Atomic-scale defect detection is shown in scanning tunneling microscopy
images of single crystal WSe2 using an ensemble of U-Net-like convolutional
neural networks. Standard deep learning test metrics indicated good detection
performance with an average F1 score of 0.66 and demonstrated ensemble
generalization to C-AFM images of WSe2 and STM images of MoSe2. Defect
coordinates were automatically extracted from defect detections maps showing
that STM image analysis enhanced by machine learning can be used to
dramatically increase sample characterization throughput.

通过使用一组类 U-Net 的卷积神经网络，在单晶 WSe2 的扫描隧道显微镜图像中展示了原子尺度的缺陷检测。标准的深度学习测试指标表明具有良好的检测性能，平均 F1 得分为 0.66，并展示了对 WSe2 的 C-AFM 图像和 MoSe2 的 STM 图像的整体泛化。从缺陷检测地图中自动提取缺陷坐标，表明通过机器学习增强的 STM 图像分析可用于显著提高样品表征吞吐量。