Deep reinforcement learning for data-driven adaptive scanning in ptychography
- Author(s)
- Marcel Schloz, Johannes Müller, Thomas C. Pekin, Wouter Van den Broek, Jacob Madsen, Toma Susi, Christoph T. Koch
- Abstract
We present a method that lowers the dose required for an electron ptychographic reconstruction by adaptively scanning the specimen, thereby providing the required spatial information redundancy in the regions of highest importance. The proposed method is built upon a deep learning model that is trained by reinforcement learning, using prior knowledge of the specimen structure from training data sets. We show that using adaptive scanning for electron ptychography outperforms alternative low-dose ptychography experiments in terms of reconstruction resolution and quality.
- Organisation(s)
- Physics of Nanostructured Materials
- External organisation(s)
- Humboldt-Universität zu Berlin
- Journal
- Scientific Reports
- Volume
- 13
- No. of pages
- 10
- ISSN
- 2045-2322
- DOI
- https://doi.org/10.48550/arXiv.2203.15413
- Publication date
- 05-2023
- Peer reviewed
- Yes
- Austrian Fields of Science 2012
- 103018 Materials physics, 103042 Electron microscopy, 102019 Machine learning
- ASJC Scopus subject areas
- General
- Portal url
- https://ucrisportal.univie.ac.at/en/publications/ffe03a04-074d-4b55-a172-4ef95a6b1e39