Atomic mechanisms for the Si atom dynamics in graphene: chemical transformations at the edge and in the bulk

Recent advances in scanning transmission electron microscopy (STEM) allow to observe solid-state transformations and reactions in materials induced by thermal stimulus or electron beam on the atomic level. However, despite the rate at which large volumes of data can be generated (sometimes in the gigabyte to terabyte range per single experiment), approaches for the extraction of material-specific knowledge on the kinetics and thermodynamics of these processes are still lacking. One of the critical issues lies in being able to map the evolution of various atomic structures and determine the associated transition probabilities directly from raw experimental data characterized by high levels of noise and missing structural elements. Here, we demonstrate an approach based on the combination of multiple machine learning techniques to study the dynamic behavior of e-beam irradiated Si atoms in the bulk and at the edges of single-layer graphene in STEM experiments. First, a deep learning network is used to convert experimental STEM movies into coordinates of individual Si and carbon atoms. Then, a Gaussian mixture model is further used to establish the elementary atomic configurations of the Si atoms, defining the bonding geometries and chemical species and accounting for the discrete rotational symmetry of the host lattice. Finally, the frequencies and Markov transition probabilities between these states are determined. This analysis enables insight into the thermodynamics of defect populations and chemical reaction networks from the atomically resolved STEM data. Here, we observe a clear tendency for the formation of a 1D Si crystal along zigzag direction of graphene edges and for the Si impurity coupling to topological defects in bulk graphene.