Automating Electron Microscopy through Machine Learning and USETEM

Michael Xu, Abinash Kumar, James LeBeau
2021 Microscopy and Microanalysis  
Advances in electron microscopy have led to an increasing emphasis on multi-scale structural and chemical materials characterization. Coupled with the rise in "big data" and machine learning (ML)-based analysis, there has been a growing need for large, representative datasets for quantification or training [1] . Yet, electron microscopy has remained a manual process, with limited representative datasets providing anecdotal, rather than statistically significant results. Automation, which has
more » ... n achieved in the biological and chemical sciences through CryoEM, is the natural solution, yet current progress for materials-centric characterization has been constrained to material-or task-specific data collection, which can be limiting given the sample heterogeneities of materials research [2] . These challenges demand a new level of automation and instrument control, crucial for efficient and reproducible electron microscopy.
doi:10.1017/s1431927621010394 fatcat:6uccblcwijh73mjftxik7gx62y