) prediction successfully recognizing the temperature of the nonequilibrium phase transitions in two-dimensional (2D) Ising spins on a square lattice. The model uses image snapshots of ferromagnetic 2D spin configurations as an input shape to provide the average output predictions. By considering supervised machine learning techniques, we perform Metropolis Monte Carlo (MC) simulations to generate the configurations. In the equilibrium Ising model, the Metropolis algorithm respects detailed balance condition (DBC), while its nonequilibrium version violates DBC. Violating the DBC of the algorithm is characterized by a parameter −8<ε<8. We find the exact result of the transition temperature Tc(ε) in terms of ε. If we set ε=0, the usual single spin-flip algorithm can be restored, and the equilibrium configurations generated with such a set up are used to train our model. For ε≠0, the system attains the nonequilibrium steady states (NESS), and the modified algorithm generates NESS configurations (test dataset). The trained model is successfully tested on the test dataset. Our result shows that CNN can determine Tc(ε≠0) for various ε values, consistent with the exact result.
In this project, the location of the phase transition in the two dimensional Ising model will be determined using Monte Carlo simulation with importance sampling. the magnetization per site [m ], energy per site [J ], magnetic susceptibility, specific heat of a Ferromagnetic materials are Calculated as a function of temperature T for 10´10, 20´ 20, 40´ 40 , 50´50 spin lattice interaction by using Monte Carlo Simulation of the 2D Ising Model for some experimental values of ferromagnetic materials such as Gadolinium Chloride ( ) 3 GdCl at Curie temperature c T B = 2.2 J k , and ferromagnetic thin film from Nickel ( ) i N growth on cooper (Cu)at Curie temperature c B T = 2.772 J k , in zero and nonzero magnetic field. It was noticed that above a certain temperature ( ) c T the material will be in a paramagnetic state, this will lead to that the average magnetization will be decrease and the average energy increase, while below that temperature ,it will be in a ferromagnetic state, and the average magnetization will increase and the average energy decrease. Moreover, above a certain temperature spontaneous magnetization will be zero
The static properties are investigated by computer simulation for the square Ising ferromagnet in which the nearest-neighbor interactions are ferromagnetic and the second interactions antiferromagnetic. Energy and magnetization at various temperatures are obtained by Monte Carlo calculations performed on the lattice with 20×20 spins. The Curie point determined as the inflection point of the energy-vs-temperature curve agrees with the result by Fan and Wu rather than other analytical approximations. The behavior of the spontaneous magnetization M 0 ( T ) for T → T c -0 as characterized by the critical exponent β is shown by comparing the data with an analytical equation for the magnetization. The exponent β remains probably unchanged from the original value 1/8.
The square Ising ferromagnet is investigated by computer simulation in the region of competing interactions (nearest-neighbor interaction K >0 and second-neighbor one K '<0). Spontaneous magnetization M 0 and energy E are calculated from advanced Monte Carlo calculations. The estimates of M 0 and of the Curie point T c ( K '/ K ) determined by analyzing the data on E are compared with the results from analysis of low-temperature series based on the assumption β=1/8. The values of T c ( K '/ K ) are obtained from padé-approximant method for low-temperature series. The value of β does not vary from the Onsager's value 1/8.