Nanoparticle detection from TEM images with deep learning

Leveraging cryogenic electron microscopy for advancing battery design

“…Recently, there has been a renaissance in AI-assisted data postprocessing, owing to the success of deep learning (DL). [61][62][63] However, certain limitations present in these studies due to the use of datasets from one specific sample 62 and the lack of a universal model for all the high-resolution images from one dataset. Thus, it is essential to develop coding tools that can be equipped with DL to process multiple TEM images and use suitable segmentation method to extract features such as the spots in fast Fourier transform (FFT) patterns so that crystallographic information about the specimens can be processed and summarized in an accurate way.…”

Adaptive iron-based magnetic nanomaterials of high performance for biomedical applications

“…The trained model can induce a two-fold increase in resolution to retrieve the useful features of the materials. Some novel algorithms were used in the processing of microscopic images to quickly and efficiently characterize nanomaterials in terms of their morphologies [67,68], sizes [69], particle densities [70], and crystallographic defects [71]. Lately, a method applying a genetic algorithm for mass-throughput analysis of the morphologies of nanoparticles is reported [72].…”

Application of Artificial Neural Networks in Crystal Growth of Electronic and Opto-Electronic Materials

“…Applications of CNN in the crystal growth are yet to come. Still, numerous papers are available on the applications of the CNNs in the fields pertinent to crystal growth simulations and crystal characterization, e.g., the prediction of turbulence [41], derivation of material data [5,[42][43][44][45][46], optimization of CFD meshes [3], classification of atomically resolved Scanning Transmission Electron Microscopy (STEM) [47], and Transmission Electron Microscopy (TEM) [48] images, just to mention a few. Different accuracy of the NARX predictions in bulk and films crystal growth in the above mentioned examples may be related to the different time scales of the transport phenomena (e.g., large time scale for the removal of the latent heat from the crystallization front in large industrial size bulk crystals versus short time scale in thin films) between these two crystal growth processes.…”