Automated Tip Conditioning for Scanning Tunneling Spectroscopy

Abstract

Scanning tunneling spectroscopy (STS), a technique that records the change in the tunneling current as a function of the bias (dI/dV) across the gap between a tip and the sample, is a powerful tool to characterize the electronic structure of single molecules and nanomaterials. While performing STS, the structure and condition of the scanning probe microscopy (SPM) tips are critical for reliably obtaining high quality point spectra. Here, we present an automated program based on machine learning models that can identify the Au(111) Shockley surface state in dI/dV point spectra and perform tip conditioning on clean or sparsely covered gold surfaces with minimal user intervention. We employed a straightforward height-based segmentation algorithm to analyze STM topographic images to identify tip conditioning positions and used 1789 archived dI/dV spectra to train machine learning models that can ascertain the condition of the tip by evaluating the quality of the spectroscopic data. Decision tree based ensemble and boosting models and deep neural networks (DNNs) have been shown to reliably identify tips in suitable conditions for STS. We expect the automated program to reduce operational costs and time, increase reproducibility in surface science studies, and accelerate the discovery and characterization of novel nanomaterials by STM. The strategies presented in this paper can readily be adapted to STM tip conditioning on a wide variety of other common substrates.

Spin splitting of dopant edge state in magnetic zigzag graphene nanoribbons

“…All STM experiments were performed using a commercial OMICRON LT-STM held at T = 4 K using PtIr STM tips. STM tips were optimized for scanning tunneling spectroscopy using an automated tip conditioning program 29 . dI/dV measurements were recorded with CO-functionalized STM tips using a lock-in amplifier with a modulation frequency of 455 Hz and a modulation amplitude of VRMS = 11 mV.…”

Automated and Autonomous Experiments in Electron and Scanning Probe Microscopy

“…138 It was recently demonstrated that using decision tree-based methods and a system with known ground truth, one can perform tip conditioning for the dI/dV spectroscopic measurements in the automated fashion. 139 STEM Tuning. The resolution of an optical instrument is fundamentally limited by diffraction, which depends on the imaging aperture size and the wavelength of radiation used.…”

“…In addition to the optimization of imaging parameters, it is equally important to optimize the STM tip for high-quality spectroscopic dI / dV measurements . It was recently demonstrated that using decision tree-based methods and a system with known ground truth, one can perform tip conditioning for the dI / dV spectroscopic measurements in the automated fashion …”

Increasing Efficiency of Nonadiabatic Molecular Dynamics by Hamiltonian Interpolation with Kernel Ridge Regression

“…Machine learning (ML) techniques have experienced rapid and extensive developments in recent decades, stimulated by growing computational power and large amounts of experimental and theoretical data accumulated in all fields, including science, technology, and daily life. Many efforts are devoted to applying ML to chemistry and materials science to predict relevant properties, − identify promising candidates for various applications, − and guide and design ongoing experiments. , With the help of ab initio-calculated data, ML is successfully practiced for predicting molecular properties. − Prediction of time-series data, such as forces on atoms in molecular dynamics (MD) simulation, can alleviate the burden of the computational cost of quantum mechanical calculations . The key to the success stems from the fact that ML models can quantitatively estimate the behavior in an unknown realm by learning the pattern from an existing data set.…”

“…Many efforts are devoted to applying ML to chemistry and materials science to predict relevant properties, 1−5 identify promising candidates for various applications, 6−9 and guide and design ongoing experiments. 9,10 With the help of ab initio-calculated data, ML is successfully practiced for predicting molecular properties. 11−16 Prediction of time-series data, such as forces on atoms in molecular dynamics (MD) simulation, can alleviate the burden of the computational cost of quantum mechanical calculations.…”