Efficiency of a neural network to detect phase transition in percolating 2D systems
DOI:
https://doi.org/10.30973/progmat/2022.14.3/1Keywords:
NN, phase transition, two-dimensional, percolationAbstract
We construct an neural network (NN) that simulates the percolation effect for the case of 2D systems using a supervised neural network. We created a database (DB) where we assigned the values of the pores with random radius that make up the two-dimensional system to train our network, once trained the NN was able to detect whether or not there was a phase transition in 2D systems with which our network was tested. We performed several tests introducing noise at the pore radii in the test systems and obtained good prediction results when the noise was small, whereas for noises greater than 0.3 the prediction accuracy tended to decrease.
References
Del Coso, R., Requejo-Isidro, J., Solis, J., Gonzalo, J., Afonso C.N. Third order nonlinear optical susceptibility of Cu: Al 2 O 3 nanocomposites: from spherical nanoparticles to the percolation threshold. Journal of applied physics. 2004, 95(5), 2755-2762. https://doi.org/10.1063/1.1643779
Medina, G., Calderón, Y.Y., Burlak, G., Hernández, J. A. Study of the critical probability of percolation in a 3D system with pores of random radius for variable grids. Revista Mexicana de Física. 2020, 66(3), 315-321. https://doi.org/10.31349/revmexfis.66.315
Li, J., Kim, J.K. Percolation threshold of conducting polymer composites containing 3D randomly distributed graphite nanoplatelets. Composites science and technology. 2007, 67(10), 2114-2120. https://doi.org/10.1016/j.compscitech.2006.11.010
Davis, S., Trapman, P., Leirs, H., Begon, M., Heesterbeek, J A.P. The abundance threshold for plague as a critical percolation phenomenon. Nature. 2008, 454(7204), 634-637. https://doi.org/10.1038/nature07053
S. Nakaya and K. Nakamura, Percolation conditions in fractured hard rocks: A numerical approach using the three-dimensional binary fractal fracture network (3D BFFN) model. Journal of Geophysical Research: Solid Earth. 2007, 112(B12). https://doi.org/10.1029/2006JB004670
Li, L., Yang, Y., Zhang, D., Ye, Z.G., Jesse, S., Kalinin, S.V., Vasudevan, R.K. Machine learning–enabled identification of material phase transitions based on experimental data: Exploring collective dynamics in ferroelectric relaxors. Science advances. 2018, 4(3), eaap8672. https://doi.org/10.1126/sciadv.aap8672
Carrasquilla, J., Melko, R.G. Machine learning phases of matter. Nature Physics. 2017, 13(5), 431-434. https://doi.org/10.1038/nphys4035
Tanaka, A., Tomiya, A. Detection of phase transition via convolutional neural networks. Journal of the Physical Society of Japan. 2017, 86(6), 063001. https://doi.org/10.7566/JPSJ.86.063001
Burlak G. Evaluation of the spectrum of a quantum system using machine learning based on incomplete information about the wavefunctions. Applied Physics Letters. 2020, 116(2), 024101. https://doi.org/10.1063/1.5136251
Salvail, J.Z., Agnew, M., Johnson, A.S., Bolduc, E., Leach, J., Boyd, R.W. Full characterization of polarization states of light via direct measurement. Nature Photonics. 2013, 7(4), 316-321, 2013. https://doi.org/10.1038/nphoton.2013.24
Burlak, G., Calderón-Segura, Y. Percolation and lasing in real 3D crystals with inhomogeneous distributed random pores. Physica B. 2014, 453, 8-13. https://doi.org/10.1016/j.physb.2014.04.030
Burlak, G., Medina-Ángel, G. Applications of a neural network to detect the percolating transitions in a system with variable radius of defects. Chaos. 2020, 30(8), 083145. https://doi.org/10.1063/5.0010904
Vogel, K., & Risken, H. Determination of quasiprobability distributions in terms of probability distributions. Physical Review A. 1989, 40(5), 2847. https://doi.org/10.1103/PhysRevA.40.2847
Grimmett, G. The random-cluster model. In: Probability on discrete structures. Berlin: Springer, 1999. https://doi.org/10.1007/978-3-540-32891-9
Cunillera, A., Soriano, M.C., Fischer, I. Cross-predicting the dynamics of an optically injected single-mode semiconductor laser using reservoir computing. Chaos. 2019, 29(11), 113113. https://doi.org/10.1063/1.5120822
Burlak, G., Rubo, Y.G. Mirrorless lasing from light emitters in percolating clusters. Physical Review A. 2015, 92(1), 013812. https://doi.org/10.1103/PhysRevA.92.013812
Kelleher, J.D., Mac Namee, B., D'arcy, A. Fundamentals of Machine Learning for Predictive Data Analytics: Algorithms, Worked Examples, and Case Studies: The MIT Press, 2020.
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2022 Gustavo Medina-Ángel, Gennadiy Burlak
This work is licensed under a Creative Commons Attribution 4.0 International License.
Usted es libre de:
 |
Compartir — compartir y redistribuir el material publicado en cualquier medio o formato. |
 |
Adaptar — combinar, transformar y construir sobre el material para cualquier propósito, incluso comercialmente. |
Bajo las siguientes condiciones:
 |
Atribución — Debe otorgar el crédito correspondiente, proporcionar un enlace a la licencia e indicar si se realizaron cambios. Puede hacerlo de cualquier manera razonable, pero de ninguna manera que sugiera que el licenciador lo respalda a usted o a su uso. |
| Sin restricciones adicionales: no puede aplicar términos legales o medidas tecnológicas que restrinjan legalmente a otros a hacer cualquier cosa que permita la licencia. |
