Related Experiment Video
Updated: Sep 27, 2025
11:19
Multimodal Hierarchical Imaging of Serial Sections for Finding Specific Cellular Targets within Large Volumes
Published on: March 20, 2018
10.6K
Learning motifs and their hierarchies in atomic resolution microscopy
Jiadong Dan1,2,3, Xiaoxu Zhao4, Shoucong Ning3
1NUS Graduate School for Integrative Sciences and Engineering, National University of Singapore, 21 Lower Kent Ridge, Singapore 119077, Singapore.
Science Advances
|April 13, 2022
Summary
This study introduces a machine learning framework for extracting atomic structural motifs from materials images. This approach accelerates materials discovery by identifying new structures and quantifying disorder in complex materials.
Area of Science:
- Materials Science
- Machine Learning
- Computational Chemistry
Background:
- Accurate materials characterization and structure-property prediction are crucial for discovering new functional materials.
- Existing methods lack rapid, noise-robust frameworks for extracting multilevel atomic structural motifs from complex materials.
- Such frameworks are needed to complement, inform, and guide first-principles modeling.
Purpose of the Study:
- To develop a machine learning framework for rapid extraction of hierarchical atomic structural motifs from atomically resolved images.
- To demonstrate the framework's utility in reconstructing complex specimens with defects.
- To enable the discovery of new material structures and quantification of disorder.
Main Methods:
- Development of a machine learning framework for motif extraction from atomic resolution images.
- Application of the framework to analyze polyoxometalate (POM) and transition metal dichalcogenide (TMoS2) systems.
- Utilizing motif hierarchies to reconstruct specimens and quantify structural disorder.
Main Results:
- The framework rapidly extracts a hierarchy of complex structural motifs from atomically resolved images.
- Demonstrated reconstruction of specimens with various defects using motif hierarchies.
- Discovered a previously unidentified structure in a Molybdenum–Vanadium–Tellurium–Niobium (Mo─V─Te─Nb) polyoxometalate (POM).
- Quantified relative disorder in twisted bilayer Molybdenum disulfide (MoS2).
Conclusions:
- The developed machine learning framework enables rapid extraction of hierarchical atomic structural motifs.
- Motif hierarchies facilitate specimen reconstruction, defect analysis, and the discovery of new material structures.
- The framework provides statistically grounded insights into self-assembly pathways and disorder in complex materials.
- This approach enhances understanding of multiscale samples with imperfections and topological phases.
Related Concept Videos
01:37Super-resolution Fluorescence Microscopy
8.2K
Super-resolution fluorescence microscopy (SRFM) provides a better resolution than conventional fluorescence microscopy by reducing the point spread function (PSF). PSF is the light intensity distribution from a point that causes it to appear blurred. Due to PSF, each fluorescing point appears bigger than its actual size, and it is the PSF interference of nearby fluorophores that causes the blurred image. Various approaches to achieving higher resolution through SRFM have recently been...
8.2K
01:17Studying the Cytoskeleton
7.8K
The cytoskeletal architecture can be studied using different microscopic and biochemical techniques. Electron microscopy was instrumental in discovering the cytoskeletal architecture around the 1960s, which allowed obtaining structural information at a high-resolution level. However, the sample preparation procedure often limits this ability in biological samples. Several protocols have been developed over the years to optimize sample preparation. In one of the protocols known as rotary...
7.8K