Search

• A classification neural networks and a regression neural network were trained on simulated CBED patterns to predict TEM sample thickness from 4D STEM convergent beam diffraction patterns. • Sub-unit cell lateral resolution, single unit cell thickness resolution, and 1 nm deviation from quantitative HAADF STEM thickness estimates were achieved. • Convolution neural networks were trained on simulation data with automatic labelling, and do not require quantitative matching between experiment and simulation. • Similar methodology might be extended to learn other physical properties of a sample from large 4D STEM datasets. Two types of convolutional neural network (CNN) models, a discrete classification network and a continuous regression network, were trained to determine local sample thickness from convergent beam diffraction (CBED) patterns of SrTiO 3 collected in a scanning transmission electron microscope (STEM) at atomic column resolution. Acquisition of atomic resolution CBED patterns for this purpose requires careful balancing of CBED feature size in pixels, acquisition speed, and detector dynamic range. The training datasets were derived from multislice simulations, which must be convolved with incoherent source broadening. Sample thicknesses were also determined using quantitative high-angle annular dark-field (HAADF) STEM images acquired simultaneously. The regression CNN performed well on sample thinner than 35 nm, with 70% of the CNN results within 1 nm of HAADF thickness, and 1.0 nm overall root mean square error between the two measurements. The classification CNN was trained for a thicknesses up to 100 nm and yielded 66% of CNN results within one classification increment of 2 nm of HAADF thickness. Our approach depends on methods from computer vision including transfer learning and image augmentation. [ABSTRACT FROM AUTHOR]