A5092514211- Electron and X-Ray Spectroscopy Techniques
- Machine Learning in Materials Science
- Industrial Vision Systems and Defect Detection
- Surface Chemistry and Catalysis
- Electronic and Structural Properties of Oxides
- Graph Theory and Algorithms
- X-ray Diffraction in Crystallography
- Model-Driven Software Engineering Techniques
- Advanced X-ray and CT Imaging
- Medical Imaging Techniques and Applications
- Advanced X-ray Imaging Techniques
- Advanced Electron Microscopy Techniques and Applications
- Metallurgy and Material Forming
- Semiconductor materials and devices
Pacific Northwest National Laboratory
2023-2025
University of California, Berkeley
2023
Thin film deposition is a fundamental technology for the discovery, optimization, and manufacturing of functional materials. Deposition by molecular beam epitaxy (MBE) typically employs reflection high-energy electron diffraction (RHEED) as real-time in situ probe growing film. However, state-of-the-art RHEED analysis during requires human observation. Here, we present an approach using machine learning (ML) methods to monitor, analyze, interpret images on-the-fly thin deposition. In...
The development of high-performance materials for microelectronics, energy storage, and extreme environments depends on our ability to describe direct property-defining microstructural order. Our present understanding is typically derived from laborious manual analysis imaging spectroscopy data, which difficult scale, challenging reproduce, lacks the reveal latent associations needed mechanistic models. Here, we demonstrate a multi-modal machine learning (ML) approach order electron...
Journal Article Maximizing Modalities: Accelerating Quantitative Multimodal Electron Microscopy Get access Sarah Akers, Akers National Security Directorate, Pacific Northwest Laboratory, Richland, WA, United States Search for other works by this author on: Oxford Academic Google Scholar Jenna Pope, Pope Arman Ter-Petrosyan, Ter-Petrosyan StatesDepartment of Physics, University California-Berkeley, Berkeley, CA, Bethany Matthews, Matthews Energy and Environment Rajendra Paudel, Paudel...
We present a method for the unsupervised segmentation of electron microscopy images, which are powerful descriptors materials and chemical systems. Images oversegmented into overlapping chips, similarity graphs generated from embeddings extracted domain$\unicode{x2010}$pretrained convolutional neural network (CNN). The Louvain community detection is then applied to perform segmentation. graph representation provides an intuitive way presenting relationship between chips communities....