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

DOI: 10.1038/s41524-022-00949-7

Authors: Kevin P. Treder (University of Oxford) , Chen Huang (University of Oxford) , Cameron G. Bell (The University of Edinburgh) , Thomas J. A. Slater (Cardiff University) , Manfred E. Schuster (Diamond Light Source; Johnson Matthey Technology Centre) , Dogan Ozkaya (Diamond Light Source; Johnson Matthey Technology Centre) , Judy S. Kim (University of Oxford; Rosalind Franklin Institute) , Angus I. Kirkland (University of Oxford; Rosalind Franklin Institute; Diamond Light Source)
Co-authored by industrial partner: Yes

Type: Journal Paper
Journal: Npj Computational Materials , VOL 9

State: Published (Approved)
Published: February 2023
Diamond Proposal Number(s): 25427 , 23814

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.

Subject Areas: Materials, Information and Communication Technology, Chemistry

Diamond Offline Facilities: Electron Physical Sciences Imaging Centre (ePSIC)
Instruments: E02-JEM ARM 300CF

Added On: 07/02/2023 15:58

Documents:
s41524-022-00949-7.pdf

Discipline Tags:

Artificial Intelligence Physical Chemistry Catalysis Information & Communication Technologies Chemistry Materials Science Nanoscience/Nanotechnology

Technical Tags:

Microscopy Electron Microscopy (EM) Scanning Transmission Electron Microscopy (STEM)