Abstract
The availability of atomically resolved imaging modalities enables an unprecedented view into the local structural states of materials, which manifest themselves by deviations from the fundamental assumptions of periodicity and symmetry. Consequently, approaches that aim to extract these local structural states from atomic imaging data with minimal assumptions regarding the average crystallographic configuration of a material are indispensable to advances in structural and chemical investigations of materials. Here, we present an approach to identify and classify local structural states that is rooted in computer vision. This approach introduces a definition of a structural state that is composed of both local and nonlocal information extracted from atomically resolved images, and is wholly untethered from the familiar concepts of symmetry and periodicity. Instead, this approach relies on computer vision techniques such as feature detection, and concepts such as scale invariance. We present the fundamental aspects of local structural state extraction and classification by application to simulated scanning transmission electron microscopy images, and analyze the robustness of this approach in the presence of common instrumental factors such as noise, limited spatial resolution, and weak contrast. Finally, we apply this computer vision-based approach for the unsupervised detection and classification of local structural states in an experimental electron micrograph of a complex oxides interface, and a scanning tunneling micrograph of a defect-engineered multilayer graphene surface.
| Original language | English |
|---|---|
| Article number | 14 |
| Journal | Advanced Structural and Chemical Imaging |
| Volume | 2 |
| Issue number | 1 |
| DOIs | |
| State | Published - Jan 1 2016 |
Funding
NL conceived and designed the research, and performed the analysis. QH and AB performed the simulations and collected the STEM data. MZ collected the STM data. NL and AB wrote the manuscript with contributions from MZ. All authors read and approved the final manuscript. NL thanks Sergei V. Kalinin for insightful discussions and for bringing his attention to this research topic. This work was supported by the Eugene P. Wigner Fellowship (NL) at Oak Ridge National Laboratory (ORNL), a US Department of Energy (DOE) facility managed by UT-Battelle, LLC for US DOE Office of Science under Contract No. DE-AC05-00OR22725. Data analysis was performed at the Center for Nanophase Materials Sciences, a DOE Office of Science User Facility at ORNL. Electron microscopy imaging and simulations (AB, QH) were supported by Materials Science and Engineering Division of the US DOE Office of Science. MZ acknowledges the support from Materials Science and Engineering Division of the US DOE Office of Science. The authors declare that they have no competing interests. NL thanks Sergei V. Kalinin for insightful discussions and for bringing his attention to this research topic. This work was supported by the Eugene P. Wigner Fellowship (NL) at Oak Ridge National Laboratory (ORNL), a US Department of Energy (DOE) facility managed by UT-Battelle, LLC for US DOE Office of Science under Contract No. DE-AC05-00OR22725. Data analysis was performed at the Center for Nanophase Materials Sciences, a DOE Office of Science User Facility at ORNL. Electron microscopy imaging and simulations (AB, QH) were supported by Materials Science and Engineering Division of the US DOE Office of Science. MZ acknowledges the support from Materials Science and Engineering Division of the US DOE Office of Science.
Keywords
- Computer vision
- Scanning transmission electron microscopy
- Scanning tunneling microscopy
- Unsupervised machine learning