Two-dimensional (2D) crystals are attracting growing interest in various research fields such as engineering, physics, chemistry, pharmacy, and biology owing to their low dimensionality and dramatic change of properties compared to the bulk counter parts. Among the various techniques used to manufacture 2D crystals, mechanical exfoliation has been essential to practical applications and fundamental research. However, mechanically exfoliated crystals on substrates contain relatively thick flakes that must be found and removed manually, limiting high-throughput manufacturing of atomic 2D crystals and van der Waals heterostructures. Here, we present a deep-learning-based method to segment and identify the thickness of atomic layer flakes from optical microscopy images. Through carefully designing a neural network based on U-Net, we found that our neural network based on U-net trained only with the data based on realistically small number of images successfully distinguish monolayer and bilayer MoS₂ and graphene with a success rate of 70–80%, which is a practical value in the first screening process for choosing monolayer and bilayer flakes of all flakes on substrates without human eye. The remarkable results highlight the possibility that a large fraction of manual laboratory work can be replaced by AI-based systems, boosting productivity.

二维（2D）晶体由于其尺寸低且与本体部件相比性能发生了巨大变化，因此在诸如工程，物理，化学，药学和生物学等各种研究领域中引起了越来越多的兴趣。在用于制造2D晶体的各种技术中，机械剥落对于实际应用和基础研究至关重要。但是，在基材上机械剥落的晶体包含必须手动找到并清除的相对较厚的薄片，这限制了原子2D晶体和范德华力异质结构的高通量制造。在这里，我们提出了一种基于深度学习的方法，可以根据光学显微镜图像分割和识别原子层薄片的厚度。通过精心设计基于U-Net的神经网络，₂和石墨烯的成功率为70–80％，这是在没有人眼的情况下选择基材上所有薄片的单层和双层薄片的第一个筛选过程的实用价值。出色的结果凸显了很大一部分手工实验室工作可以被基于AI的系统取代的可能性，从而提高了生产率。