Quantifying Atomically Dispersed Catalysts Using Deep Learning Assisted Microscopy

The catalytic performance of atomically dispersed catalysts(ADCs)is greatly influenced by their atomic configurations, such as atom-atomdistances, clustering of atoms into dimers and trimers, and theirdistributions. Scanning transmission electron microscopy (STEM) isa powerful technique for imaging ADCs at the atomic scale; however,most STEM analyses of ADCs thus far have relied on human labeling,making it difficult to analyze large data sets. Here, we introducea convolutional neural network (CNN)-based algorithm capable of quantifyingthe spatial arrangement of different adatom configurations. The algorithmwas tested on different ADCs with varying support crystallinity andhomogeneity. Results show that our algorithm can accurately identifyatom positions and effectively analyze large data sets. This workprovides a robust method to overcome a major bottleneck in STEM analysisfor ADC catalyst research. We highlight the potential of this methodto serve as an on-the-fly analysis tool for catalysts in future insitu microscopy experiments.