EXTENDED ABSTRACT: The atomic structure of a material (such as vacancies, grain boundaries, phases, stacking faults, etc.) signiffcantly affects its electrical, optical, mechanical, and catalytic properties, thus is key to understanding the transfer law of material microstructure to macroscopic properties. Transmission electron microscopy (TEM) is an important means to characterize the atomic scale structure of materials. However, manual analysis of microscopic images has limitations such as intensive labor work, heavy time consumption, low analytical precision, sensitivity to image quality, and difffculty in obtaining statistical conclusions. Therefore, it is urgent to develop automatic microscopic image recognition and analysis methods. This report will introduce (1) the use of graph neural networks to accurately identify defects with diverse structures and random large-scale lattice distortion, and (2) using the disentangled representation learning method (a generative model), to generate a large corpus of annotated simulation data that closely resembles experimental conditions. A structural inference model is then trained via a residual neural network which can directly deduce the interlayer slip and rotation of diversiffed and complicated stacking patterns at van der Waals interfaces with picometer-scale accuracy across various materials with different layer numbers.

Keywords: machine learning; generative model; graph neutral network; defects; atomic-scale structure

REFERENCES:

[1] S. Wang#, S. Zhang#, J. Zhang*, Atomic-Scale Studies of Overlapping Grain Boundaries between Parallel and QuasiParallel Grains in Low-Symmetry Monolayer ReS2, Matter, 2020, 3, 2108.

[2] S. Wang*, F. Ouyang*, J. Zhang* Lateral and Vertical Morphology Engineering of Low-Symmetry, Weakly-Coupled 2D ReS2, Adv. Funct. Mater. 2023, 33, 2210502.

[3] F. Liu*, S. Wang*, J. Zhang*, Constructing slip stacking diversity in van der Waals homobilayers, Adv. Mater., 2024, DOI:10.1002/adma.202404734.

[4] L. Yao*, F. Ouyang*, J. Zhang*, S. Wang*, Auto-resolving atomic structure at van der Waal interfaces using a generative model, Adv. Mater., 2024, DOI: arXiv:2408.16802.