cs.LGNov 8, 2026

Building heterogeneous multistep workflows in automated microscopy: reward design and knowledge transfer for autonomous structure property discovery

Authors: Sergei V. Kalinin

Organizations: Department of Materials Science and Engineering, University of Tennessee, Knoxville, TN 37996, USA · Department of Electrical Engineering and Computer Science, University of Tennessee, Knoxville, TN 37996, USA

Abstract

Autonomous microscopy can turn fast acquisition into scientific progress when it decides not only where to measure, but also what information to acquire, at what scan rate, and when to recalibrate the instrument. We develop a budget constrained framework for such multistep structure-property workflows. It combines explicit scientific rewards, action costs, instrument observation models, transfer of pre experiment knowledge into the online campaign, and evaluation kept independent of the controller. The transferred knowledge includes predictor accuracy and computational cost, empirical learner maturity functions that weight model-derived rewards, and drift characteristics established before controller training. Using a real electron energy-loss spectroscopy dataset, we run two complementary campaigns. In the first, the controller chooses between imaging and spectroscopy, image size, and scan speed. In the second, the instrument drifts and the controller also decides when to recalibrate. The campaigns show that response discovery and structure-property learning favor different surrogate models and acquisition strategies. They also show that simple acquisition rules form strong, practical baselines. Independent error analysis reveals where model uncertainty is and is not a reliable learning signal. In the drift campaign, explicit registration greatly improves positional accuracy, and the framework measures what this costs in spectroscopy throughput. Together, these results provide a reproducible way to design, compare, and audit autonomous experiments, and they define what microscopes must provide for deployment: independently executable actions, characterized scan and detector responses, timestamped registration telemetry, and complete action records.

Explore similar work

CardsList
  1. PATHFINDER: Multi-objective discovery in structural and spectral spaces

    Apr 5, 2026Kamyar Barakati, Boris N. Slautin, Utkarsh Pratiush +2Autonomous ExperimentationMulti-Objective Optimization

  2. Novelty-Driven Target-Space Discovery in Automated Electron and Scanning Probe Microscopy

    Mar 17, 2026Utkarsh Pratiush, Kamyar Barakati, Boris N. Slautin +4Deep Kernel LearningScanning Transmission Electron Microscopy

  3. From Closed-Loop Optimization to Open Decision Making: Coupled Digital Twins for Predictive and Autonomous Microscopy

    Jul 7, 2026Yu Liu, Boris Slautin, Ian Mercer +2Digital TwinsAutonomous Experimentation