Machine Learning of the Two-dimensional Diluted Bond Ising Model
Main Article Content
Abstract
Bond-diluted 2D Ising model is essential for understanding the effects of disorder on magnetic systems. Although the T-p phase diagram of this model has been developed through analytical methods and Monte Carlo simulations, the region near the percolation threshold pc remains insufficiently explored. In this work, we investigated the impact of bond dilution on phase transitions in the bond-diluted 2D Ising model using a machine learning approach. A convolutional neural network, initially trained on data from the pure (undiluted) 2D Ising model, is employed through transfer learning to analyze bond-diluted systems. The numerical results show that as bond concentration decreases, the critical temperature also decreases, in agreement with previous Monte Carlo simulation results. Moreover, these findings are instrumental in estimating the critical bond dilution near the percolation threshold pc. As a result, a comprehensive phase diagram for the bond-diluted 2D Ising model has been constructed.
References
No. 997, pp. 8379-8383, https://doi.org/10.1088/0305-4470/30/24/006.
[2] P. H. L. Martins, A. Plascak, Universality Class of the Two-dimensional Site-diluted Ising Model, Phys. Rev. E, Vol. 76, 2007, pp. 0121021-0121024, https://doi.org/10.1103/PhysRevE.76.012102.
[3] R. Kenna, J. J. R. Lorenzo, Scaling Analysis of the Site-diluted Ising Model in Two Dimensions, Phys. Rev. E, Vol. 78, 2008, pp. 0311341-0311347, https://doi.org/10.1103/PhysRevE.78.031134.
[4] V. S. Dotsenko, V. S. Dotsenko, Critical Behaviour of the Phase Transition in the 2d Ising Model with Impurities, Advances in Physics, Vol. 32, 1983, pp. 129-172, https://doi.org/10.1080/00018738300101541.
[5] B. N. Shalaev, Critical Behavior of the Two-dimensional Ising Model with Random Bonds, Physics Reports,
Vol. 237, 1994, pp. 129-188, https://doi.org/10.1016/0370-1573(94)90086-8.
[6] I. A. Hadjiagapiou, Monte Carlo Analysis of the Critical Properties of the Two-dimensional Randomly Bond-Diluted Ising Model Via Wang–Landau Algorithm, Physica A: Statistical Mechanics and its Applications,
Vol. 390, 2011, pp. 1279-1288, https://doi.org/10.1016/j.physa.2010.12.022.
[7] H. Nishimori, Transition Point of the Random Ising Model with Bond Dilution, Journal of Physics C: Solid State Physics, Vol. 12, 1979, pp. 641-644, https://doi.org/10.1088/0022-3719/12/17/001.
[8] W. Zhong, G. T. Barkema, D. Panja, Super Slowing Down in the Bond-Diluted Ising Model, Physical Review E, Vol. 102, 2020, pp. 0221321-0221321, https://doi.org/10.1103/PhysRevE.102.022132.
[9] Y. L. Loh, E. W. Carlson, Efficient Algorithm for Random-bond Ising Models in 2d, Physical Review Letters, Vol. 97, 2006, pp. 2272051-2272054, https://doi.org/10.1103/PhysRevLett.97.227205.
[10] A. H. Kole, G. T. Barkema, L. Fritz, Comparison of Cluster Algorithms for the Bond-Diluted Ising Model, Physical Review E, Vol. 105, 2022, pp. 0153131-0153137, https://doi.org/10.1103/PhysRevE.105.015313.
[11] J. Carrasquilla, R. G Melko, Machine Learning Phases of Matter, Nature Physics, Vol. 13, 2017, pp. 431-434, https://www.nature.com/articles/nphys4035.
[12] S. Efthymiou, M. J. S. Beach, R. G. Melko, Super-resolving the Ising Model with Convolutional Neural Networks, Physical Review B, Vol. 99, 2019, pp. 0751131-0751139, https://doi.org/10.1103/PhysRevB.99.075113.
[13] B. C¸ivitciog˘lu, R. A. Ro¨mer, A.Honecker, Machine Learning the Square-Lattice Ising Model, Journal of Physics: Conference Series, Vol. 2207, 2022, pp. 0120581-0120586,
https://doi.org/10.1088/1742-6596/2207/1/012058.
[14] G. L. G. Pavioni, M. Arlego, C. A. Lamas, Minimalist Neural Networks Training for Phase Classification in Diluted Ising Models, Computational Materials Science, Vol. 235, 2024, pp. 1127921-11279228, https://doi.org/10.1016/j.commatsci.2024.112792.
[15] P. J. Meyer, Computational Studies of Pure and Dilute Spin Models, Master’s thesis, University of Derby, 2000.