About this Abstract |
Meeting |
2025 TMS Annual Meeting & Exhibition
|
Symposium
|
Characterization of Materials through High Resolution Coherent Imaging
|
Presentation Title |
AI-Driven Workflow for Autonomous High-Resolution Scanning X-Ray Microscopy |
Author(s) |
Tao Zhou, Saugat Kandel, Mathew Cherukara, Charadatta Phatak, Martin Holt |
On-Site Speaker (Planned) |
Tao Zhou |
Abstract Scope |
We report the Fast Autonomous Scanning Toolkit (FAST) that combines a neural network, route optimization, and efficient hardware controls to enable a self-driving experiment that actively identifies and measures a sparse but representative data subset in lieu of the full dataset. FAST requires no prior information about the sample and is computationally efficient. We demonstrate FAST in a dark-field X-ray microscopy experiment on an exfoliated multilayer WSe2 thin film. Our studies show that a FAST scan of <25% is sufficient to accurately image all the spontaneously formed bubbles in the sample, with a decision making time of less than 1 second per 50 points.
FAST is easy to adapt for any scanning microscope. Its broad adoption will empower general multi-level studies of materials evolution with respect to time, temperature, or other parameters. |
Proceedings Inclusion? |
Planned: |
Keywords |
Machine Learning, Characterization, |