Scanning tunneling state recognition with multi-class neural network ensembles

Gordon, O.; d'Hondt, P.; Knijff, L.; Freeney, S. E.; Junqueira, F.; Moriarty, P.; Swart, I.

Document type :

Compte-rendu et recension critique d'ouvrage

DOI :

10.1063/1.5099590

Title :

Scanning tunneling state recognition with multi-class neural network ensembles

Author(s) :

Gordon, O. [Auteur]
University of Nottingham, UK [UON]
d'Hondt, P. [Auteur]
Physique - IEMN [PHYSIQUE - IEMN]
University of Nottingham, UK [UON]
Institut d’Électronique, de Microélectronique et de Nanotechnologie - UMR 8520 [IEMN]
Knijff, L. [Auteur]
Universiteit Utrecht / Utrecht University [Utrecht]
Freeney, S. E. [Auteur]
Universiteit Utrecht / Utrecht University [Utrecht]
Junqueira, F. [Auteur]
University of Nottingham, UK [UON]
Moriarty, P. [Auteur]
University of Nottingham, UK [UON]
Swart, I. [Auteur]
Universiteit Utrecht / Utrecht University [Utrecht]

Journal title :

Review of Scientific Instruments

Pages :

103704

Publisher :

American Institute of Physics

Publication date :

2019

ISSN :

0034-6748

HAL domain(s) :

Informatique [cs]/Automatique
Informatique [cs]/Réseau de neurones [cs.NE]

English abstract : [en]

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. ...
Show more >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 tunneling tip states on both metal and nonmetal 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 lowquality 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. Provided that training data are available, these ensembles therefore enable fully autonomous scanning tunneling state recognition for a wide range of typical scanning conditions.Show less >

Language :

Anglais

Popular science :

Non

Collections :