# Scanning Probe State Recognition With Multi-Class Neural Network Ensembles

## TL;DR

This paper presents a neural network ensemble approach for automated recognition of scanning probe tip states, significantly improving accuracy and efficiency in in situ corrections during scanning probe microscopy.

## Contribution

Introduces a convolutional neural network protocol with ensemble voting for automated tip state recognition on various surfaces, enhancing current manual correction methods.

## Key findings

- Achieved high precision (up to 0.96) in distinguishing tip states.
- Demonstrated successful automatic identification on multiple metal surfaces.
- Ensemble models significantly outperform individual models in accuracy.

## Abstract

One of the largest obstacles facing scanning probe microscopy is the constant need to correct flaws in the scanning probe in situ. This is currently a manual, time-consuming process that would benefit greatly from automation. Here we introduce a convolutional neural network protocol that enables automated recognition of a variety of desirable and undesirable scanning probe tip states on both metal and non-metal surfaces. By combining the best performing models into majority voting ensembles, we find that the desirable states of H:Si(100) can be distinguished with a mean precision of 0.89 and an average receiver-operator-characteristic curve area of 0.95. More generally, high and low-quality tips can be distinguished with a mean precision of 0.96 and near perfect area-under-curve of 0.98. With trivial modifications, we also successfully automatically identify undesirable, non-surface-specific states on surfaces of Au(111) and Cu(111). In these cases we find mean precisions of 0.95 and 0.75 and area-under-curves of 0.98 and 0.94, respectively.