Atomic resolution electron microscopy has become an essential tool for many scientific fields, when direct visualization of atomic arrangements and defects is needed, as they dictate the material's functional and mechanical behavior. Achieving this precision is often hindered by noise, arising from electron microscopy acquisition limitations. In this work, a deep learning‐based denoising approach is presented that operates in the frequency domain using a convolutional neural network U‐Net. To generate the training dataset, Fast Fourier Transform patterns are simulated for various materials, crystallographic orientations, and imaging conditions, introducing noise and drift artifacts to mimic experimental scenarios. The model is trained to identify relevant frequency components, which are used to enhance experimental images by applying element‐wise multiplication in the frequency domain. The model enhances experimental images by identifying and amplifying relevant frequency components, significantly improving signal‐to‐noise ratio while preserving structural integrity. Applied to both Ge quantum wells and WS 2 monolayers, the method facilitates more accurate strain quantitative analyses, critical for assessing functional device performance (e.g., quantum properties in SiGe quantum wells), and enables the clear identification of light atoms in beam‐sensitive materials. The results demonstrate the potential of automated frequency‐based deep learning denoising as a useful tool for atomic‐resolution nanomaterials analysis.
Pinto‐Huguet et al. (2025) studied this question.