Abstract

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.

Abstract

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.

Abstract

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.

Abstract

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.