Machine Learning-Based Reward-Driven Tuning of Scanning Probe Microscopy: Toward Fully Automated Microscopy.

Journal: ACS nano
Published Date: May 19, 2025

Abstract

Since the dawn of scanning probe microscopy (SPM), tapping or intermittent contact mode has been one of the most widely used imaging modes. Manual optimization of tapping mode not only takes a lot of instrument and operator time but also often leads to frequent probe and sample damage, poor image quality, and reproducibility issues for new types of samples or inexperienced users. Despite wide use, optimization of tapping mode imaging is an extremely difficult problem, being ill-suited to both classical control methods and machine learning techniques. Here, we describe a reward-driven workflow to automate the optimization of the SPM in tapping mode. The reward function is defined based on multiple channels with physical and empirical knowledge of good scans encoded, representing a sample-agnostic measure of image quality and imitating the decision-making logic employed by human operators. The workflow determines scanning parameters that produce consistent, high-quality images in attractive modes across various probes and samples. These results demonstrate improved efficiency and reliability in tapping mode SPM operation.

Authors

  • Yu Liu
    Research Center of Information Technology, Beijing Academy of Agriculture and Forestry Science, Beijing, China.
  • Roger Proksch
    Department of Materials Science and Engineering, University of Tennessee, Knoxville, Tennessee 37996, United States.
  • Jason Bemis
    Oxford Instruments Asylum Research, Santa Barbara, California 93117, United States.
  • Utkarsh Pratiush
    Department of Materials Science and Engineering, University of Tennessee, Knoxville, Tennessee 37996, United States.
  • Astita Dubey
    Department of Materials Science and Engineering, University of Tennessee, Knoxville, Tennessee 37996, United States.
  • Mahshid Ahmadi
    Department of Materials Science and Engineering, University of Tennessee, Knoxville, Tennessee 37996, United States.
  • Reece Emery
    Department of Materials Science and Engineering, University of Tennessee, Knoxville, Tennessee 37996, United States.
  • Philip D Rack
    Department of Materials Science and Engineering, University of Tennessee, Knoxville, Tennessee 37996, United States.
  • Yu-Chen Liu
    Institute of Engineering in Medicine, University of California, San Diego, La Jolla, CA, USA.
  • Jan-Chi Yang
    Department of Physics, National Cheng Kung University, Tainan 70101, Taiwan.
  • Sergei V Kalinin

Keywords

No keywords available for this article.

External Resources

Popular Topics
Recent Journals