Toward automated classification of monolayer versus few-layer nanomaterials using texture analysis and neural networks

Automated statistical analysis of raman spectra of nanomaterials

Both at the academic and the industrial level, material scientists are exploring routes for mass production and functionalization of graphene, carbon nanotubes (CNT), carbon dots, 2D materials, and heterostructures of these. Proper application of the novel materials requires fast and thorough characterization of the samples. Raman spectroscopy stands out as a standard non-invasive technique capable of giving key information on the structure and electronic properties of nanomaterials, including the presence of defects, degree of functionalization, diameter (in the case of CNT), different polytypes, doping, etc. Here, we present a computational tool to automatically analyze the Raman spectral features of nanomaterials, which we illustrate with the example of CNT and graphene. The algorithm manages hundreds of spectra simultaneously and provides statistical information (distribution of Raman shifts, average values of shifts and relative intensities, standard deviations, correlation between different peaks, etc.) of the main spectral features defining the structure and electronic properties of the samples, as well as publication-ready graphical material.

Fractal Nature Bridge between Neural Networks and Graph Theory Approach within Material Structure Characterization

Many recently published research papers examine the representation of nanostructures and biomimetic materials, especially using mathematical methods. For this purpose, it is important that the mathematical method is simple and powerful. Theory of fractals, artificial neural networks and graph theory are most commonly used in such papers. These methods are useful tools for applying mathematics in nanostructures, especially given the diversity of the methods, as well as their compatibility and complementarity. The purpose of this paper is to provide an overview of existing results in the field of electrochemical and magnetic nanostructures parameter modeling by applying the three methods that are “easy to use”: theory of fractals, artificial neural networks and graph theory. We also give some new conclusions about applicability, advantages and disadvantages in various different circumstances.

Universal image segmentation for optical identification of 2D materials

Machine learning methods are changing the way data is analyzed. One of the most powerful and widespread applications of these techniques is in image segmentation wherein disparate objects of a digital image are partitioned and classified. Here we present an image segmentation program incorporating a series of unsupervised clustering algorithms for the automatic thickness identification of two-dimensional materials from digital optical microscopy images. The program identifies mono- and few-layer flakes of a variety of materials on both opaque and transparent substrates with a pixel accuracy of roughly 95%. Contrasting with previous attempts, application generality is achieved through preservation and analysis of all three digital color channels and Gaussian mixture model fits to arbitrarily shaped data clusters. Our results provide a facile implementation of data clustering for the universal, automatic identification of two-dimensional materials exfoliated onto any substrate.