A High Throughput and Unbiased Machine Learning Approach for Classification of Graphene Dispersions

Significant research to define and standardize terminologies for describing stacks of atomic layers in bulk graphene materials has been undertaken. Most methods to measure the stacking characteristics are time consuming and are not suited for obtaining information by directly imaging dispersions. Conventional optical microscopy has difficulty in identifying the size and thickness of a few layers of graphene stacks due to their low photon absorption capacity. Utilizing a contrast based on anisotropic refractive index in 2D materials, it is shown that localized thickness-specific information can be captured in birefringence images of graphene dispersions. Coupling pixel-by-pixel information from brightfield and birefringence images and using unsupervised statistical learning algorithms, three unique data clusters representing flakes (unexfoliated), nanoplatelets (partially exfoliated), and 2D sheets (well-exfoliated) species in various laboratory-based and commercial dispersions of graphene and graphene oxide are identified. The high-throughput, multitasking capability of the approach to classify stacking at sub-nanometer to micrometer scale and measure the size, thickness, and concentration of exfoliated-species in generic dispersions of graphene/graphene oxide are demonstrated. The method, at its current stage, requires less than half an hour to quantitatively assess one sample of graphene/graphene oxide dispersion.