Source-linked AI summary
Autonomous Scanning Probe Microscopy in-situ Tip Conditioning through Machine Learning
Mohammad Rashidi, Robert A. Wolkow
TL;DR
SPM manipulation depends on atomically sharp tips, but surface interactions degrade them and in-situ restoration is time-consuming. This work uses a CNN to assess silicon dangling-bond images and automate tip conditioning, reaching beyond 99% operational accuracy with majority voting.
Problem
Surface interactions can degrade atomically sharp SPM tips, while in-situ treatments are time-consuming and often require repeated attempts.
Source: p. 1Method
A CNN assesses images of isolated dangling bonds on hydrogen-terminated Si(100), and the routine conditions the tip when degraded quality is detected.
Source: p. 1Results
97% accuracy on dangling-bond images improved to beyond 99% operational accuracy using majority voting.
Source: p. 1Takeaways & Limitations
The framework is presented as a step toward autonomous atom-scale fabrication and can be applied to other material systems and nanoscale imaging techniques.
Source: p. 4
Abstract
from arXiv · showhide
Atomic scale characterization and manipulation with scanning probe microscopy rely upon the use of an atomically sharp probe. Here we present automated methods based on machine learning to automatically detect and recondition the quality of the probe of a scanning tunneling microscope. As a model system, we employ these techniques on the technologically relevant hydrogen-terminated silicon surface, training the network to recognize abnormalities in the appearance of surface dangling bonds. Of the machine learning methods tested, a convolutional neural network yielded the greatest accuracy, achieving a positive identification of degraded tips in 97% of the test cases. By using multiple points of comparison and majority voting, the accuracy of the method is improved beyond 99%. The methods described here can easily be generalized to other material systems and nanoscale imaging techniques.