Machine Learning-Enabled Fast-Scan STEM for the Precise Identification of Labile Single-Atom Sites

supports, circumventing the limitations of high-noise imaging. Analysis reveals random displacements of ∼3.2% relative to ideal lattice sites, offering a direct glimpse into intrinsic structural disorder. Furthermore, we observe persistent heterogeneity in the local electric field across Pt atomic columns in differential phase contrast (DPC) imaging. These results suggest that single-atom sites locate in a highly dynamic, nonideal equilibrium state. This study also establishes a rigorous computational framework for resolving atomic-scale structures under noisy imaging conditions.