Detecting Atomic Scale Surface Defects in STM of TMDs with Ensemble Deep Learning
This work addresses the problem of low-throughput sample characterization in materials science, though it is incremental as it applies existing deep learning methods to a new domain.
The researchers tackled atomic-scale defect detection in scanning tunneling microscopy images of WSe2 using an ensemble of U-Net-like CNNs, achieving an average F1 score of 0.66 and demonstrating generalization to other imaging techniques and materials.
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.