Centers and Institutes
Published December 20, 2023 | Version v1
Journal article Open

Machine learning for automated experimentation in scanning transmission electron microscopy

Creators

  • 1. University of Tennessee, Knoxville
  • 2. Oak Ridge National Laboratory
  • 3. University of Chicago
  • 4. Pacific Northwest National Laboratory
  • 5. Drexel University

Description

Machine learning (ML) has become critical for post-acquisition data analysis in (scanning) transmission electron microscopy, (S)TEM, imaging and spectroscopy. An emerging trend is the transition to real-time analysis and closed-loop microscope operation. The effective use of ML in electron microscopy now requires the development of strategies for microscopy-centric experiment workflow design and optimization. Here, we discuss the associated challenges with the transition to active ML, including sequential data analysis and out-of-distribution drift effects, the requirements for edge operation, local and cloud data storage, and theory in the loop operations. Specifically, we discuss the relative contributions of human scientists and ML agents in the ideation, orchestration, and execution of experimental workflows, as well as the need to develop universal hyper languages that can apply across multiple platforms. These considerations will collectively inform the operationalization of ML in next-generation experimentation.

Data availability

Since, this is a perspective, all data pertaining to this is available from the individual manuscripts cited, depending upon their data sharing policies.

Files

Machine-learning-for-automated-experimentation-in-scanning-transmission-electron-microscopy.pdf

Files (4.5 MB)

Additional details

Identifiers

DOI
10.1038/s41524-023-01142-0
Other
oai:uchicago.tind.io:10238

Funding

U.S. Department of Energy
DE-AC05-00OR22725
UT Knoxville
start-up funding
U.S. Department of Energy
Battelle Memorial Institute
National Science Foundation
OAC:DMR:CSSI – 2246463
U.S. Department of Energy
Office of Science, Office of Advanced Scientific Computing Research
U.S. Department of Commerce
National Institute of Standards and Technology

UChicago Information

Division(s)
Physical Sciences Division
Center(s) or Institute(s)
Data Science Institute