A Machine-Learning Based Approach to the Evaluation of the Critical Scaling Behavior of Anisotropic Spin Systems
Abstract
Computational models adequately representing phase transitions and evaluating the critical system parameters are essential for the understanding of the properties of a wide range of materials. Here we propose a machine learning (ML)-based approach to the identification of the critical point in anisotropic spin systems. Our approach implies training of a convolutional neural network (CNN) model from the correlation matrices obtained by Monte Carlo simulations. Next, the pretrained model is employed as a fast estimator of the critical temperature, which can be extracted in several complementary ways from the CNN model inference, this way improving the robustness of the analysis. The ML-based estimates obtained in this study are in very good agreement with the reference Monte Carlo simulation results, while computational costs are about 10x lower compared to the classical thermodynamic approach.
Versions
Related
- Effective-Geometry Rescaling and Universal Critical Behavior in the Anisotropic Three-State Potts Model on the Square Lattice
- Machine learning prediction of discrete eigenvalues for the radiative transfer equation under anisotropic Henyey–Greenstein scattering
- Predicting Locomotor Behavior on an Irregular Surface from Even-Surface Gait: A Machine Learning Approach
- Knowledge-Guided Construction of Machine Learning Potentials for Reactive Behavior in Energetic Materials
- Interaction dependence of the critical correlation length amplitude ratio in anisotropic scalar lattice ϕ4 theory
BibTeX
@misc{chubarova2026machinelearning,
title = {{A Machine-Learning Based Approach to the Evaluation of the Critical Scaling Behavior of Anisotropic Spin Systems}},
author = {Alina A. Chubarova and Ivan A. Mamonov and Marina V. Mamonova and Mikhail I. Bogachev and Pavel V. Prudnikov},
howpublished = {arXiv},
year = {2026},
month = sep,
doi = {10.48550/arxiv.2606.06925},
eprint = {2606.06925},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2606.06925},
note = {CC BY-NC-ND 4.0},
}
RIS
TY - UNPB
TI - A Machine-Learning Based Approach to the Evaluation of the Critical Scaling Behavior of Anisotropic Spin Systems
AU - Alina A. Chubarova
AU - Ivan A. Mamonov
AU - Marina V. Mamonova
AU - Mikhail I. Bogachev
AU - Pavel V. Prudnikov
PY - 2026
DA - 2026/09/08
PB - arXiv
DO - 10.48550/arxiv.2606.06925
UR - https://arxiv.org/abs/2606.06925
AB - Computational models adequately representing phase transitions and evaluating the critical system parameters are essential for the understanding of the properties of a wide range of materials. Here we propose a machine learning (ML)-based approach to the identification of the critical point in anisotropic spin systems. Our approach implies training of a convolutional neural network (CNN) model from the correlation matrices obtained by Monte Carlo simulations. Next, the pretrained model is employed as a fast estimator of the critical temperature, which can be extracted in several complementary ways from the CNN model inference, this way improving the robustness of the analysis. The ML-based estimates obtained in this study are in very good agreement with the reference Monte Carlo simulation results, while computational costs are about 10x lower compared to the classical thermodynamic approach.
ER -