EUVIMEDOpdag EUVIMED
Open access · CC BY 4.0

Generating the Critical Ising Model via SRGAN: A Schramm–Loewner Evolution Analysis from a Geometric Deep Learning Perspective

Yuxiang Yang iD, Wei Li, Yanyang Wang iD, Zhihang Liu, Kui Tuo

Entropy · 2026-03-31 · 28 (4) · 385

DOI: 10.3390/e28040385 ↗

At a glance

Journal article in Entropy, published online on 2026-03-31. Written by Yuxiang Yang and 4 co-authors. Institution: Key Laboratory of Quark and Lepton Physics (MOE) and Institute of Particle Physics, Central China Normal University, Wuhan 430079, China. 40 references. The full text is freely available (open access, CC BY 4.0). Funded by: the National Key Research and Development Program of China, the Fundamental Research Funds for Central China Normal University, the open funds of Key Laboratory of Quark and Lepton Physics (MOE).

AbstractSubjectsBibliografiske oplysningerCiteRelated studies

Abstract (original language)

The geometric signatures of macroscopic interfaces in the two-dimensional critical Ising model strictly adhere to Schramm–Loewner Evolution (SLE) theory. In this study, we propose a physics-driven generative approach using Super-Resolution Generative Adversarial Networks (SRGANs) to approximate the inverse coarse-graining operation to generate larger configurations. From the perspective of Geometric Deep Learning (GDL), we leverage the geometric priors of Convolutional Neural Networks (CNNs)—specifically their translational and rotational symmetries—to effectively encode the universal physical laws of the Ising Hamiltonian. This inductive bias allows the model to be trained on small scales yet be generalized to large-scale systems (2048 × 2048) while preserving physical conservation. To accommodate spin discreteness, we employ an L1-based loss function to maintain domain wall sharpness. SLE analysis and long-range correlation functions confirm that the model reproduces critical dynamics and conformal invariance, successfully serving as a physics-preserving inverse coarse-graining transformation framework.

Subjects

Author keywords

SRGANSchramm-Lowner evolutioncritical ising model

Authors and institutions

  • Key Laboratory of Quark and Lepton Physics (MOE) and Institute of Particle Physics, Central China Normal University, Wuhan 430079, China.
  • SCIQ Lab, ESIEA, Campus Ivry sur Seine, 73 bis Avenue Maurice Thorez, 94200 Ivry sur Seine, France.
  • Wuhan Technology and Business University, Wuhan 430065, China.

ORCID profiles: Yuxiang Yang, Yanyang Wang

Funding

  • the National Key Research and Development Program of China
  • the Fundamental Research Funds for Central China Normal University
  • the open funds of Key Laboratory of Quark and Lepton Physics (MOE)
  • the 111 Project
  • National Key Research and Development Program of China
  • Key Laboratory of Quark and Lepton Physics
  • Fundamental Research Funds for the Central Universities

Cite

APA

Yang, Y., Li, W., Wang, Y., Liu, Z., & Tuo, K. (2026). Generating the Critical Ising Model via SRGAN: A Schramm–Loewner Evolution Analysis from a Geometric Deep Learning Perspective. Entropy, 28(4), 385. https://doi.org/10.3390/e28040385

Vancouver

Yang Y, Li W, Wang Y, Liu Z, Tuo K. Generating the Critical Ising Model via SRGAN: A Schramm–Loewner Evolution Analysis from a Geometric Deep Learning Perspective. Entropy. 2026;28(4):385. doi:10.3390/e28040385

BibTeX
@article{Yang2026,
  author = {Yang, Yuxiang and Li, Wei and Wang, Yanyang and Liu, Zhihang and Tuo, Kui},
  title = {Generating the Critical Ising Model via SRGAN: A Schramm–Loewner Evolution Analysis from a Geometric Deep Learning Perspective},
  journal = {Entropy},
  year = {2026},
  volume = {28},
  number = {4},
  pages = {385},
  doi = {10.3390/e28040385}
}
Start for free →