Unsupervised reward-driven image segmentation in automated scanning transmission electron microscopy experiments

Automated experiments in scanning transmission electron microscopy (STEM) require rapid image segmentation to optimize the data representation for human interpretation, decision-making, site-selective spectroscopy, and atomic manipulation. Currently, segmentation tasks are typically performed using supervised machine learning methods, which require human-labeled data and are sensitive to out-of-distribution drift effects caused by changes in resolution, sampling, or beam shape. Here, we operationalize and benchmark a recently proposed reward-driven optimization workflow for on-the-fly image analysis in STEM. This unsupervised approach is much more robust because it does not rely on human labels and is fully explainable. The explanatory feedback can help humans verify the decision-making and potentially tune the model by selecting the position along the Pareto frontier of the reward functions. We established the timing and effectiveness of this method and demonstrated its capability for real-time performance in highthroughput and dynamic automated STEM experiments. The reward-driven approach allows for the construction of explainable robust analysis workflows and can be generalized to a broad range of image analysis tasks in electron and scanning probe microscopy and chemical imaging.

Authors

Institutions

Publication Details

Journal
Nanotechnology
Published
2026-11-16
DOI
https://doi.org/10.1088/1361-6528/aec26d
Citations
8
Primary Topic
Advanced Electron Microscopy Techniques and Applications
Type
article
Field-Weighted Citation Impact
4.49

Funders

Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
NOV
article

Unsupervised reward-driven image segmentation in automated scanning transmission electron microscopy experiments

Kamyar Barakati, Sergei V. Kalinin, Austin Houston, Gerd J. Duscher et al.
8 citations
Nanotechnology
Advanced Electron Microscopy Techniques and Applications
4.49
article

Unsupervised reward-driven image segmentation in automated scanning transmission electron microscopy experiments

Kamyar Barakati, Sergei V. Kalinin, Austin Houston, Gerd J. Duscher, Utkarsh Pratiush
article en
8 citations

Abstract

Automated experiments in scanning transmission electron microscopy (STEM) require rapid image segmentation to optimize the data representation for human interpretation, decision-making, site-selective spectroscopy, and atomic manipulation. Currently, segmentation tasks are typically performed using supervised machine learning methods, which require human-labeled data and are sensitive to out-of-distribution drift effects caused by changes in resolution, sampling, or beam shape. Here, we operationalize and benchmark a recently proposed reward-driven optimization workflow for on-the-fly image analysis in STEM. This unsupervised approach is much more robust because it does not rely on human labels and is fully explainable. The explanatory feedback can help humans verify the decision-making and potentially tune the model by selecting the position along the Pareto frontier of the reward functions. We established the timing and effectiveness of this method and demonstrated its capability for real-time performance in highthroughput and dynamic automated STEM experiments. The reward-driven approach allows for the construction of explainable robust analysis workflows and can be generalized to a broad range of image analysis tasks in electron and scanning probe microscopy and chemical imaging.

Nanotechnology
University of Tennessee at Knoxville (US)
U.S. Department of Energy, Office of Science, Basic Energy Sciences, Oak Ridge National Laboratory, Energy Frontier Research Centers
Openalex Percentile: Top 6%
Advanced Electron Microscopy Techniques and Applications
4.49
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.

Laika access coming soon