Autonomous convergence of STM control parameters using Bayesian optimization

Ganesh Narasimha; Saban Hus; Arpan Biswas; Rama Vasudevan; Maxim Ziatdinov

doi:10.1063/5.0185362

Autonomous convergence of STM control parameters using Bayesian optimization

Ganesh Narasimha
, Saban Hus
, Arpan Biswas
, Rama Vasudevan
, Maxim Ziatdinov

Research output: Contribution to journal › Article › peer-review

6 Scopus citations

Abstract

Scanning tunneling microscopy (STM) is a widely used tool for atomic imaging of novel materials and their surface energetics. However, the optimization of the imaging conditions is a tedious process due to the extremely sensitive tip–surface interaction, thus limiting the throughput efficiency. In this paper, we deploy a machine learning (ML)-based framework to achieve optimal atomically resolved imaging conditions in real time. The experimental workflow leverages the Bayesian optimization (BO) method to rapidly improve the image quality, defined by the peak intensity in the Fourier space. The outcome of the BO prediction is incorporated into the microscope controls, i.e., the current setpoint and the tip bias, to dynamically improve the STM scan conditions. We present strategies to either selectively explore or exploit across the parameter space. As a result, suitable policies are developed for autonomous convergence of the control parameters. The ML-based framework serves as a general workflow methodology across a wide range of materials.

Original language	English
Article number	016121
Journal	APL Machine Learning
Volume	2
Issue number	1
DOIs	https://doi.org/10.1063/5.0185362
State	Published - Mar 1 2024

Funding

The work was supported by the Center for Nanophase Materials Sciences (CNMS), which is a U.S. Department of Energy, Office of Science User Facility at Oak Ridge National Laboratory. We thank Professor Sergei V. Kalinin (University of Tennessee) for helpful discussions about optimizing imaging parameters in scanning probes and scanning tunneling microscopy experiments. We also acknowledge Mr. Sai Mani Prudhvi Valleti for helping with the blob-detection method. The work was supported by the Center for Nanophase Materi- als Sciences (CNMS), which is a U.S. Department of Energy, Office of Science User Facility at Oak Ridge National Laboratory. We thank Professor Sergei V. Kalinin (University of Tennessee) for helpful discussions about optimizing imaging parameters in scanning probes and scanning tunneling microscopy experiments. We also acknowledge Mr. Sai Mani Prudhvi Valleti for helping with the blob-detection method.

Access to Document

10.1063/5.0185362

Cite this

@article{5b2580a7f1124be6be815b6ed4c6571d,

title = "Autonomous convergence of STM control parameters using Bayesian optimization",

abstract = "Scanning tunneling microscopy (STM) is a widely used tool for atomic imaging of novel materials and their surface energetics. However, the optimization of the imaging conditions is a tedious process due to the extremely sensitive tip{\textendash}surface interaction, thus limiting the throughput efficiency. In this paper, we deploy a machine learning (ML)-based framework to achieve optimal atomically resolved imaging conditions in real time. The experimental workflow leverages the Bayesian optimization (BO) method to rapidly improve the image quality, defined by the peak intensity in the Fourier space. The outcome of the BO prediction is incorporated into the microscope controls, i.e., the current setpoint and the tip bias, to dynamically improve the STM scan conditions. We present strategies to either selectively explore or exploit across the parameter space. As a result, suitable policies are developed for autonomous convergence of the control parameters. The ML-based framework serves as a general workflow methodology across a wide range of materials.",

author = "Ganesh Narasimha and Saban Hus and Arpan Biswas and Rama Vasudevan and Maxim Ziatdinov",

note = "Publisher Copyright: {\textcopyright} 2024 Author(s).",

year = "2024",

month = mar,

day = "1",

doi = "10.1063/5.0185362",

language = "English",

volume = "2",

journal = "APL Machine Learning",

issn = "2770-9019",

number = "1",

}

TY - JOUR

T1 - Autonomous convergence of STM control parameters using Bayesian optimization

AU - Narasimha, Ganesh

AU - Hus, Saban

AU - Biswas, Arpan

AU - Vasudevan, Rama

AU - Ziatdinov, Maxim

PY - 2024/3/1

Y1 - 2024/3/1

N2 - Scanning tunneling microscopy (STM) is a widely used tool for atomic imaging of novel materials and their surface energetics. However, the optimization of the imaging conditions is a tedious process due to the extremely sensitive tip–surface interaction, thus limiting the throughput efficiency. In this paper, we deploy a machine learning (ML)-based framework to achieve optimal atomically resolved imaging conditions in real time. The experimental workflow leverages the Bayesian optimization (BO) method to rapidly improve the image quality, defined by the peak intensity in the Fourier space. The outcome of the BO prediction is incorporated into the microscope controls, i.e., the current setpoint and the tip bias, to dynamically improve the STM scan conditions. We present strategies to either selectively explore or exploit across the parameter space. As a result, suitable policies are developed for autonomous convergence of the control parameters. The ML-based framework serves as a general workflow methodology across a wide range of materials.

AB - Scanning tunneling microscopy (STM) is a widely used tool for atomic imaging of novel materials and their surface energetics. However, the optimization of the imaging conditions is a tedious process due to the extremely sensitive tip–surface interaction, thus limiting the throughput efficiency. In this paper, we deploy a machine learning (ML)-based framework to achieve optimal atomically resolved imaging conditions in real time. The experimental workflow leverages the Bayesian optimization (BO) method to rapidly improve the image quality, defined by the peak intensity in the Fourier space. The outcome of the BO prediction is incorporated into the microscope controls, i.e., the current setpoint and the tip bias, to dynamically improve the STM scan conditions. We present strategies to either selectively explore or exploit across the parameter space. As a result, suitable policies are developed for autonomous convergence of the control parameters. The ML-based framework serves as a general workflow methodology across a wide range of materials.

UR - https://www.scopus.com/pages/publications/105024410710

U2 - 10.1063/5.0185362

DO - 10.1063/5.0185362

M3 - Article

AN - SCOPUS:105024410710

SN - 2770-9019

VL - 2

JO - APL Machine Learning

JF - APL Machine Learning

IS - 1

M1 - 016121

ER -

Autonomous convergence of STM control parameters using Bayesian optimization

Abstract

Funding

Access to Document

Other files and links

Fingerprint

Cite this