Building workflows for an interactive human-in-the-loop automated experiment (hAE) in STEM-EELS

2025/01/01 by Utkarsh Pratiush, Kevin M. Roccapriore, Yongtao Liu +3 · 1 voice
Computer Science · Engineering · #Advanced Data Processing Techniques #Distributed and Parallel Computing Systems #Engineering Education and Technology

paper · pdf · doi:10.1039/d5dd00033e

openalex publication_date 2025/01/01 · openalex created_date 2025/10/10 · openalex updated_date 2026/08/01

Abstract

This work presents a human-in-the-loop framework for STEM-EELS using deep kernel learning and Bayesian optimization to accelerate spectral acquisition and improve adaptive discovery of nanoscale features beyond grid sampling.

Citations

• Hyper-Parameter Optimization: A Review of Algorithms and Applications
• Active learning in open experimental environments: selecting the right information channel(s) based on predictability in deep kernel learning

Discussions

• In this week's first featured article, Pratiush, Kalinin et al. investigate the design of deep kernel learning workflows for STEM-EELS and present a human-in-the-loop approach to address challenges. R [bsky, 1 points, 0 comments]

Related

• Building Workflows for Interactive Human in the Loop Automated Experiment (hAE) in STEM-EELS
• Implementing dynamic high-performance computing supported workflows on Scanning Transmission Electron Microscope
• Human-in-the-loop: The future of Machine Learning in Automated Electron Microscopy
• Deep Learning for EELS hyperspectral images unmixing -- using autoencoders
• Embedding theory in ML toward real-time tracking of structural dynamics through hyperspectral datasets