Detecting Atomic Scale Surface Defects in STM of TMDs with Ensemble Deep Learning

Darian Smalley; Stephanie D. Lough; Luke Holtzman; Kaikui Xu; Madisen Holbrook; Matthew R. Rosenberger; J. C. Hone; Katayun Barmak; Masahiro Ishigami

Detecting Atomic Scale Surface Defects in STM of TMDs with Ensemble Deep Learning

Materials Science 2023-12-11 v1 Machine Learning

Authors: Darian Smalley , Stephanie D. Lough , Luke Holtzman , Kaikui Xu , Madisen Holbrook , Matthew R. Rosenberger , J. C. Hone , Katayun Barmak , Masahiro Ishigami

View on arXiv ↗ PDF ↗

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.

Keywords

neural networks in physics machine learning in astronomy machine learning for materials science

Cite

@article{arxiv.2312.05160,
  title  = {Detecting Atomic Scale Surface Defects in STM of TMDs with Ensemble Deep Learning},
  author = {Darian Smalley and Stephanie D. Lough and Luke Holtzman and Kaikui Xu and Madisen Holbrook and Matthew R. Rosenberger and J. C. Hone and Katayun Barmak and Masahiro Ishigami},
  journal= {arXiv preprint arXiv:2312.05160},
  year   = {2023}
}

Comments

9 pages, 4 figures, submitted to MRS Advances as a conference preceding for the 2023 MRS Fall Meeting & Exhibit

Detecting Atomic Scale Surface Defects in STM of TMDs with Ensemble Deep Learning

Abstract

Keywords

Cite

Comments

Related papers