nNPipe: a neural network pipeline for automated analysis of morphologically diverse catalyst systems

Abstract

We describe nNPipe for the automated analysis of morphologically diverse catalyst materials. Automated imaging routines and direct-electron detectors have enabled the collection of large data stacks over a wide range of sample positions at high temporal resolution. Simultaneously, traditional image analysis approaches are slow and hence unsuitable for large data stacks and consequently, researchers have progressively turned towards machine learning and deep learning approaches. Previous studies often detail work on morphologically uniform material systems with clearly discernible features, limited workable image sizes and training data that may be biased due to manual labelling. The nNPipe data-processing method consists of two standalone convolutional neural networks that were exclusively trained on multislice image simulations and enables fast analysis of 2048 × 2048 pixel images. Inference performance compared between idealised and real industrial catalytic samples and insights derived from subsequent data analysis are placed into the context of an automated imaging scenario.

Quantifying the thickness of WTe2 using atomic-resolution STEM simulations and supervised machine learning

“…74 Similarly, Lee et al reported a deep learning-based technique to visualize single-atom defects in high-angle annular dark-field (HAADF)-STEM images of 2D monolayers down to the picometer scale and mapped the strain field induced by such defects. 75 Therefore, ML models are powerful tools to extract structural and chemical features that can provide insights about physical properties, [76][77][78][79][80] and they are able to identify relationships in huge datasets to extract useful information without explicitly fitting the data using complex equations.…”