University of Vienna, Faculty of Physics and Center for Computational Materials Science, 1090 Vienna, Austria
University of Vienna, Vienna Doctoral School in Physics, 1090 Vienna, Austria
Institut für Angewandte Physik,
TU Wien, 1040 Wien, Austria
Department of Surface and Plasma Science, Faculty of Mathematics and Physics, Charles University, 180 00 Prague 8, Czech Republic
Dipartimento di Fisica e Astronomia, Università di Bologna, 40127 Bologna, Italy
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 TiO2(101), oxygen deficient rutile TiO2(110) with and without CO adsorbates, SrTiO3(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.
Corresponding author: Marco Corrias.
You can download a PDF file of this open-access article from Machine Learning: Science and Technology or from the IAP/TU Wien web server.