Transcending Material Structure and Chemical Uncertainty through Advanced Data Handling and Modeling

J. Aguiar, M. Gong, T. Tasdizen
Idaho National Laboratory, Idaho, United States

Keywords: Artifical intelligence, material informatics, microscopy, diffraction, engineering qualification

Extending from the micron to the atomic scale transmission electron microscopy is a powerful research tool for structural and chemical analysis for materials research. The breadth of data collected simultaneously in the latest generation of scanning transmission electron microscopes presents challenges and opportunities for advancements in microscopy, multi-modal data analytics, image-based forensics, and materials research. Recent advancements in deep learning have made it possible to analyze these massive data sets and perform complex imaging tasks. However, deep learning and augmented analysis have not yet disrupted the microscopy and microanalysis community like they have the computer vision community. In this presentation, we will discuss the development of an emerging real-time augmented feedback framework for microscopy and materials research. This includes pending developments that utilize hybridized first principal and deep learning models for augmented analysis of material properties, spectroscopy, and diffraction patterns for crystallographic analysis. In addition, we will discuss the growing potential of automating data collection from live analysis of microscope feeds for real-time event tracking in materials. The talk will conclude with examples taken from our current collaborations to augment the collection and analysis of multidimensional datasets.