A. V. Nartova, A. V. Matveev, L. M. Kovtunova, A. G. Okunev, “Deep machine learning for STEM image analysis”, Mendeleev Commun., 2024, Volume 34, Issue 6,Pages <nobr>774

Communications

Deep machine learning for STEM image analysis

A. V. Nartova^ab, A. V. Matveev^a, L. M. Kovtunova^ab, A. G. Okunev^a

^a Department of Chemistry, Novosibirsk State University, Novosibirsk, Russian Federation
^b G.K. Boreskov Institute of Catalysis, Siberian Branch of the Russian Academy of Sciences, Novosibirsk, Russian Federation

Abstract: The universal, user-friendly online iOk Platform for automatic recognition of any type of objects in images based on deep machine learning is presented. Services aggregated in the iOk Platform significantly reduce the time spent on quantitative image analysis, decrease the influence of the subjective factor and increase the accuracy of the analysis by expanding the set of data that can be analyzed automatically. It is shown how the services can be used to analyze scanning transmission electron microscopy images obtained in heterogeneous catalysis studies, allowing for measurements of thousands of objects in an image, as well as simultaneous analysis of objects of different types, namely: nanoparticles and single sites.

Keywords: deep machine learning, STEM, automatic recognition of objects, supported catalysts, neural network, microscopy, image analysis.

Language: English

DOI: 10.1016/j.mencom.2024.10.002