Automated Real-Space Lattice Extraction for Atomic Force Microscopy Images

Autor(en)

Marco Corrias, Lorenzo Papa, Igor Sokolović, Viktor Birschitzky, Alexander Gorfer, Martin Setvín, Michael Schmid, Ulrike Diebold, Michele Reticcioli, Cesare Franchini

Abstrakt

Analyzing atomically resolved images is a time-consuming process requiring solid experience and substantial human intervention. In addition, the acquired images contain a large amount of information such as crystal structure, presence and distribution of defects, and formation of domains, which need to be resolved to understand a material’s surface structure. Therefore, machine learning techniques have been applied in scanning probe and electron microscopies during the last years, aiming for automatized and efficient image analysis. This work introduces a free and open source tool (AiSurf: Automated Identification of Surface Images) developed to inspect atomically resolved images via scale-invariant feature transform and clustering algorithms. AiSurf extracts primitive lattice vectors, unit cells, and structural distortions from the original image, with no pre-assumption on the lattice and minimal user intervention. The method is applied to various atomically resolved non-contact atomic force microscopy images of selected surfaces with different levels of complexity: anatase TiO

₂(101), oxygen deficient rutile TiO

₂(110) with and without CO adsorbates, SrTiO

₃(001) with Sr vacancies and graphene with C vacancies. The code delivers excellent results and is tested against atom misclassification and artifacts, thereby facilitating the interpretation of scanning probe microscopy images.

Organisation(en)

Computergestützte Materialphysik

Externe Organisation(en)

Technische Universität Wien, Charles University Prague, Università di Bologna

Journal

Machine Learning: Science and Technology

Band

4

Anzahl der Seiten

9

ISSN

2632-2153

DOI

https://doi.org/10.1088/2632-2153/acb5e0

Publikationsdatum

01-2023

Peer-reviewed

Ja

ÖFOS 2012

102019 Machine Learning, 103009 Festkörperphysik

Schlagwörter

ASJC Scopus Sachgebiete

Software, Artificial Intelligence, Human-computer interaction

Link zum Portal

https://ucrisportal.univie.ac.at/de/publications/04f766cb-08c6-4932-8f44-5e1394934d4e