Artificial Intelligence-Assisted Workflow for Transmission Electron Microscopy: Enhanced Materials Characterization

Strategic Insights -

Researchers at the Catalan Institute of Nanoscience and Nanotechnology have developed an analytical workflow to address the challenges in correlating precise atomic structure information with the functional properties of devices using scanning transmission electron microscopy (S)TEM. This workflow automates the experimental (S)TEM data analysis, providing an in-depth characterization of crystallographic information, 3D orientation, elemental composition, and strain distribution.

The researchers introduced a physics-guided artificial intelligence model to generate representative descriptions of materials and samples, enabling simulations that provide crucial insights into device behavior in practical applications. Demonstrated with SiGe planar heterostructures for scalable spin qubits, the workflow links digital twins to theoretical properties, revealing how atomic structure impacts materials and functional properties.

The versatility of the workflow is demonstrated through its application to a wide array of materials systems, device configurations, and sample morphologies.

Key Takeaways:

  • The developed analytical workflow automates the experimental (S)TEM data analysis, reducing the process from days to minutes for a trained human.
  • The workflow provides an in-depth characterization of crystallographic information, 3D orientation, elemental composition, and strain distribution.
  • The physics-guided artificial intelligence model enables the generation of representative descriptions of materials and samples.
  • The workflow links digital twins to theoretical properties, revealing how atomic structure impacts materials and functional properties.
  • The versatility of the workflow is demonstrated through its application to various materials systems, device configurations, and sample morphologies.
  • The research has been peer-reviewed and published in Advanced Materials.
  • The development of this workflow has the potential to accelerate the discovery of new materials with improved properties.

Statistics:

  • The developed workflow automates the experimental (S)TEM data analysis, reducing the process time from days to minutes.
  • The workflow characterizes crystallographic information, 3D orientation, elemental composition, and strain distribution in a single analysis.
  • The physics-guided artificial intelligence model enables the generation of representative descriptions of materials and samples.
  • The workflow has been demonstrated to work with SiGe planar heterostructures for scalable spin qubits.
  • The workflow links digital twins to theoretical properties, revealing how atomic structure impacts materials and functional properties.

Sources:

  • "Artificial Intelligence-Assisted Workflow for Transmission Electron Microscopy: From Data Analysis Automation to Materials Knowledge Unveiling." Advanced Materials, 2025.
  • Catalan Institute of Nanoscience and Nanotechnology - ICN2 (CSIC and BIST)
  • Wiley-Blackwell - www.wiley.com/
  • Advanced Materials - onlinelibrary.wiley.com/journal/10.1002/(ISSN)1521-4095