Understanding lattice deformations is crucial in determining the properties of nanomaterials, which can become more prominent in future applications ranging from energy harvesting to electronic devices. However, it remains challenging to reveal unexpected deformations that crucially affect material properties across a large sample area. Here, we demonstrate a rapid and semi-automated unsupervised machine learning approach to uncover lattice deformations in materials. Our method utilizes divisive hierarchical clustering to automatically unveil multi-scale deformations in the entire sample flake from the diffraction data using four-dimensional scanning transmission electron microscopy (4D-STEM). Our approach overcomes the current barriers of large 4D data analysis without a priori knowledge of the sample. Using this purely data-driven analysis, we have uncovered different types of material deformations, such as strain, lattice distortion, bending contour, etc., which can significantly impact the band structure and subsequent performance of nanomaterials-based devices. We envision that this data-driven procedure will provide insight into materials’ intrinsic structures and accelerate the discovery of materials.
Understanding the structure of materials is crucial for engineering devices and materials with enhanced performance. Four-dimensional scanning transmission electron microscopy (4D-STEM) is capable of mapping nanometer-scale local crystallographic structure over micron-scale field of views. However, 4D-STEM datasets can contain tens of thousands of images from a wide variety of material structures, making it difficult to automate detection and classification of structures. Traditional automated analysis pipelines for 4D-STEM focus on supervised approaches, which require prior knowledge of the material structure and cannot describe anomalous or deviant structures. In this article, a pipeline for engineering 4D-STEM feature representations for unsupervised clustering using non-negative matrix factorization (NMF) is introduced. Each feature is evaluated using NMF and results are presented for both simulated and experimental data. It is shown that some data representations more reliably identify overlapping grains. Additionally, real space refinement is applied to identify spatially distinct sample regions, allowing for size and shape analysis to be performed. This work lays the foundation for improved analysis of nanoscale structural features in materials that deviate from expected crystallographic arrangement using 4D-STEM.
more » « less- Award ID(s):
- 1848079
- NSF-PAR ID:
- 10392405
- Publisher / Repository:
- Oxford University Press
- Date Published:
- Journal Name:
- Microscopy and Microanalysis
- Volume:
- 28
- Issue:
- 6
- ISSN:
- 1431-9276
- Page Range / eLocation ID:
- p. 1998-2008
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
more » « less
Abstract -
more » « less
Abstract Electron backscattering diffraction provides the analysis of crystalline phases at large scales (microns) while precession electron diffraction may be used to get 4D‐STEM data to elucidate structure at nanometric resolution. Both are limited by the probe size and also exhibit some difficulties for the generation of large datasets, given the inherent complexity of image acquisition. The latter appoints the application of advanced machine learning techniques, such as deep learning adapted for several tasks, including pattern matching, image segmentation, etc. This research aims to show how Gabor filters provide an appropriate feature extraction technique for electron microscopy images that could prevent the need of large volumes of data to train deep learning models. The work presented herein combines an algorithm based on Gabor filters for feature extraction and an unsupervised learning method to perform particle segmentation of polyhedral metallic nanoparticles and crystal orientation mapping at atomic scale. Experimental results have shown that Gabor filters are convenient for electron microscopy images analysis, that even a nonsupervised learning algorithm can provide remarkable results in crystal segmentation of individual nanoparticles. This approach enables its application to dynamic analysis of particle transformation recorded with aberration‐corrected microscopy, offering new possibilities of analysis at nanometric scale.
-
more » « less
Abstract With shrinking dimensions in integrated circuits, sensors, and functional devices, there is a pressing need to develop nanofabrication techniques with simultaneous control of morphology, microstructure, and material composition over wafer length scales. Current techniques are largely unable to meet all these conditions, suffering from poor control of morphology and defect structure or requiring extensive optimization or post‐processing to achieve desired nanostructures. Recently, thermomechanical nanomolding (TMNM) has been shown to yield single‐crystalline, high aspect ratio nanowires of metals, alloys, and intermetallics over wafer‐scale distances. Here, TMNM is extended for wafer‐scale fabrication of 2D nanostructures. Using In, Al, and Cu, nanomold nanoribbons with widths < 50 nm, depths ≈0.5–1 µm and lengths ≈7 mm into Si trenches at conditions compatible is successfully with back end of line processing . Through SEM cross‐section imaging and 4D‐STEM grain orientation maps, it is shown that the grain size of the bulk feedstock is transferred to the nanomolded structures up to and including single crystal Cu. Based on the retained microstructures of molded 2D Cu, the deformation mechanism during molding for 2D TMNM is discussed.
-
Abstract Material properties strongly depend on the nature and concentration of defects. Characterizing these features may require nano- to atomic-scale resolution to establish structure–property relationships. 4D-STEM, a technique where diffraction patterns are acquired at a grid of points on the sample, provides a versatile method for highlighting defects. Computational analysis of the diffraction patterns with virtual detectors produces images that can map material properties. Here, using multislice simulations, we explore different virtual detectors that can be applied to the diffraction patterns that go beyond the binary response functions that are possible using ordinary STEM detectors. Using graphene and lead titanate as model systems, we investigate the application of virtual detectors to study local order and in particular defects. We find that using a small convergence angle with a rotationally varying detector most efficiently highlights defect signals. With experimental graphene data, we demonstrate the effectiveness of these detectors in characterizing atomic features, including vacancies, as suggested in simulations. Phase and amplitude modification of the electron beam provides another process handle to change image contrast in a 4D-STEM experiment. We demonstrate how tailored electron beams can enhance signals from short-range order and how a vortex beam can be used to characterize local symmetry.more » « less
-
more » « less
Abstract The budding field of materials informatics has coincided with a shift towards artificial intelligence to discover new solid-state compounds. The steady expansion of repositories for crystallographic and computational data has set the stage for developing data-driven models capable of predicting a bevy of physical properties. Machine learning methods, in particular, have already shown the ability to identify materials with near ideal properties for energy-related applications by screening crystal structure databases. However, examples of the data-guided discovery of entirely new, never-before-reported compounds remain limited. The critical step for determining if an unknown compound is synthetically accessible is obtaining the formation energy and constructing the associated convex hull. Fortunately, this information has become widely available through density functional theory (DFT) data repositories to the point that they can be used to develop machine learning models. In this Review, we discuss the specific design choices for developing a machine learning model capable of predicting formation energy, including the thermodynamic quantities governing material stability. We investigate several models presented in the literature that cover various possible architectures and feature sets and find that they have succeeded in uncovering new DFT-stable compounds and directing materials synthesis. To expand access to machine learning models for synthetic solid-state chemists, we additionally present
MatLearn . This web-based application is intended to guide the exploration of a composition diagram towards regions likely to contain thermodynamically accessible inorganic compounds. Finally, we discuss the future of machine-learned formation energy and highlight the opportunities for improved predictive power toward the synthetic realization of new energy-related materials.
