Deep learning in two-dimensional materials: Characterization, prediction, and design

Article Properties
  • Language
    English
  • Publication Date
    2024/04/16
  • Indian UGC (Journal)
  • Refrences
    175
  • Xinqin Meng
  • Chengbing Qin
  • Xilong Liang
  • Guofeng Zhang
  • Ruiyun Chen
  • Jianyong Hu
  • Zhichun Yang
  • Jianzhong Huo
  • Liantuan Xiao
  • Suotang Jia
Abstract
Cite
Meng, Xinqin, et al. “Deep Learning in Two-Dimensional Materials: Characterization, Prediction, and Design”. Frontiers of Physics, vol. 19, no. 5, 2024, https://doi.org/10.1007/s11467-024-1394-7.
Meng, X., Qin, C., Liang, X., Zhang, G., Chen, R., Hu, J., Yang, Z., Huo, J., Xiao, L., & Jia, S. (2024). Deep learning in two-dimensional materials: Characterization, prediction, and design. Frontiers of Physics, 19(5). https://doi.org/10.1007/s11467-024-1394-7
Meng X, Qin C, Liang X, Zhang G, Chen R, Hu J, et al. Deep learning in two-dimensional materials: Characterization, prediction, and design. Frontiers of Physics. 2024;19(5).
Journal Categories
Science
Physics
Description

Can deep learning accelerate the discovery of novel two-dimensional materials? This review comprehensively outlines the progress of deep learning in the realm of 2D materials, a field spurred by the isolation of graphene, addressing persistent challenges in their development. The review discusses deep learning methods, such as convolutional neural networks, generative adversarial networks, and U-net models, with the use of unique properties of 2d materials. By addressing the effective identification of diverse 2D materials, the domains of large-scale and high-precision characterization, also intelligent function prediction and design. Furthermore, the characterization of 2D materials by deep learning methods will be discussed, including defects and materials identification, as well as automatic thickness characterization. Progress in predicting unique properties, involving electronic, mechanical, and thermodynamic features, and the inverse design of functional 2D materials will be succinctly evaluated. This review may offer guidance to boost the understanding and employing novel 2D materials.

Published in Frontiers of Physics, this review aligns perfectly with the journal's scope, focusing on the intersection of physics and materials science. The discussion of deep learning applications in 2D materials is highly relevant to the journal’s audience, who are interested in new and emerging areas in Physics.

Refrences
Refrences Analysis
The category Technology: Electrical engineering. Electronics. Nuclear engineering: Materials of engineering and construction. Mechanics of materials 175 is the most frequently represented among the references in this article. It primarily includes studies from ACS Nano The chart below illustrates the number of referenced publications per year.
Refrences used by this article by year